Agent skills that run yaml, that ask for Write, in claude-code format

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. github-project-managementruvnet/ruflo

   Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning

   claude-codebashjavascriptmarkdownyamlmcp__github__*mcp__claude-flow__*Bash
2. bat-story-evalhomeassistant-ai/ha-mcp

   Compare MCP tool behavior between target and baseline versions using pre-built and custom stories with diff-based triage.

   claude-codebashpythonyamlBashReadWrite
3. agent-creatormysleekdesigns/crawlforge-mcp

   Creates new Claude Code agent configurations from user requirements. Translates task descriptions into precisely-tuned agent .md files with expert personas, system prompts, and opt

   claude-codemarkdownyamlReadWriteEdit
4. helm-updatemaximhq/bifrost

   Apply helm chart updates for Bifrost. Detects config.schema.json changes since the last helm release, applies user-requested changes, updates values.yaml / values.schema.json / _he

   claude-codebashgo-templatejsonmarkdownReadGrepGlob
5. api-validatormaximhq/bifrost

   Scan Bifrost HTTP controllers/handlers/integrations and validate OpenAPI API coverage, route methods/paths, parameters, request/response docs, and auth/security information. Use wh

   claude-codebashmarkdownyamlReadGrepGlob
6. sprint-planDonchitos/Claude-Code-Game-Studios

   Generates a new sprint plan or updates an existing one based on the current milestone, completed work, and available capacity. Pulls context from production documents and design ba

   claude-codemarkdownyamlReadGlobGrep
7. version-bumpBenedictKing/ccx

   升级项目版本号并提交git，支持patch/minor/major版本升级或指定具体版本号，自动从git log生成CHANGELOG

   claude-codebashmarkdownyamlBashReadWrite
8. moai-workflow-dddmodu-ai/moai-adk

   Domain-Driven Development workflow specialist using ANALYZE-PRESERVE-IMPROVE cycle for behavior-preserving code transformation. Use when refactoring legacy code or reducing technic

   claude-codeyamlReadWriteEdit
9. moai-workflow-tddmodu-ai/moai-adk

   Test-Driven Development workflow specialist using RED-GREEN-REFACTOR cycle for test-first software development. Use when developing new features from scratch or when behavior speci

   claude-codeyamlReadWriteEdit
10. promptscriptmrwogu/promptscript

    PromptScript language expert for reading, writing, modifying, and troubleshooting .prs files. Use when working with PromptScript syntax, creating or editing .prs files, adding bloc

    claude-codepromptscriptyamlReadWriteGlob
11. exploreparcadei/Continuous-Claude-v3

    Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)

    claude-codebashmarkdownpythonyamlBashTaskRead
12. fixparcadei/Continuous-Claude-v3

    Meta-skill workflow orchestrator for bug investigation and resolution. Routes to debug, implement, test, and commit based on scope.

    claude-codebashmarkdownyamlBashReadGrep
13. skill-developerparcadei/Continuous-Claude-v3

    Meta-skill for creating and managing Claude Code skills

    claude-codebashjsonmarkdownpythonBashReadWrite
14. sub-agentsparcadei/Continuous-Claude-v3

    Create and configure Claude Code sub-agents with custom prompts, tools, and models

    claude-codebashyamlReadWriteBash
15. tdd-migrateparcadei/Continuous-Claude-v3

    TDD workflow for migrations - orchestrate agents, zero main context growth

    claude-codebashyamlTaskTodoWriteWrite
16. research-externalparcadei/Continuous-Claude-v3

    External research workflow for docs, web, APIs - NOT codebase exploration

    claude-codebashmarkdownyamlBashReadWrite
17. skill-upgraderparcadei/Continuous-Claude-v3

    Upgrade any skill to v5 Hybrid format using decision theory + modal logic

    claude-codebashmarkdownyamlBashReadWrite
18. slash-commandsparcadei/Continuous-Claude-v3

    Create and use Claude Code slash commands - quick prompts, bash execution, file references

    claude-codebashmarkdownyamlReadWriteBash
19. slash-commandsvibeeval/vibecosystem

    Create and use Claude Code slash commands - quick prompts, bash execution, file references

    claude-codebashmarkdownyamlReadWriteBash
20. research-externalvibeeval/vibecosystem

    External research workflow for docs, web, APIs - NOT codebase exploration

    claude-codebashmarkdownyamlBashReadWrite
21. explorevibeeval/vibecosystem

    Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)

    claude-codebashmarkdownpythonyamlBashTaskRead
22. fixvibeeval/vibecosystem

    Meta-skill workflow orchestrator for bug investigation and resolution. Routes to debug, implement, test, and commit based on scope.

