Agent skills that run json, that ask for Edit, 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. iwsdk-ui-panelfacebook/immersive-web-sdk

   Create, place, preview, debug, and connect manifest-backed IWSDK UIKitML assets. Use for spatial panels, browser HUDs, UIKitML layout, fonts, editor previews, or runtime element be

   claude-codebashjsontypescriptReadEditWrite
2. 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
3. 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
4. upstream-checkBenedictKing/ccx

   检查 Claude Code / Codex 上游版本变更，对比本地版本，识别协议/工具/用法相关更新并追加 TODO 提醒

   claude-codebashjsonmarkdownBashReadWrite
5. model-updateBenedictKing/ccx

   新增或更新 CCX 项目中的模型注册技能。适用于 Claude 与非 Claude 模型，覆盖能力表、路由白名单、基准映射、代码生成与验证。

   claude-codebashjsonBashReadWrite
6. creating-claude-hooksAgentWorkforce/relay

   Use when creating or publishing Claude Code hooks - covers executable format, event types, JSON I/O, exit codes, security requirements, and PRPM package structure

   claude-codebashjsonmarkdowntypescriptReadWriteEdit
7. shadcn-uicodedogQBY/ReadAny

   Provides complete shadcn/ui component library patterns including installation, configuration, and implementation of accessible React components. Use when setting up shadcn/ui, inst

   claude-codebashcssjavascriptjsonReadWriteBash
8. compound-learningsparcadei/Continuous-Claude-v3

   Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns s

   claude-codebashjsonmarkdownReadGlobGrep
9. skill-developerparcadei/Continuous-Claude-v3

   Meta-skill for creating and managing Claude Code skills

   claude-codebashjsonmarkdownpythonBashReadWrite
10. agentica-sdkparcadei/Continuous-Claude-v3

    Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration

    claude-codejsonpythonBashReadWrite
11. stable-releaseanthony-chaudhary/dos-kernel

    Promote an already-shipped rolling release (vX.Y.Z) of the DOS kernel to a named stable channel — gated on a green kernel suite + a green third-party CI run on the candidate + a cl

    claude-codebashjsonmarkdownReadEditGrep
12. meridian-mcpMeridiona/meridian

    Build, configure, and debug the Meridian MCP server. Exposes app session data to AI tools via the Model Context Protocol.

    claude-codebashjsonBashReadEdit
13. compound-learningsvibeeval/vibecosystem

    Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns s

    claude-codebashjsonmarkdownReadGlobGrep
14. agentica-sdkvibeeval/vibecosystem

    Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration

    claude-codejsonpythonBashReadWrite
15. skill-developervibeeval/vibecosystem

    Meta-skill for creating and managing Claude Code skills

    claude-codebashjsonmarkdownpythonBashReadWrite
16. 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
17. debt-cleananthony-chaudhary/fak

    One repeatable, evidence-backed pass that retires a bounded batch of maturity debt worst-first across the system's dedicated debt lanes. Features rich queryability (--query, --heal

    claude-codebashjsonReadBashWrite
18. 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
19. 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
20. titan-syncoptave/ops-codegraph-tool

    Identify overlapping fixes across audit results, plan shared abstractions, produce an ordered execution plan with logical commit grouping (Titan Paradigm Phase 3)

    claude-codebashjsonBashReadWrite
21. bench-checkoptave/ops-codegraph-tool

    Run benchmarks against a saved baseline, detect performance regressions, and update the baseline — guards against silent slowdowns

    claude-codebashjsonmarkdownBashReadWrite
22. titan-gauntletoptave/ops-codegraph-tool

    Audit codebase files against the 4-pillar quality manifesto using RECON work batches, with batch processing and context budget management (Titan Paradigm Phase 2)

    claude-codebashjsonBashReadWrite
23. titan-forgeoptave/ops-codegraph-tool

    Execute the sync.json plan — refactor code, validate with /titan-gate, commit, and advance state (Titan Paradigm Phase 4)

    claude-codebashjsonBashReadWrite
24. titan-gateoptave/ops-codegraph-tool

    Validate staged changes — codegraph checks + project lint/build/test, auto-rollback on failure, pass/fail commit gate (Titan Paradigm Phase 4)

    claude-codebashjsonBashReadWrite
25. titan-reconoptave/ops-codegraph-tool

    Map a codebase's dependency graph, identify hotspots, name logical domains, propose work batches, and produce a ranked priority queue for autonomous cleanup (Titan Paradigm Phase 1

    claude-codebashjsonmarkdownBashReadWrite
26. titan-grindoptave/ops-codegraph-tool

