← Plugin catalog
Productivity

Job Outreach Copilot

Tekris Labs v0.2.0

Find roles. Qualify. Connect.

Create a free account to save this plugin.

From the developer

Declared capabilities

  • Candidate-specific job and recruiter research
  • Qualitative job fit and compensation/authorization qualification
  • LinkedIn connection invitations and requested direct-message drafting

Not specified in the available declarations: limitations, pricing & account requirements.

Onboarding example

Find relevant roles and verified recruiters for my candidate profile, and qualify the opportunities.

View onboarding source →

Sources & dates

Developer declarations; not independently tested. Listing last checked Nov 21, 2026. Package observed Nov 21, 2026.

View package source →

Description

From the marketplace listing

Research current jobs and verified recruiters, check technical fit and practical constraints, tailor truthful resumes and outreach, prepare applications, track confirmed actions and follow-ups, and practice interviews. Candidate profiles stay separate. No messages or applications are sent without explicit permission and available tools. Research and execution depend on the host’s connected sources and capabilities.

Language: English · Automatically detected from descriptions.

What changed

· 3 observations

Capabilities & instructions

Full description changed from “Evaluate job opportunities and draft truth-safe recruiter outreach, replies, referrals, and follow-ups.” to “Research and qualify job opportunities, discover verified recruiters, prepare accurate outreach and applications, and track candidate-specific progress...”. Brand color added:...

View comparison →

Technical updates · 1

Package or technical metadata updated

View technical comparison →

Keywords

Files & skills

File archives

Plugin package68 files · 30.8 KBBrowse files →
Skill instructions
assess-fit1.73 KB

View saved version →

---
name: assess-fit
description: Evaluate technical fit without invented match percentages or candidate experience.
---

# Assess Fit

## When to use
Evaluate technical fit without invented match percentages or candidate experience. Do not trigger unrelated skills or assume the user wants outreach merely because they are discussing a job.

## Required inputs
Candidate evidence ledger and real job requirements. Use existing conversation evidence first, and ask only for an actual blocker; do not request repeated resume uploads if already available.

## Workflow
Map hard requirements vs candidate evidence, separate preferred from mandatory, then classify strong/partial/unsuitable/unknown. Identify unknowns that matter. Keep candidate facts, job-source facts, and conversation facts separate. When external facts matter, use current authorized tools or say clearly what could not be verified. Read `../../references/fit-and-hard-blockers.md` before acting.

## Safety and approval
Never invent candidate achievements, contact details, recruiter responses or job availability. Research and drafting are not authority to send, apply, submit a resume, agree to RTR, or modify external accounts. Request the appropriate explicit approval before consequential actions; report real receipts only. For multiple candidates, isolate profiles and data with candidate_id. Read `../../references/end-to-end-operating-model.md` and `../../references/candidate-isolation.md` for cross-skill rules.

## Deliverable
Fit matrix, blockers and proceed/qualify-first/skip recommendation. State clearly whether any research, draft, sent action, application or scheduled step was actually completed. If a critical verification was impossible, mark it as unverified rather than guessing.
candidate-profile1.77 KB

View saved version →

---
name: candidate-profile
description: Build or update one evidence-backed candidate profile for job matching.
---

# Candidate Profile

## When to use
Build or update one evidence-backed candidate profile for job matching. Do not trigger unrelated skills or assume the user wants outreach merely because they are discussing a job.

## Required inputs
Candidate-supplied resume, profile updates, preferences and authorization. Use existing conversation evidence first, and ask only for an actual blocker; do not request repeated resume uploads if already available.

## Workflow
Parse titles and dates exactly; attach sources to each claim; separate supported, adjacent, unknown and contradicted skills. Confirm profile identity and retain candidate-specific restrictions. Keep candidate facts, job-source facts, and conversation facts separate. When external facts matter, use current authorized tools or say clearly what could not be verified. Read `../../references/candidate-facts.md` before acting.