    claude-codebashmarkdownyamlBashReadGrep
23. skill-developervibeeval/vibecosystem

    Meta-skill for creating and managing Claude Code skills

    claude-codebashjsonmarkdownpythonBashReadWrite
24. skill-upgradervibeeval/vibecosystem

    Upgrade any skill to v5 Hybrid format using decision theory + modal logic

    claude-codebashmarkdownyamlBashReadWrite
25. tdd-migratevibeeval/vibecosystem

    TDD workflow for migrations - orchestrate agents, zero main context growth

    claude-codebashyamlTaskTodoWriteWrite
26. sub-agentsvibeeval/vibecosystem

    Create and configure Claude Code sub-agents with custom prompts, tools, and models

    claude-codebashyamlReadWriteBash
27. canvas-setupX-isdoingreat/canvas-pilot

    Use this skill on a fresh Canvas Pilot install when the student has never configured the project before. Trigger phrases include "set me up", "set up canvas pilot", "install canvas

    claude-codebashpythonyamlBashReadWrite
28. canvas-humanizerX-isdoingreat/canvas-pilot

    Reduces AI-detection signals in drafted text by routing every non-locked sentence through round-trip translation (English → intermediate language → English) and selecting the candi

    claude-codejsonpythonyamlBashReadWrite
29. canvas-humanizer-surgicalX-isdoingreat/canvas-pilot

    Second-pass humanizer that fixes specific issues left over from canvas-humanizer (v2) without re-introducing LLM-shaped prose. v3 design uses per-position-differentiated ESL regist

    claude-codejsonpythonyamlBashReadWrite
30. agent-evalmturac/everything-openai-codex

    Head-to-head comparison of coding agents (OpenAI Codex, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

    claude-codebashyamlReadWriteEdit
31. tsa-constraintsaimasteracc/tree-sitter-analyzer

    Architectural constraint enforcement. Detect forbidden cross-module calls ("MCP must not depend on CLI") at index time and gate edits on them. Rules live in YAML at repo root; viol

    claude-codebashyamlmcp__tree-sitter-analyzer__editBashRead
32. create-agentTOKTOKHAN-DEV/agent-company

    새 에이전트를 설계하고 registry.yaml + AGENT.md + skills/ 를 정합성 있게 생성한다. 새 런타임이나 새 도메인이 필요할 때 사용.

    claude-codebashmarkdownyamlBashReadWrite
33. ato-make-agentWillNigri/Agentic-Tool-Optimization

    Turn any installed skill (gstack, custom, third-party) into an ATO agent the user can summon into war-rooms. Reads a SKILL.md, extracts the persona, strips runtime boilerplate, and

    claude-codebashmarkdownyamlBashReadEdit
34. obsidian-brainanton-abyzov/vskill

    Autonomous Obsidian vault management using the PARA + LLM Wiki pattern. Three operations: ingest (inbox to wiki + PARA routing), query (cross-vault synthesis), lint (health check).

    claude-codebashyamlReadWriteGlob+7 files
35. visor-agent-devprobelabs/visor

    Guide for building and extending visor AI assistants. Use when creating new skills, workflows, checks, or modifying assistant.yaml configurations. Covers the full development loop

    claude-codebashyamlReadGrepGlob
36. prometheusCloudChef/atlasclaw-providers

    Prometheus monitoring and alerting for cloud-native observability. Use when implementing metrics collection, PromQL queries, alerting rules, service discovery, recording rules, and

    claude-codebashgopromqlpythonReadGrepGlob
37. self-improving-agentzhouguoqing/QianYuan.AIAgenticFramework

    A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-tr

    claude-codejsonmarkdownyamlReadWriteEdit
38. scaffold-frontend-subpagebbvch-ai/aihub-core

    Scaffold a detail wrapper with SelectButton tab navigation and nested tab subpages. Creates the tab bar, NavItem routing, StructuralColumn content, and overview tab following the [

    claude-codetypescriptvueyamlReadWriteEdit
39. document-featurebbvch-ai/aihub-core

    Create user-facing feature documentation for the docs VitePress docs site. Analyzes the codebase and produces an index.en.md in the correct docs directory. Use when user says 'docu

    claude-codebashyamlReadGrepGlob
40. scaffold-api-endpointbbvch-ai/aihub-core

    Generate a new REST API controller with fluent builder pattern, typed endpoints, permission-based auth, DTOs, and main.py registration. Use when user says "create API endpoint", "s

    claude-codepythonyamlReadWriteEdit
41. scaffold-agentbbvch-ai/aihub-core

    Generate a new AI agent with all boilerplate (agent class, events, config with form duality, memory, LLM streaming, i18n, BDD tests, entry point). Includes pattern catalog, executi

    claude-codebashgherkinpythonyamlReadWriteBash
42. write-docbbvch-ai/aihub-core

    Write new documentation pages for the VitePress docs site at docs/docs/. Ensures correct file structure (index.en.md only), frontmatter, heading hierarchy, media references, VitePr

    claude-codebashmarkdownyamlReadWriteEdit
43. scaffold-frontend-pagebbvch-ai/aihub-core

