Agent skills that run json, that ask for Task

Skills declare what they need inconsistently: 58.8% name the languages they run, 11.2% list the tools they ask for, and 4.6% give themselves a category. Filtering narrows to the ones that said so, never to the ones that are.

1. dev-pipelinenexus-substrate/nexus-agents

   Multi-agent development pipeline (Orchestrator + workers + consensus vote). Use when the user asks to "build a feature", "fix a bug with the pipeline", or "run the dev pipeline". T

   pluginjsonReadWriteEdit
2. docs-writermaximhq/bifrost

   Write, update, and review Mintlify MDX documentation for Bifrost features. Explores the full codebase (UI, Go backend, config schema), validates config.json examples, places screen

   claude-codebashjsonmarkdownmdxReadGrepGlob
3. auto-review-loopwanshuiyin/Auto-claude-code-research-in-sleep

   Autonomous multi-round research review loop. In Copilot CLI it defaults to the native complementary rubber-duck subagent with host-event model evidence; elsewhere it uses Codex, wh

   otherbashjsonjsonlmarkdownBash(*)ReadGrep+4 files
4. pdcaww-w-ai/bkit-claude-code

   Unified PDCA cycle management — plan, design, do, analyze, iterate, report. PDCA runs per-feature (9-phase: pm→plan→design→do→check→act→qa→report→archive); for multi-feature scope/

   pluginbashjsonReadWriteEdit
5. pdca-batchww-w-ai/bkit-claude-code

   Manage multiple PDCA features as independent parallel cycles (no shared scope/budget). For multiple features that share scope, budget, or timeline as one cohesive initiative, use /

   pluginbashjsonReadWriteGlob
6. team-coordinationbybren-llc/safe-agentic-workflow

   Agent Teams orchestration patterns for multi-agent SAFe workflows. Use when spawning agent teams, coordinating teammates, enforcing quality gates via task dependencies, or orchestr

   claude-codejsonReadBashGrep
7. patinadevswha/patina

   Detect and rewrite AI writing patterns in Korean, English, Chinese, and Japanese text so it reads as if a human wrote it. Meaning-preservation (MPS) verified.

   pluginbashjsonReadWriteEdit
8. issue-orchestratoranthony-chaudhary/fak

   Plan, partition, and coordinate multi-wave parallel subagent campaigns to resolve and close GitHub issues across the repository. Uses `fak issue-orchestrator --plan-waves` (or `fak

   claude-codebashjsonReadBashWrite+2 files
9. issue-queueanthony-chaudhary/fak

   One repeatable, evidence-backed pass that manages, prioritizes, and resolves a bounded batch of backlog issues worst-first using specialized subagents. Inspects the issue queue via

   claude-codebashjsonReadBashWrite
10. git-subagent-syncanthony-chaudhary/fak

    Synchronize subagent changes to git on shared trunk across all lanes and all untracked WIP by default (or scoped via --lane/--paths). Enforces single-source invariants, safe merge

    claude-codebashjsonReadBashWrite
11. nav-skill-creatoralekspetrov/navigator

    Analyze codebase patterns and create custom skills for repetitive workflows. Use when project needs automation or pattern enforcement. Auto-invoke when user says "create a skill fo

    pluginbashjsonmarkdownpythonReadWriteEdit
12. product-designalekspetrov/navigator

    Automates design review, token extraction, component mapping, and implementation planning. Reduces design handoff from 6-10 hours to 5 minutes via direct Figma MCP integration. Aut

    pluginbashjsonmarkdownpythonReadWriteEdit
13. ideasflonat/flonat-research

    Capture and integrate improvement ideas for the shared Claude Code and Codex infrastructure. Use when recording an infrastructure enhancement for later review rather than implement

    otherjsonmarkdownReadWriteEdit
14. skill-creatorflonat/flonat-research

    Create, revise, and evaluate reusable AI workflow skills, including trigger-quality tests. Use when authoring a new skill, repairing an existing skill, or measuring whether its met

    otherbashjsonmarkdownReadWriteEdit+3 files
15. bob-diff-reviewvmihalis/hacker-bob

    Headless Bob diff-review pipeline — invoked by bob-runner.ts via 'claude --dangerously-skip-permissions --print "/bob-diff-review -- ..."'. Ingests a unified diff, initializes a Bo

    claude-codebashjsonReadWriteTask
16. starknet-identitykeep-starknet-strange/starknet-agentic

    Register AI agents on-chain using the ERC-8004 Trustless Agents standard. Manage agent identity as NFTs, build reputation through feedback, and request third-party validation.

    pluginbashjsontypescriptBashReadWrite+1 files
17. starknet-anonymous-walletkeep-starknet-strange/starknet-agentic

    Create an anonymous Starknet wallet via Typhoon and interact with Starknet contracts. Privacy-focused wallet creation for agents requiring anonymity.

    pluginbashjavascriptjsonBashReadWrite+1 files
18. starknet-walletkeep-starknet-strange/starknet-agentic

    Create and manage Starknet wallets for AI agents. Transfer tokens, check balances, manage session keys, deploy accounts, and interact with smart contracts using native Account Abst

    pluginbashjsontypescriptBashReadWrite+1 files
19. creview-specjoshft/correctless

    Multi-agent adversarial review of a spec. Spawns red team, assumptions auditor, testability auditor, design contract checker, and UX auditor. Use after /cspec or /cmodel.