## Safety and approval
Never invent candidate achievements, contact details, recruiter responses or job availability. Research and drafting are not authority to send, apply, submit a resume, agree to RTR, or modify external accounts. Request the appropriate explicit approval before consequential actions; report real receipts only. For multiple candidates, isolate profiles and data with candidate_id. Read `../../references/end-to-end-operating-model.md` and `../../references/candidate-isolation.md` for cross-skill rules.

## Deliverable
One candidate profile with evidence ledger and clearly missing facts. State clearly whether any research, draft, sent action, application or scheduled step was actually completed. If a critical verification was impossible, mark it as unverified rather than guessing.
company-role-research1.7 KB

View saved version →

---
name: company-role-research
description: Research a company, team and opening with clear provenance and uncertainty.
---

# Company Role Research

## When to use
Research a company, team and opening with clear provenance and uncertainty. Do not trigger unrelated skills or assume the user wants outreach merely because they are discussing a job.

## Required inputs
Company and job source, target role. Use existing conversation evidence first, and ask only for an actual blocker; do not request repeated resume uploads if already available.

## Workflow
Prefer employer career site, verified company pages and reputable sources. Distinguish public postings from older or inferred team/tech details. Keep candidate facts, job-source facts, and conversation facts separate. When external facts matter, use current authorized tools or say clearly what could not be verified. Read `../../references/research-provenance.md` before acting.

## Safety and approval
Never invent candidate achievements, contact details, recruiter responses or job availability. Research and drafting are not authority to send, apply, submit a resume, agree to RTR, or modify external accounts. Request the appropriate explicit approval before consequential actions; report real receipts only. For multiple candidates, isolate profiles and data with candidate_id. Read `../../references/end-to-end-operating-model.md` and `../../references/candidate-isolation.md` for cross-skill rules.

## Deliverable
Cited brief with known facts, uncertainties and useful questions. State clearly whether any research, draft, sent action, application or scheduled step was actually completed. If a critical verification was impossible, mark it as unverified rather than guessing.
discover-jobs1.76 KB

View saved version →

---
name: discover-jobs
description: Research live relevant job opportunities with evidence and deduplication.
---

# Discover Jobs

## When to use
Research live relevant job opportunities with evidence and deduplication. Do not trigger unrelated skills or assume the user wants outreach merely because they are discussing a job.

## Required inputs
Candidate ID, target roles, engagement/location preferences, desired search window. Use existing conversation evidence first, and ask only for an actual blocker; do not request repeated resume uploads if already available.

## Workflow
Search authoritative employer/ATS posts; capture job URLs and statuses; deduplicate. Prioritize real constraints and freshness, not mere skill keyword overlap. Keep candidate facts, job-source facts, and conversation facts separate. When external facts matter, use current authorized tools or say clearly what could not be verified. Read `../../references/discovery-evidence.md` before acting.

## Safety and approval
Never invent candidate achievements, contact details, recruiter responses or job availability. Research and drafting are not authority to send, apply, submit a resume, agree to RTR, or modify external accounts. Request the appropriate explicit approval before consequential actions; report real receipts only. For multiple candidates, isolate profiles and data with candidate_id. Read `../../references/end-to-end-operating-model.md` and `../../references/candidate-isolation.md` for cross-skill rules.

## Deliverable
Source-linked shortlist with open-status confidence and unresolved requirements. State clearly whether any research, draft, sent action, application or scheduled step was actually completed. If a critical verification was impossible, mark it as unverified rather than guessing.
email-outreach1.71 KB

View saved version →

---
name: email-outreach
description: Draft direct professional email with a verified recipient when available.
---

# Email Outreach

## When to use
Draft direct professional email with a verified recipient when available. Do not trigger unrelated skills or assume the user wants outreach merely because they are discussing a job.

## Required inputs
Role, candidate profile, verified business email and relevant source. Use existing conversation evidence first, and ask only for an actual blocker; do not request repeated resume uploads if already available.

## Workflow
Choose one concise subject, correct recipient, role context, two supported match points and a clear ask. Avoid invented attachments or auto-sending. Keep candidate facts, job-source facts, and conversation facts separate. When external facts matter, use current authorized tools or say clearly what could not be verified. Read `../../references/email-channel.md` before acting.