    Adopt extracted helpers — find dead symbols from forge, wire them into consumers, replace duplicated inline patterns, and gate on dead-symbol delta (Titan Paradigm Phase 4.5)

    claude-codebashjsonBashReadWrite
27. titan-closeoptave/ops-codegraph-tool

    Split branch commits into focused PRs, compile issue tracker, generate final report with before/after metrics (Titan Paradigm Phase 5)

    claude-codebashjsonmarkdownBashReadWrite
28. canvas-executeX-isdoingreat/canvas-pilot

    This skill should be used when executing an already-scanned Canvas plan after the user has approved it. Invoked after `canvas-scan` wrote `runs/<today>/plan.json` and the user repl

    claude-codebashjsonmarkdownpythonBashReadWrite+1 files
29. canvas-skipX-isdoingreat/canvas-pilot

    This skill should be used when an assignment was routed as `mixed_unsupported` (currently the zyBooks math course). Logs the assignment to the daily todo.md so the user can do it m

    claude-codejsonBashReadWrite
30. canvas-humanizer-loopX-isdoingreat/canvas-pilot

    Nested-loop wrapper around canvas-humanizer that runs the round-trip humanizer, audits its output for meaning/structure/rubric damage via 3 parallel sub-agents with majority vote,

    claude-codejsonpythonBashReadWrite
31. canvas-genericX-isdoingreat/canvas-pilot

    Fallback runtime-designed handler for Canvas assignments that don't fit any of the 5 specific skills (canvas-ics33 / canvas-reading-annotation / canvas-essay / canvas-zybooks / can

    claude-codejsonpythonBashReadWrite
32. canvas-scanX-isdoingreat/canvas-pilot

    This skill should be used when scanning Canvas for pending assignments and producing an approval-gated plan. Invoked manually when the user says "check canvas", "scan canvas", "wha

    claude-codebashjsonmarkdownpythonBashReadWrite+1 files
33. 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
34. canvas-awkward-syntaxX-isdoingreat/canvas-pilot

    Direct-commit syntactically-marked rewrite humanizer. Single sub-agent per sentence (K=1, no candidate competition), role-aware transformation allowlist, paragraph-balanced constra

    claude-codejsonpythonBashReadWrite
35. canvas-insideX-isdoingreat/canvas-pilot

    Canvas in-page answering handler — currently scoped to Classic Quizzes (`online_quiz`); see the SKILL's Scope note. Handles open quizzes (MCQ, multi-answer, T/F, matching, short-an

    claude-codejsonmarkdownpythonBashReadWrite
36. canvas-reading-annotationX-isdoingreat/canvas-pilot

    Generic reading-annotation handler for academic-writing courses — annotates reading PDFs with color-coded highlights + margin notes + filled answer blanks per the instructor's rubr

    claude-codejsonmarkdownpythonBashReadWrite
37. 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
38. pipelineHatmanStack/RAGStack-Lambda

    Run the adversarial plan-implement-review pipeline. Spawns agents for each role with their own context windows. Use after /brainstorm, /repo-eval, /repo-health, or /doc-health has

    claude-codejsonxmlAgentReadWrite
39. agent-architecture-auditmturac/everything-openai-codex

    Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and r

    claude-codebashjsonReadWriteEdit
40. workflow-plancatlog22/Claude-Code-Workflow

    Unified planning skill - 4-phase planning workflow, plan verification, and interactive replanning. Triggers on "workflow-plan", "workflow-plan-verify", "workflow:replan".

    claude-codejavascriptjsonSkillAgentAskUserQuestion
41. workflow-multi-cli-plancatlog22/Claude-Code-Workflow

    Multi-CLI collaborative planning with codebase context gathering, iterative cross-verification, and execution handoff.

    claude-codejavascriptjsonSkillAgentAskUserQuestion
42. workflow-tdd-plan-plancatlog22/Claude-Code-Workflow

    Unified TDD workflow skill combining 6-phase TDD planning with Red-Green-Refactor task chain generation, and 4-phase TDD verification with compliance reporting. Triggers on "workfl

    claude-codejavascriptjsonSkillAgentAskUserQuestion
43. spec-generatorcatlog22/Claude-Code-Workflow

    Specification generator - 7 phase document chain producing product brief, PRD, architecture, epics, and issues with Codex review gates. Triggers on generate spec, create specificat

    claude-codejavascriptjsonAgentAskUserQuestionTaskCreate+16 files
44. workflow-test-fixcatlog22/Claude-Code-Workflow

    Unified test-fix pipeline combining test generation (session, context, analysis, task gen) with iterative test-cycle execution (adaptive strategy, progressive testing, CLI fallback

    claude-codejavascriptjsonSkillAgentAskUserQuestion
45. sibyl-self-healerSibyl-Research-Team/AutoResearch-SibylSystem

