← Claus Argos Skill OSCONTENT HISTORY

Update to Claus Argos Skill OS

Snapshot Nov 21, 2026 · 00:11 UTC · version 1.16.1

Collection source: downloaded plugin package. These snapshots do not have a confirmed matching collection source. Differences in file lists alone do not establish changes to the package.

WHAT CHANGED

Instructions updated for compose-role-teams

Skill instructions — Now says: Define role responsibilities from the task, available expertise and user constraints. State who can recommend, approve or act; do not infer permissions from...

Observed in instructions or declared skills. Runtime behavior has not been tested.

Save Claus Argos Skill OS and check future changes in Following.

Up to 3 plugins free · no card required.

All fields and original values.

Skill instructions

Before

Sep 30, 2026 · 23:14 UTC

Apply the shared [expert standard](../../shared/expert-system/expert-standard.md), [role registry](../../shared/expert-system/expert-role-registry.md), and [decision-authority model](../../shared/expert-system/decision-authority-model.md...

After

Nov 21, 2026 · 00:11 UTC

Define role responsibilities from the task, available expertise and user constraints. State who can recommend, approve or act; do not infer permissions from a role title. - Keep live project scheduling and execution management separate f...

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -26,8 +26,8 @@
 - Keep research, creation, approval, and criticism separate only when that separation improves reliability.
 - Avoid role-play that obscures uncertainty or source limitations.
 - Preserve explicit exclusions and tool/permission boundaries.
-- Apply the shared [expert standard](../../shared/expert-system/expert-standard.md), [role registry](../../shared/expert-system/expert-role-registry.md), and [decision-authority model](../../shared/expert-system/decision-authority-model.md) when they fit the requested blueprint.
-- Route live project, phase, and task expert selection to `$orchestrate-projects`; this skill produces the reusable team contract and does not manage project execution.
+- Define role responsibilities from the task, available expertise and user constraints. State who can recommend, approve or act; do not infer permissions from a role title.
+- Keep live project scheduling and execution management separate from this reusable team blueprint. Define project-specific responsibilities before anyone acts.
 