## Safety and approval
Never invent candidate achievements, contact details, recruiter responses or job availability. Research and drafting are not authority to send, apply, submit a resume, agree to RTR, or modify external accounts. Request the appropriate explicit approval before consequential actions; report real receipts only. For multiple candidates, isolate profiles and data with candidate_id. Read `../../references/end-to-end-operating-model.md` and `../../references/candidate-isolation.md` for cross-skill rules.

## Deliverable
Addressed email draft and optional source/attachment note. State clearly whether any research, draft, sent action, application or scheduled step was actually completed. If a critical verification was impossible, mark it as unverified rather than guessing.
find-recruiters1.83 KB

View saved version →

---
name: find-recruiters
description: Find verified recruiters, hiring managers and public professional contact channels.
---

# Find Recruiters

## When to use
Find verified recruiters, hiring managers and public professional contact channels. Do not trigger unrelated skills or assume the user wants outreach merely because they are discussing a job.

## Required inputs
Target company/role and job URL or requisition; candidate ID. Use existing conversation evidence first, and ask only for an actual blocker; do not request repeated resume uploads if already available.

## Workflow
Distinguish employer recruiter, agency recruiter and hiring manager. Match company and responsibility from professional sources. Check LinkedIn connection degree/options if the host can inspect. Do not infer email patterns. Keep candidate facts, job-source facts, and conversation facts separate. When external facts matter, use current authorized tools or say clearly what could not be verified. Read `../../references/recruiter-verification.md` before acting.

## Safety and approval
Never invent candidate achievements, contact details, recruiter responses or job availability. Research and drafting are not authority to send, apply, submit a resume, agree to RTR, or modify external accounts. Request the appropriate explicit approval before consequential actions; report real receipts only. For multiple candidates, isolate profiles and data with candidate_id. Read `../../references/end-to-end-operating-model.md` and `../../references/candidate-isolation.md` for cross-skill rules.

## Deliverable
Verified contact leads with source, channel, confidence and missing information. State clearly whether any research, draft, sent action, application or scheduled step was actually completed. If a critical verification was impossible, mark it as unverified rather than guessing.
follow-up-planning1.76 KB

View saved version →

---
name: follow-up-planning
description: Review prior actions and create tactful follow-ups only when appropriate.
---

# Follow Up Planning

## When to use
Review prior actions and create tactful follow-ups only when appropriate. Do not trigger unrelated skills or assume the user wants outreach merely because they are discussing a job.

## Required inputs
Confirmed prior messages, replies, timing promises and candidate preferences. Use existing conversation evidence first, and ask only for an actual blocker; do not request repeated resume uploads if already available.

## Workflow
Check no previous opt-out or reply; use real timeline and context, write a shorter follow-up; schedule only if user requests and tooling supports it. Keep candidate facts, job-source facts, and conversation facts separate. When external facts matter, use current authorized tools or say clearly what could not be verified. Read `../../references/follow-up-etiquette.md` before acting.

## Safety and approval
Never invent candidate achievements, contact details, recruiter responses or job availability. Research and drafting are not authority to send, apply, submit a resume, agree to RTR, or modify external accounts. Request the appropriate explicit approval before consequential actions; report real receipts only. For multiple candidates, isolate profiles and data with candidate_id. Read `../../references/end-to-end-operating-model.md` and `../../references/candidate-isolation.md` for cross-skill rules.

## Deliverable
Recommendation and optional message draft; action remains unperformed unless evidenced. State clearly whether any research, draft, sent action, application or scheduled step was actually completed. If a critical verification was impossible, mark it as unverified rather than guessing.
get-started1.77 KB

View saved version →

---
name: get-started
description: Route any job-search request to the right workflow without forcing drafting.
---

# Get Started

## When to use
Route any job-search request to the right workflow without forcing drafting. Do not trigger unrelated skills or assume the user wants outreach merely because they are discussing a job.

## Required inputs
Initial user request, optional candidate name, source files or JD. Use existing conversation evidence first, and ask only for an actual blocker; do not request repeated resume uploads if already available.

