{"data":[{"slug":"blueprint-sdlc","title":"blueprint-sdlc","description":"Blueprint SDLC — 27 slash commands that turn Claude Code into a disciplined engineering team. Full pipeline from /backlog through   /finish with 15-rule audit hooks, parallel subagent execution, and session crash recovery.","developer":"Shirleyson Kaisser","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/skaisser/blueprint-plugin.git"},{"slug":"better-dev","title":"better-dev","description":"[meta] better development: CSS workflows, Firebase development, code quality, real testing, parallel exploration, documentation verification, and token-efficient codegen","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"2389-research/claude-plugins"},{"slug":"backend-security-skills","title":"backend-security-skills","description":"Security auditor for Node.js and Python backend APIs. Four skills cover pre-audit reconnaissance (route graph, auth matrix, invariants), static code audit across the OWASP API Security Top 10 via 8 parallel agents (authz / authn / injection / deserialization-and-ssrf / crypto-and-secrets / resource-and-business-logic / config-and-supply-chain / llm-and-integration), and live HTTP probing that verifies findings with reproducible curl transcripts. Outputs markdown or JSON with severity + CWE + OWASP API Top 10 tags per finding. Built for Express, NestJS, Fastify, Koa, Next.js, FastAPI, Django, Flask, and Starlette.","developer":"Marcus Souza","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/souzavinny/backend-security-skills.git"},{"slug":"auto-research","title":"auto-research","description":"Autonomous skill improvement through parallel research agents. Inspired by Karpathy's autoresearch methodology, it spawns 5 parallel agents (domain expert, quality auditor, competitive analyst, gap analyst, tech scout), synthesizes findings\ninto ranked proposals, then runs an iterative keep/discard experiment loop to improve any Claude Code skill. Scores skills on 7 quality dimensions and only keeps changes that genuinely improve the composite score.","developer":"gyoz-ai","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/gyoz-ai/auto-research.git"},{"slug":"arcanum","title":"arcanum","description":"Advanced debugging, code review, deep research, technical documentation, creative ideation, and semi-autonomous development workflows with parallel theory validation, team-based research, war room investigation, root cause analysis, PR review assistance, elite technical writing, and Maestro development pipeline","developer":"Eric Burns","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/burnsbert/claude-arcanum.git"},{"slug":"alley-oop","title":"alley-oop","description":"Alley Oop keeps your development momentum going across sessions without the cost of replaying full conversation history. When you're ready to hand off, /alley distills your current session into a compact cold-start prompt — capturing just what the next session needs to orient and act immediately. Start the new session with /oop and you're back in the game. For parallel workstreams, /alleyarchive and /ooparchive let you branch, archive, and resume multiple threads independently.","developer":"Alley Oop","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/1azarus/alley-oop.git"},{"slug":"agentops","title":"agentops","description":"Enterprise guardrails, delivery lifecycle, and self-evolution for Claude Code. Wraps every session in 7 security layers (path validation, command validation, injection scanning, credential redaction, exfiltration detection), structures work with the STAR methodology, and orchestrates full project builds from vision to merged PR through an 8.5-phase lifecycle with TDD enforcement, wave-based parallel execution, and two-stage code review. Includes 37 commands, 44 hooks, 12 specialist agents, 49 templates, and 32+ feature flags.","developer":"Gareth Daine","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/garethdaine/agentops.git"},{"slug":"agent-manager","title":"agent-manager","description":"Spawn and manage autonomous background agents with persistent state across sessions","developer":"Himanshu Lohani","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/devhimanshulohani/claude-agent-manager.git"},{"slug":"agent-estimate","title":"agent-estimate","description":"Effort estimation for AI coding agents. PERT three-point estimation with METR reliability thresholds, modifier stacks (spec clarity, warm context, agent fit), and wave planning for multi-agent parallel execution. Supports single tasks, batch files, and GitHub issues.","developer":"Kiloloop","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/haoranc/agent-estimate.git"},{"slug":"16minds","title":"16minds","description":"16-minds summons agents modeled on 16 distinct personality types — each with its own values, thinking patterns, and tone — to debate, review, or advise on any topic. Each personality is written directly into an independent prompt, so outputs carry visibly different voices instead of the averaged answer a single agent tends to produce.\n\nThree commands cover the range:\n  - /mind <type> — a single type's opinion\n  - /pair <a> <b> — a two-type debate (open → rebut → reply / synthesize)\n  - /minds — fan out to all 16 in parallel, then synthesize\n\nThree modes (light / middle / heavy) trade depth for token cost.\n\nThe /minds synthesis follows a fixed 4-section rubric — score distribution, axes of disagreement, easily-overlooked perspectives, and landing-zone candidates with per-candidate \"types likely to agree / fit / risk\" — to keep 16-voice output structured rather than scattershot. The --save flag writes the full execution log to a file for use as article material or decision logs.\n\nBuilt for decisions where a single averaged answer would lose the edges: idea generation, design judgment, code review, and life/career questions.","developer":"yukurash","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/yukurash/16minds-plugin.git"}],"total":82,"page":3,"per_page":36,"observed_at":"2026-11-08T00:00:01.297Z","source_counts":{"web":529,"demo":12,"skills":5,"official":317,"community":2283,"knowledge-work":123}}