    pluginbashjsonmarkdownReadGrepGlob
20. cdebugjoshft/correctless

    Structured bug investigation workflow. Root cause analysis, hypothesis testing, TDD fix with agent separation, escalation after 3 failed attempts. Use when stuck on a bug.

    pluginbashjsonmarkdownReadGrepGlob
21. cchoresjoshft/correctless

    Fully-autonomous issue-resolution pipeline. Selects one open GitHub issue, branches off the fresh default branch, delegates root-cause + TDD fix to /cdebug (autonomous mode), verif

    pluginbashjsonReadGrepGlob
22. cautojoshft/correctless

    Semi-auto mode. Orchestrates the full implementation pipeline after human-approved spec review. Runs ctdd, simplify, cverify, cupdate-arch, cdocs, then creates a PR. After /cauto c

    pluginbashjsonyamlReadGrepGlob
23. cspecjoshft/correctless

    Create a structured specification with testable invariants for a new feature. Researches current best practices before writing invariants. Adapts format to workflow intensity.

    pluginbashjsonmarkdownReadGrepGlob
24. ctddjoshft/correctless

    Enforced TDD workflow. Write failing tests from spec rules, then implement. Use after /creview approves a spec.

    pluginbashjsonReadGrepGlob
25. verify-uiThisIsSadeghi/KMPilot

    Verify UI implementation against Stitch design via a token audit (HTML ↔ Code, with X-component default-render checks) and an X-components compliance check.

    claude-codebashjsonmarkdownTaskReadWrite
26. start-qarlajous/claude-code-commands

    Execute QA tests from plan file

    pluginbashjavascriptjsonyamlReadTaskBash+1 files
27. mega-planTaoidle/plan-cascade

    Project-level multi-task orchestration system. Manages multiple hybrid:worktree features in parallel with dependency resolution, coordinated PRD generation, and unified merge workf

    pluginbashjsonReadWriteEdit+2 files
28. sast-drivenscadastrangelove/rust-in-peace

    The SAST-driven find mode — a fourth, deliberately ISOLATED pass alongside blind / threat-model / CVE-seeded. Runs every static-analysis engine with its DEFAULT rules out of the bo

    claude-codebashjsonReadGlobGrep
29. triagescadastrangelove/rust-in-peace

    Triage a batch of raw security findings. Verify each is real, collapse duplicates, re-rank by derived exploitability, and tag with an owner. Takes a directory or file of scanner ou

    claude-codejsonReadGlobGrep
30. patchscadastrangelove/rust-in-peace

    Generate candidate fixes for verified security findings. Consumes TRIAGE.json (preferred), VULN-FINDINGS.json, or a vuln-pipeline results directory. Pipeline input is delegated to

    claude-codejsonmarkdownReadGlobGrep
31. vuln-scanscadastrangelove/rust-in-peace

    Static source-code vulnerability scan. Reads a target directory (and THREAT_MODEL.md if present), spawns parallel review subagents per focus area, and writes VULN-FINDINGS.json + .

    claude-codejsonReadGlobGrep
32. sweepenapt/SwarmLLM

    Deploy parallel agents to scan the entire codebase for dead code, duplication, inconsistencies, and stale references

    claude-codejsonReadWriteGrep
33. diagnosetranhieutt/software_development_department
    claude-codejsonjsonlReadGlobGrep
34. crewarpitnath/claude-capsule-kit

    Orchestrate multi-agent teams for parallel multi-branch work. Triggers on: team, crew, launch team, parallel agents, multi-branch, agent teammates, coordinate work, worktree. Handl

    otherbashjsonTaskBashRead
35. interview-meSorbh/interview-me

    Deep-dive spec interviewer. Reads a file, GitHub issue, or requirement, analyzes it against the codebase, then conducts a rigorous 1-on-1 interview using AskUserQuestion to produce

    pluginjsonmarkdownReadGlobGrep
36. add-skillfredericvilcot/clean-claude

    Add specialized craft skills to agents. Default craft principles always active. Everything MUST respect the craft philosophy.

    claude-codebashjsontypescriptReadWriteBash
37. agentfredericvilcot/clean-claude

    Start a Clean Claude agent with optional reactive links. Examples: /agent frontend-engineer, /agent frontend-engineer --link qa-engineer, /agent architect --link frontend-engineer,

    claude-codebashjsonReadWriteBash
38. craftfredericvilcot/clean-claude

    Craft something. Claude orchestrates, agents execute.

    claude-codejsonReadWriteEdit
39. healfredericvilcot/clean-claude

    Auto-repair with smart routing: test failures → Dev, type errors → Architect, spec gaps → PO. Routes each problem to the right expert.

    claude-codebashjsonjsonlmarkdownReadBashTask
40. devteam-planmichael-harris/devteam

    Conduct interactive requirements gathering, research the codebase, create a PRD, and generate a development plan with tasks and sprints.

    pluginbashjavascriptjsonmarkdownReadGlobGrep
41. ai-video-producerzysilm/video-producer-skill

    AI video production workflow using Google Flow via MCP Playwright browser automation. Creates any video type: promotional, educational, narrative, social media, animations, game tr

    pluginbashjsonmarkdownpythonReadWriteEdit

Browse all 69,865 skills →200 at a time, grouped by owner. The list above is the skills with the highest standing; this is every one of them.

The whole corpus is one call away through the search API, or ask a question of it on the index itself.