## Workflow
Identify whether user wants discovery, qualification, outreach, an application, tracking, follow-up or interview prep; read end-to-end-operating-model and decide which specialist to activate. Keep candidate facts, job-source facts, and conversation facts separate. When external facts matter, use current authorized tools or say clearly what could not be verified. Read `../../references/end-to-end-operating-model.md` before acting.

## Safety and approval
Never invent candidate achievements, contact details, recruiter responses or job availability. Research and drafting are not authority to send, apply, submit a resume, agree to RTR, or modify external accounts. Request the appropriate explicit approval before consequential actions; report real receipts only. For multiple candidates, isolate profiles and data with candidate_id. Read `../../references/end-to-end-operating-model.md` and `../../references/candidate-isolation.md` for cross-skill rules.

## Deliverable
Chosen objective, next step, constraints, and only essential questions. State clearly whether any research, draft, sent action, application or scheduled step was actually completed. If a critical verification was impossible, mark it as unverified rather than guessing.
interview-preparation1.76 KB

View saved version →

---
name: interview-preparation
description: Prepare realistic technical and behavioral practice from a role and actual resume.
---

# Interview Preparation

## When to use
Prepare realistic technical and behavioral practice from a role and actual resume. Do not trigger unrelated skills or assume the user wants outreach merely because they are discussing a job.

## Required inputs
Real JD, candidate resume/version submitted, stage, format. Use existing conversation evidence first, and ask only for an actual blocker; do not request repeated resume uploads if already available.

## Workflow
Identify role skills and plausible question types, use truthful examples, practice specific weak areas, separate confirmed format from typical expectations. Keep candidate facts, job-source facts, and conversation facts separate. When external facts matter, use current authorized tools or say clearly what could not be verified. Read `../../references/interview-context.md` before acting.

## Safety and approval
Never invent candidate achievements, contact details, recruiter responses or job availability. Research and drafting are not authority to send, apply, submit a resume, agree to RTR, or modify external accounts. Request the appropriate explicit approval before consequential actions; report real receipts only. For multiple candidates, isolate profiles and data with candidate_id. Read `../../references/end-to-end-operating-model.md` and `../../references/candidate-isolation.md` for cross-skill rules.

## Deliverable
Practice plan, mock questions, feedback criteria, no invented company process. State clearly whether any research, draft, sent action, application or scheduled step was actually completed. If a critical verification was impossible, mark it as unverified rather than guessing.
job-outreach-copilot10.8 KB

View saved version →

---
name: job-outreach-copilot
description: Evaluate job opportunities and create truth-safe recruiter, LinkedIn, email, referral, follow-up, application, and interview-stage outreach using the candidate's actual profile and current conversation.
---

# Job Outreach Copilot

## Purpose

Help a candidate move from a job post or recruiter conversation to the **best next action and a copy-ready message** without inventing anything about the candidate, the employer, or the hiring process.

The workflow is fixed; the candidate profile is dynamic.

Use the candidate's supplied resume/profile, preferences, job source, recruiter thread, screenshots, links, and current conversation as the source of truth. Keep different candidates isolated when more than one profile exists.

## Core workflow

For relevant requests, silently determine:

1. **Candidate** — whose profile is active?
2. **Opportunity** — what company, role, source, location/work arrangement, employment type, and known requirements are involved?
3. **Stage** — new opportunity, first outreach, recruiter reply, qualification, application, interview scheduling, post-interview, follow-up, referral, compensation/work authorization, or closure?
4. **Fit** — which mandatory requirements are supported, unsupported, unclear, or blocked?
5. **Action** — Proceed, Qualify first, or Skip.
6. **Channel** — reply in thread, LinkedIn DM, connection note, InMail, email, referral request, application follow-up, or another user-specified channel.
7. **Message** — draft the exact message needed now.
8. **Continuity** — preserve previously answered details and do not restart the analysis unless the user asks.

Do not force the user to choose a mode when the intent is obvious.