    Scaffold a new Nuxt 3 list page with StructuralScreen/Column layout, Pinia-Colada data fetching, card grid, create modal, and NuxtPage outlet for nested detail routes. Use when use

    claude-codevueyamlReadWriteEdit
44. wheeler-service-creatormaxwellsdm1867/wheeler

    Scaffold a NEW Wheeler service adapter that integrates an external tool into Wheeler end to end. Reach for this whenever the user wants to "create a wheeler service", "add a new to

    claude-codebashyamlReadWriteEdit
45. mlops-engineertranhieutt/software_development_department
    claude-codepythonyamlReadGlobGrep
46. devops-deploytranhieutt/software_development_department
    claude-codebashdockerpythonyamlReadGlobGrep
47. pii-engineeranonde-io/anonde

    Apply when designing, building, benchmarking, or debugging local-first PII detection / anonymization systems. Covers metric tradeoffs (leak rate vs F1), NER backend selection (patt

    claude-codegopythonyamlReadBashEdit
48. sprint-planbullish0x/GameStudio

    Generates a new sprint plan or updates an existing one based on the current milestone, completed work, and available capacity. Pulls context from production documents and design ba

    claude-codemarkdownyamlReadGlobGrep
49. design-taste-frontendcharlieviettq/awesome-agent-skill

    Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated

    claude-codebashcsstypescriptyamlBashReadWrite
50. sf-agentforceClientell-Ai/salesforce-skills

    Build, configure, and test Agentforce agents on Salesforce. Covers agent setup, topics, actions (Flow, Apex, PromptTemplate, External Service), Agent Scripts for deterministic FSM-

    claude-codeapexbashsoqlyamlReadWriteEdit+1 files
51. sf-deployClientell-Ai/salesforce-skills

    Orchestrate Salesforce deployments with dependency resolution, package.xml generation, targeted test execution, error diagnosis, and rollback strategies. Use when asked to deploy c

    claude-codebashxmlyamlReadWriteEdit+1 files
52. importmyclaude-sh/myclaude-creator-engine

    Import existing skills from .claude/skills/ into the Engine workspace for validation, packaging, and publishing. Auto-detects type, creates .meta.yaml, runs MCS-1 check. Use when:

    claude-codeyamlReadWriteGlob
53. packagemyclaude-sh/myclaude-creator-engine

    Package a product for distribution across 33+ platforms. Strips WHY comments, generates triple manifests (vault.yaml + plugin.json + agentskills.yaml), stages .publish/. Use when:

    claude-codehtmljsonmarkdownyamlReadWriteEdit
54. createmyclaude-sh/myclaude-creator-engine

    Scaffold a new product with MCS-1 valid structure and WHY comments. Supports all 13 types. Use when the creator says 'new skill', 'create', 'scaffold', 'start building', or wants t

    claude-codeyamlReadWriteGlob
55. spec-lockaegntic/cldcde

    Bi-directional code and documentation synchronizer. Use when editing code that affects specifications, API contracts, or documentation. Prevents documentation rot by maintaining sy

    claude-codebashjavascriptjsonsqlBashReadWrite
56. compound-engineeringaegntic/cldcde

    Orchestration layer that coordinates Debt-Sentinel, Red Team Tribunal, and Spec-Lock into unified workflows. Use when you need comprehensive quality assurance with multiple validat

    claude-codebashjsonpythonsqlBashReadWrite
57. red-team-tribunalaegntic/cldcde

    Multi-agent adversarial verification system. Use when you need thorough code review, security auditing, or quality validation. Spawns three specialized agents (Skeptic, User Proxy,

    claude-codebashjsonpythonyamlBashReadWrite
58. extendonurpolat05/ALBA

    Add one new capability to an existing ALBA setup - skill, hook, rule, slash command or MCP integration - interactively, then wire it into CLAUDE.md and settings.json. Use when user

    claude-codejsonyamlReadWriteEdit
59. aget-close-sessionaget-framework/aget

    Close session with pre-close triage, enriched output, and dual provenance. Orchestrates wind-down — does not replace it.

    claude-codebashyamlBashReadWrite
60. commit-twiddlerust-works/omni-dev

    Validates and corrects commit messages against project guidelines after a commit is created. Invoke automatically after every git commit to ensure messages conform to .omni-dev/com

    claude-codebashyamlBash(mkdir *)ReadWrite

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.