 ## Output
 
Full technical diff · 1 changed fields

changed /skill_md_contents

BEFORE
"---\nname: compose-role-teams\ndescription: Create or audit a reusable expert-role blueprint or role prompt with responsibilities, decision rights, conflicts, handoffs, and quality criteria. Use when the deliverable itself is a role team, department simulation, AI persona configuration, or repair of a prompt containing vague or overlapping roles. Do not use for live multi-phase project orchestration, where expert roles must be routed dynamically by task.\n---\n\n# Compose Role Teams\n\nTurn an objective into a functional team, not a theatrical list of titles.\n\n## Workflow\n\n1. Extract the objective, deliverable, domain, audience, risk, research need, execution stages, and final decision owner.\n2. List required capabilities before naming roles.\n3. Group related capabilities. Create a role only when it owns a distinct decision, artifact, evidence source, or quality gate.\n4. Default to three to five roles: lead, domain specialist, researcher/analyst when evidence matters, executor/designer, and critic/compliance reviewer when risk warrants it.\n5. Define for each role: mission, inputs, outputs, authority, prohibitions, success criteria, and handoff.\n6. Define disagreement priority. The lead integrates; safety, law, verified evidence, and explicit user constraints outrank style or optimization.\n7. Run the tests in `references/role-tests.md`. Merge redundant roles and add missing ownership.\n8. Deliver either a role blueprint, a copy-ready role prompt, or an audit of an existing role list.\n\n## Rules\n\n- Prefer responsibilities over claims such as “world-class expert.”\n- Never imply professional licensure. Require qualified human review in regulated or high-stakes contexts.\n- Do not create a role solely to repeat another role's review.\n- Keep research, creation, approval, and criticism separate only when that separation improves reliability.\n- Avoid role-play that obscures uncertainty or source limitations.\n- Preserve explicit exclusions and tool/permission boundaries.\n- Apply the shared [expert standard](../../shared/expert-system/expert-standard.md), [role registry](../../shared/expert-system/expert-role-registry.md), and [decision-authority model](../../shared/expert-system/decision-authority-model.md) when they fit the requested blueprint.\n- Route live project, phase, and task expert selection to `$orchestrate-projects`; this skill produces the reusable team contract and does not manage project execution.\n\n## Output\n\nReturn:\n\n1. Objective and assumptions\n2. Capability map\n3. Role table: role, ownership, inputs, output, authority, handoff\n4. Conflict and escalation rules\n5. Copy-ready team instruction when requested\n6. Lean-team check: roles merged, omitted, or conditional\n\nRead `references/role-tests.md` when building or auditing a team.\n"
AFTER
"---\nname: compose-role-teams\ndescription: Create or audit a reusable expert-role blueprint or role prompt with responsibilities, decision rights, conflicts, handoffs, and quality criteria. Use when the deliverable itself is a role team, department simulation, AI persona configuration, or repair of a prompt containing vague or overlapping roles. Do not use for live multi-phase project orchestration, where expert roles must be routed dynamically by task.\n---\n\n# Compose Role Teams\n\nTurn an objective into a functional team, not a theatrical list of titles.\n\n## Workflow\n\n1. Extract the objective, deliverable, domain, audience, risk, research need, execution stages, and final decision owner.\n2. List required capabilities before naming roles.\n3. Group related capabilities. Create a role only when it owns a distinct decision, artifact, evidence source, or quality gate.\n4. Default to three to five roles: lead, domain specialist, researcher/analyst when evidence matters, executor/designer, and critic/compliance reviewer when risk warrants it.\n5. Define for each role: mission, inputs, outputs, authority, prohibitions, success criteria, and handoff.\n6. Define disagreement priority. The lead integrates; safety, law, verified evidence, and explicit user constraints outrank style or optimization.\n7. Run the tests in `references/role-tests.md`. Merge redundant roles and add missing ownership.\n8. Deliver either a role blueprint, a copy-ready role prompt, or an audit of an existing role list.\n\n## Rules\n\n- Prefer responsibilities over claims such as “world-class expert.”\n- Never imply professional licensure. Require qualified human review in regulated or high-stakes contexts.\n- Do not create a role solely to repeat another role's review.\n- Keep research, creation, approval, and criticism separate only when that separation improves reliability.\n- Avoid role-play that obscures uncertainty or source limitations.\n- Preserve explicit exclusions and tool/permission boundaries.\n- Define role responsibilities from the task, available expertise and user constraints. State who can recommend, approve or act; do not infer permissions from a role title.\n- Keep live project scheduling and execution management separate from this reusable team blueprint. Define project-specific responsibilities before anyone acts.\n\n## Output\n\nReturn:\n\n1. Objective and assumptions\n2. Capability map\n3. Role table: role, ownership, inputs, output, authority, handoff\n4. Conflict and escalation rules\n5. Copy-ready team instruction when requested\n6. Lean-team check: roles merged, omitted, or conditional\n\nRead `references/role-tests.md` when building or auditing a team.\n"
Full snapshot data
{
  "description": "Create or audit a reusable expert-role blueprint or role prompt with responsibilities, decision rights, conflicts, handoffs, and quality criteria. Use when the deliverable itself is a role team, department simulation, AI persona configuration, or repair of a prompt containing vague or overlapping roles. Do not use for live multi-phase project orchestration, where expert roles must be routed dynamically by task.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 227
    },
    {
      "relative_path": "references/role-tests.md",
      "size_in_bytes": 1250
    }
  ],
  "name": "compose-role-teams",
  "skill_md_contents": "---\nname: compose-role-teams\ndescription: Create or audit a reusable expert-role blueprint or role prompt with responsibilities, decision rights, conflicts, handoffs, and quality criteria. Use when the deliverable itself is a role team, department simulation, AI persona configuration, or repair of a prompt containing vague or overlapping roles. Do not use for live multi-phase project orchestration, where expert roles must be routed dynamically by task.\n---\n\n# Compose Role Teams\n\nTurn an objective into a functional team, not a theatrical list of titles.\n\n## Workflow\n\n1. Extract the objective, deliverable, domain, audience, risk, research need, execution stages, and final decision owner.\n2. List required capabilities before naming roles.\n3. Group related capabilities. Create a role only when it owns a distinct decision, artifact, evidence source, or quality gate.\n4. Default to three to five roles: lead, domain specialist, researcher/analyst when evidence matters, executor/designer, and critic/compliance reviewer when risk warrants it.\n5. Define for each role: mission, inputs, outputs, authority, prohibitions, success criteria, and handoff.\n6. Define disagreement priority. The lead integrates; safety, law, verified evidence, and explicit user constraints outrank style or optimization.\n7. Run the tests in `references/role-tests.md`. Merge redundant roles and add missing ownership.\n8. Deliver either a role blueprint, a copy-ready role prompt, or an audit of an existing role list.\n\n## Rules\n\n- Prefer responsibilities over claims such as “world-class expert.”\n- Never imply professional licensure. Require qualified human review in regulated or high-stakes contexts.\n- Do not create a role solely to repeat another role's review.\n- Keep research, creation, approval, and criticism separate only when that separation improves reliability.\n- Avoid role-play that obscures uncertainty or source limitations.\n- Preserve explicit exclusions and tool/permission boundaries.\n- Define role responsibilities from the task, available expertise and user constraints. State who can recommend, approve or act; do not infer permissions from a role title.\n- Keep live project scheduling and execution management separate from this reusable team blueprint. Define project-specific responsibilities before anyone acts.\n\n## Output\n\nReturn:\n\n1. Objective and assumptions\n2. Capability map\n3. Role table: role, ownership, inputs, output, authority, handoff\n4. Conflict and escalation rules\n5. Copy-ready team instruction when requested\n6. Lean-team check: roles merged, omitted, or conditional\n\nRead `references/role-tests.md` when building or auditing a team.\n"
}

SHA-256 of public snapshot: 2cca8b76623417de3a98747aa374dbf69d1320d3ab4dc3e6fc39f1c676e04ef4