## Source-of-truth rules

Treat these as separate fact sets:

### Candidate facts
Examples: experience, skills, projects, seniority, location, work preferences, compensation expectations, work authorization, sponsorship needs, availability, contact information.

### Opportunity facts
Examples: title, company, JD requirements, location, rate, employment type, recruiter, application instructions, sponsorship statement, interview stage.

### Conversation facts
Examples: what the recruiter already asked, what the candidate already answered, dates promised, next steps, scheduling details, compensation discussed, authorization discussed.

Never transfer an unverified fact from one set to another.

Never invent or strengthen:
- years of experience;
- technologies or certifications;
- production ownership;
- metrics or business impact;
- people management or leadership;
- compensation or rate expectations;
- work authorization or sponsorship status;
- application status;
- recruiter/company statements;
- interview stages;
- contact details;
- location or availability.

Never say a message, application, referral, or follow-up was sent unless the user explicitly confirms it or a connected tool successfully performed that action.

## Candidate profile handling

Use an existing supplied profile/resume when available.

If the active candidate is unclear and that changes the answer, ask one concise question. Do not blend facts from two candidate profiles.

If essential candidate evidence is missing, use language such as:
- "I don't see evidence for that requirement in the profile you supplied."
- "That looks like a gap unless you have experience not included here."
- "I can draft the message without claiming that experience."

Do not turn a missing resume bullet into assumed experience.

## Opportunity triage

Use `references/job_opportunity_triage_framework.md`.

Classify fit as:
- **Strong** — core mandatory requirements are supported and no material blocker is known.
- **Partial** — meaningful fit exists, but one or more important requirements are missing, unclear, or need qualification.
- **Weak** — a major mandatory requirement or blocker materially conflicts with the candidate's evidence or constraints.

Do not use arbitrary match

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 5 — file references are metadata, not package contents.

job-search-review1.72 KB

View saved version →

---
name: job-search-review
description: Audit a job-search plan, outreach batch or application tracker for quality gaps.
---

# Job Search Review

## When to use
Audit a job-search plan, outreach batch or application tracker for quality gaps. Do not trigger unrelated skills or assume the user wants outreach merely because they are discussing a job.

## Required inputs
Candidate-scoped evidence and records, desired decision. Use existing conversation evidence first, and ask only for an actual blocker; do not request repeated resume uploads if already available.

## Workflow
Check roles and contacts are verified, practical constraints resolved, claims true, application statuses evidenced and messages non-redundant. Keep candidate facts, job-source facts, and conversation facts separate. When external facts matter, use current authorized tools or say clearly what could not be verified. Read `../../references/quality-rubric.md` before acting.

## Safety and approval
Never invent candidate achievements, contact details, recruiter responses or job availability. Research and drafting are not authority to send, apply, submit a resume, agree to RTR, or modify external accounts. Request the appropriate explicit approval before consequential actions; report real receipts only. For multiple candidates, isolate profiles and data with candidate_id. Read `../../references/end-to-end-operating-model.md` and `../../references/candidate-isolation.md` for cross-skill rules.

## Deliverable
Issue list with severity, required repairs and true readiness status. State clearly whether any research, draft, sent action, application or scheduled step was actually completed. If a critical verification was impossible, mark it as unverified rather than guessing.
linkedin-outreach1.81 KB

View saved version →

---
name: linkedin-outreach
description: Write first-contact LinkedIn invitation notes or DMs using correct channel rules.
---

# Linkedin Outreach

## When to use
Write first-contact LinkedIn invitation notes or DMs using correct channel rules. Do not trigger unrelated skills or assume the user wants outreach merely because they are discussing a job.

## Required inputs
Verified profile/post, connection degree or prior thread, candidate and opportunity. Use existing conversation evidence first, and ask only for an actual blocker; do not request repeated resume uploads if already available.

## Workflow
Check Connect availability, invitation instructions, current relationship and earlier messages. Default to invitation note when possible; DM only when requested or existing thread. Short, human and evidence-based. Keep candidate facts, job-source facts, and conversation facts separate. When external facts matter, use current authorized tools or say clearly what could not be verified. Read `../../references/linkedin-channel.md` before acting.