    Sibyl 自愈 agent - 后台自动检测修复系统错误，添加回归测试，git commit 留痕

    claude-codejsonReadWriteEdit
46. OpenAI Apps MCPcoco-research/coco

    Build ChatGPT apps with MCP servers on Cloudflare Workers. Extend ChatGPT with custom tools and interactive widgets (HTML/JS UI). Use when: developing ChatGPT extensions, implemen

    claude-codebashhtmljsontypescriptReadWriteEdit
47. playwright-testArman-Kudaibergenov/1c-ai-development-kit

    Этот скилл MUST быть вызван когда пользователь говорит "напиши UI-тест", "создай playwright тест", "scaffold playwright", "протестируй фичу в браузере". SHOULD также вызывать после

    claude-codebashjavascriptjsonReadWriteEdit
48. 1c-test-runnerArman-Kudaibergenov/1c-ai-development-kit

    Этот скилл MUST быть вызван когда пользователь говорит "напиши тест", "протестируй модуль", "запусти unit-тесты" для 1С. SHOULD также вызывать после реализации бизнес-логики для ве

    claude-codebsljsonxmlReadWriteEdit
49. 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
50. zach-search-term-report-analyzerzach22-1999/amazon-skills

    分析 Amazon Ads SP / SB / SD 搜索词报告。确定性脚本负责清洗、时间窗聚合、词根聚类和决策计算，AI 助手或人工负责词根级语义分类；通过词根继承减少长尾词的待判定比例，输出 Markdown、CSV、HTML 和 JSON 六类结果。 使用时机：判断搜索词是否应该否定、控成本、继续测试或放量，分析 7/14/30 天 CVR 与 ACO

    claude-codebashjsonReadWriteEdit
51. zach-sif-cvr-threshold-analyzerzach22-1999/amazon-skills

    基于领星 ASIN 360 或同类日业务报表，以及用户自己 SIF MCP 导出的日级关键词自然排名 JSON，回测 CVR 与核心词/稳定词自然排名波动的关系，并输出观察线、危险线、广告 CVR 确认线。 使用时机：站外放量、达人投放、联盟投放或内容种草后，需要判断 CVR 低到什么区间会增加自然排名波动风险。 触发词：/zach-sif-cvr-thre

    claude-codebashjsonReadWriteEdit
52. zach-product-researchzach22-1999/amazon-skills

    基于Sorftime MCP的选品分析，发现高潜力市场机会、多维度属性标注与交叉分析、验证竞争格局、测算投入产出、输出Go/No-Go决策与选品报告。 使用时机：选品立项前的市场调研。新品上架工作流第一步。 触发词：/zach-product-research

    claude-codebashjsonmarkdownpythonReadWriteEdit
53. proof-checkersjtuytc/ResearchMathAgent

    Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (external reviewer backend, xhigh reasoning), fixes each g

    claude-codebashjsonmarkdownBash(*)ReadGrep+3 files
54. kill-argumentsjtuytc/ResearchMathAgent

    Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-u

    claude-codebashjsonmarkdownBash(*)ReadWrite+2 files
55. api-developerVinix24/vnx-orchestration

    API developer specializing in clean, well-documented REST APIs

    claude-codejsonReadWriteEdit
56. qaWillNigri/Agentic-Tool-Optimization

    Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when

    claude-codebashjsonBashReadWrite
57. design-reviewWillNigri/Agentic-Tool-Optimization

    Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source cod

    claude-codebashjsonBashReadWrite
58. pi-sub-agentwquguru/skills

    将具体执行委派给 pi coding agent + ZenMux 便宜执行模型（默认强档 deepseek/deepseek-v4-pro：1M 上下文、推理型；廉价快档 inclusionai/ling-3.0-flash：256K、非思考、更省），Claude 负责任务-模型匹配判断、任务书编写、驱动（一次性 pi -p 或 tmux 交互长程）、硬超

    claude-codebashjavascriptjsonReadWriteEdit
59. skill-statusXBuilderLAB/cheat-on-skill

    cheat-on-skill 的陪跑进度 skill。用户问“今天该干嘛”“我现在做到哪了”“继续学”“打卡”“我卡住了”“下一步是什么”时触发。读取 .skill-state.json 的 active.progress 和 learning_plan，给当天任务、检查完成情况、记录进度、根据快慢调整计划。前置：已有 .skill-state.json 且

    claude-codebashjsonBash(*)ReadWrite
60. twin-writerkody-w/rappterbook

    Generate content for the multi-platform digital twin pipeline. Creates blog posts, podcast scripts, X threads, newsletter issues, book chapters, course outlines, stream concepts, a

    claude-codejsonBashReadWrite

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.