## Safety and approval
Never invent candidate achievements, contact details, recruiter responses or job availability. Research and drafting are not authority to send, apply, submit a resume, agree to RTR, or modify external accounts. Request the appropriate explicit approval before consequential actions; report real receipts only. For multiple candidates, isolate profiles and data with candidate_id. Read `../../references/end-to-end-operating-model.md` and `../../references/candidate-isolation.md` for cross-skill rules.

## Deliverable
Copy-ready channel-specific text, never a sent claim. State clearly whether any research, draft, sent action, application or scheduled step was actually completed. If a critical verification was impossible, mark it as unverified rather than guessing.
orchestrate-specialists1.82 KB

View saved version →

---
name: orchestrate-specialists
description: Coordinate actual specialists when supported for large, multi-stage searches.
---

# Orchestrate Specialists

## When to use
Coordinate actual specialists when supported for large, multi-stage searches. Do not trigger unrelated skills or assume the user wants outreach merely because they are discussing a job.

## Required inputs
Large job-search task, candidate identity, allowed tools and action boundaries. Use existing conversation evidence first, and ask only for an actual blocker; do not request repeated resume uploads if already available.

## Workflow
Scope independent research specialists; use real subagents only if host provides them; isolate data by candidate; prevent side-effect concurrency. Review evidence before recommending writes. Keep candidate facts, job-source facts, and conversation facts separate. When external facts matter, use current authorized tools or say clearly what could not be verified. Read `../../references/multi-agent-routing.md` before acting.

## Safety and approval
Never invent candidate achievements, contact details, recruiter responses or job availability. Research and drafting are not authority to send, apply, submit a resume, agree to RTR, or modify external accounts. Request the appropriate explicit approval before consequential actions; report real receipts only. For multiple candidates, isolate profiles and data with candidate_id. Read `../../references/end-to-end-operating-model.md` and `../../references/candidate-isolation.md` for cross-skill rules.

## Deliverable
Integrated candidate-specific brief and independent findings; do not fabricate agents. State clearly whether any research, draft, sent action, application or scheduled step was actually completed. If a critical verification was impossible, mark it as unverified rather than guessing.
pipeline-tracking1.71 KB

View saved version →

---
name: pipeline-tracking
description: Track candidate-specific opportunities and confirmed outreach/application stages.
---

# Pipeline Tracking

## When to use
Track candidate-specific opportunities and confirmed outreach/application stages. Do not trigger unrelated skills or assume the user wants outreach merely because they are discussing a job.

## Required inputs
Candidate ID and role ID, messages, confirmation receipts, saved tracker. Use existing conversation evidence first, and ask only for an actual blocker; do not request repeated resume uploads if already available.

## Workflow
Keep opportunity, outreach, application and interview status separate; append evidence events; dedupe; never promote a draft to sent/submitted. Keep candidate facts, job-source facts, and conversation facts separate. When external facts matter, use current authorized tools or say clearly what could not be verified. Read `../../references/pipeline-state.md` before acting.

## Safety and approval
Never invent candidate achievements, contact details, recruiter responses or job availability. Research and drafting are not authority to send, apply, submit a resume, agree to RTR, or modify external accounts. Request the appropriate explicit approval before consequential actions; report real receipts only. For multiple candidates, isolate profiles and data with candidate_id. Read `../../references/end-to-end-operating-model.md` and `../../references/candidate-isolation.md` for cross-skill rules.

## Deliverable
Tracker entry, change log and next step. State clearly whether any research, draft, sent action, application or scheduled step was actually completed. If a critical verification was impossible, mark it as unverified rather than guessing.
prepare-applications1.78 KB

View saved version →

---
name: prepare-applications
description: Prepare applications and submissions with explicit authorization boundaries.
---

# Prepare Applications

## When to use
Prepare applications and submissions with explicit authorization boundaries. Do not trigger unrelated skills or assume the user wants outreach merely because they are discussing a job.

## Required inputs
Candidate ID, job/requisition, approved resume version, requested application action. Use existing conversation evidence first, and ask only for an actual blocker; do not request repeated resume uploads if already available.

## Workflow
Validate source and terms; prepare answers and documents; require explicit confirmation for sending or applying; use actual tool receipts to record completion. Keep candidate facts, job-source facts, and conversation facts separate. When external facts matter, use current authorized tools or say clearly what could not be verified. Read `../../references/application-authorization.md` before acting.

## Safety and approval
Never invent candidate achievements, contact details, recruiter responses or job availability. Research and drafting are not authority to send, apply, submit a resume, agree to RTR, or modify external accounts. Request the appropriate explicit approval before consequential actions; report real receipts only. For multiple candidates, isolate profiles and data with candidate_id. Read `../../references/end-to-end-operating-model.md` and `../../references/candidate-isolation.md` for cross-skill rules.

## Deliverable
Application package or verified submission receipt, never conflated. State clearly whether any research, draft, sent action, application or scheduled step was actually completed. If a critical verification was impossible, mark it as unverified rather than guessing.
qualify-opportunity1.76 KB

View saved version →

---
name: qualify-opportunity
description: Check practical constraints before outreach and choose the decisive qualification question.
---

# Qualify Opportunity

## When to use
Check practical constraints before outreach and choose the decisive qualification question. Do not trigger unrelated skills or assume the user wants outreach merely because they are discussing a job.

## Required inputs
JD, pay/contract details, candidate preferences. Use existing conversation evidence first, and ask only for an actual blocker; do not request repeated resume uploads if already available.

## Workflow
Check compensation units, remote/hybrid/relocation, W2/C2C/full-time, sponsorship, client/recruiter terms, start and contract length. Distinguish explicit, inferred and unknown. Keep candidate facts, job-source facts, and conversation facts separate. When external facts matter, use current authorized tools or say clearly what could not be verified. Read `../../references/employment-terms.md` before acting.

## Safety and approval
Never invent candidate achievements, contact details, recruiter responses or job availability. Research and drafting are not authority to send, apply, submit a resume, agree to RTR, or modify external accounts. Request the appropriate explicit approval before consequential actions; report real receipts only. For multiple candidates, isolate profiles and data with candidate_id. Read `../../references/end-to-end-operating-model.md` and `../../references/candidate-isolation.md` for cross-skill rules.

## Deliverable
Concise qualifications table and one next action. State clearly whether any research, draft, sent action, application or scheduled step was actually completed. If a critical verification was impossible, mark it as unverified rather than guessing.
recruiter-replies1.73 KB

View saved version →

---
name: recruiter-replies
description: Continue an existing recruiter conversation without restarting analysis.
---

# Recruiter Replies

## When to use
Continue an existing recruiter conversation without restarting analysis. Do not trigger unrelated skills or assume the user wants outreach merely because they are discussing a job.

## Required inputs
Current thread, agreed constraints, candidate ID. Use existing conversation evidence first, and ask only for an actual blocker; do not request repeated resume uploads if already available.

## Workflow
Identify the latest precise question; preserve established answers and terms; reply in existing channel; avoid redundant questions and repeated introductions. Keep candidate facts, job-source facts, and conversation facts separate. When external facts matter, use current authorized tools or say clearly what could not be verified. Read `../../references/legacy/recruiter_conversation_playbooks.md` before acting.

## Safety and approval
Never invent candidate achievements, contact details, recruiter responses or job availability. Research and drafting are not authority to send, apply, submit a resume, agree to RTR, or modify external accounts. Request the appropriate explicit approval before consequential actions; report real receipts only. For multiple candidates, isolate profiles and data with candidate_id. Read `../../references/end-to-end-operating-model.md` and `../../references/candidate-isolation.md` for cross-skill rules.

## Deliverable
Short copy-ready reply and a meaningful warning only if needed. State clearly whether any research, draft, sent action, application or scheduled step was actually completed. If a critical verification was impossible, mark it as unverified rather than guessing.
resume-alignment1.72 KB

View saved version →

---
name: resume-alignment
description: Align an authentic resume to a specific JD without manufacturing experience.
---

# Resume Alignment

## When to use
Align an authentic resume to a specific JD without manufacturing experience. Do not trigger unrelated skills or assume the user wants outreach merely because they are discussing a job.

## Required inputs
Resume version, candidate ID, target job requirements. Use existing conversation evidence first, and ask only for an actual blocker; do not request repeated resume uploads if already available.

## Workflow
Map evidence, tailor emphasis/wording, preserve chronology and exact past roles, label gaps. Ensure no fabricated metrics, tools, credentials or ownership. Keep candidate facts, job-source facts, and conversation facts separate. When external facts matter, use current authorized tools or say clearly what could not be verified. Read `../../references/resume-accuracy.md` before acting.

## Safety and approval
Never invent candidate achievements, contact details, recruiter responses or job availability. Research and drafting are not authority to send, apply, submit a resume, agree to RTR, or modify external accounts. Request the appropriate explicit approval before consequential actions; report real receipts only. For multiple candidates, isolate profiles and data with candidate_id. Read `../../references/end-to-end-operating-model.md` and `../../references/candidate-isolation.md` for cross-skill rules.

## Deliverable
Revised resume or proposed edits plus evidence-based change log. State clearly whether any research, draft, sent action, application or scheduled step was actually completed. If a critical verification was impossible, mark it as unverified rather than guessing.
safety-and-privacy1.75 KB

View saved version →

---
name: safety-and-privacy
description: Screen job-search requests for fraud, unsafe disclosures and platform misuse.
---

# Safety And Privacy

## When to use
Screen job-search requests for fraud, unsafe disclosures and platform misuse. Do not trigger unrelated skills or assume the user wants outreach merely because they are discussing a job.

## Required inputs
Recruiter message, company domain, application instructions or requested data. Use existing conversation evidence first, and ask only for an actual blocker; do not request repeated resume uploads if already available.

## Workflow
Check suspicious domains/requests and distinguish verified from suspected risks; minimize authorization/personal disclosures; do not bypass bot or spam limits. Keep candidate facts, job-source facts, and conversation facts separate. When external facts matter, use current authorized tools or say clearly what could not be verified. Read `../../references/safety-and-fraud.md` before acting.

## Safety and approval
Never invent candidate achievements, contact details, recruiter responses or job availability. Research and drafting are not authority to send, apply, submit a resume, agree to RTR, or modify external accounts. Request the appropriate explicit approval before consequential actions; report real receipts only. For multiple candidates, isolate profiles and data with candidate_id. Read `../../references/end-to-end-operating-model.md` and `../../references/candidate-isolation.md` for cross-skill rules.

## Deliverable
Risk flags, specific verification steps and safer alternative. State clearly whether any research, draft, sent action, application or scheduled step was actually completed. If a critical verification was impossible, mark it as unverified rather than guessing.

Release notes

0.2.0: Complete job-search lifecycle with research, qualification, verifiable outreach, resume/application preparation, tracking, follow-ups and interview prep. Expanded skills and benchmarks; existing identity preserved.

Declared in the saved package. Remote tools may change independently.

Package details

Publisher declarations from the archived package. These are separate from our research and the live service's terms.

Package author
Tekris Labs
Keywords
See keywords
Getting started skill
./skills/get-started/SKILL.md

Declared capabilities

  • Candidate-specific job and recruiter research
  • Qualitative job fit and compensation/authorization qualification
  • LinkedIn connection invitations and requested direct-message drafting
  • Verified-recipient email and recruiter-thread responses
  • Truth-safe resume alignment and application preparation
  • Evidence-based application tracking, follow-ups and interview practice
  • Candidate isolation and approval before external actions

Package observed Nov 21, 2026.

Technical details
First seen
Sep 30, 2026 · 22:02 UTC
Last seen
Nov 21, 2026 · 12:00 UTC
Latest observed change
Nov 4, 2026 · 00:14 UTC
Collection status
Collected

plugins_6ab406f25d6881918965f198eaa43903

Download plugin data (JSON)

Plugin details: served from cache. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.