Agent skills that ask for Read, in other 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. agnixagent-sh/agnix

   Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 455 rules.

   otherbashBash(agnix:*)Bash(cargo:*)Read
2. cloudbrowser-use/browser-use

   Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud REST API (v2, v3, or

   otherRead
3. open-sourcebrowser-use/browser-use

   Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration,

   otherRead
4. x402browser-use/browser-use

   Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (s

   otherbashpythontypescriptBashReadWrite
5. qabrowser-use/browser-use

   QA-test a website or web app and return a 1-5 quality score (5 = flawless, 1 = broken) with evidence. Use when the user wants to test, QA, evaluate, score, or "check how good" a si

   otherbashBashReadTask
6. ui-checkstyleopen-metadata/OpenMetadata

   Run the exact ESLint + Prettier + organize-imports sequence that CI's `UI Checkstyle` workflow runs — on just the files the PR changed — and fail the task if any file ends up with

   otherbashBashReadGrep
7. connector-reviewopen-metadata/OpenMetadata

   Review an OpenMetadata connector against golden standards. Runs multi-agent analysis covering architecture, code quality, type safety, testing, and performance. When a PR number is

   otherbashBashReadGlob
8. scaffold-connectoropen-metadata/OpenMetadata

   Build a new OpenMetadata connector from scratch — scaffold JSON Schema, Python boilerplate, and AI context using schema-first architecture with code generation across Python, Java,

   otherbashBashReadWrite
9. java-checkstyleopen-metadata/OpenMetadata

   Run `mvn spotless:apply` to fix Java checkstyle / formatting failures and verify the result. Invoke after authoring or modifying any `.java` files, or when CI reports a "Java check

   otherbashBashReadGrep
10. dev-setupopen-metadata/OpenMetadata

    Set up, verify, or repair a local OpenMetadata development environment on macOS or Linux. Installs the toolchain (Java 21, Maven, Node 22, Yarn 1.x, Python 3.10+, ANTLR 4.9.2, Dock

    otherbashBashReadGlob
11. connector-standardsopen-metadata/OpenMetadata

    Load all OpenMetadata connector development standards into context. Use before building or reviewing connectors to ensure consistent patterns.

    otherReadGlob
12. test-locallyopen-metadata/OpenMetadata

    Build and deploy a full local OpenMetadata stack with Docker to test your connector in the UI. Handles code generation, build optimization, health checks, and guided testing.

    otherbashBashReadGlob
13. ui-core-componentsopen-metadata/OpenMetadata

    Use when writing or editing React/TSX in `openmetadata-ui/src/main/resources/ui/src/` or `openmetadata-ui-core-components/`, before reaching for a raw `<div>` + Tailwind utility cl

    othertypescriptReadGrepGlob
14. honcho-cliplastic-labs/honcho

    Inspect and debug Honcho workspaces via the `honcho` CLI. Use when investigating peer representations, memory state, session context, or dialectic quality — any task that requires

    otherbashBash(honcho:*)Bash(jq:*)Read
15. honcho-integrationplastic-labs/honcho

    Integrate Honcho memory into existing Python or TypeScript codebases. Use when adding Honcho SDK, setting up peers, configuring sessions, and accessing Honcho's representation.

    otherbashReadGlobGrep
16. gan-style-harnesssifxprime/kodelyth-ecc

    GAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomously. Based on Anthropic's March 2026 harness design paper.

    otherbashmarkdownReadWriteEdit
17. eval-harnesssifxprime/kodelyth-ecc

    Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles

    otherbashmarkdownReadWriteEdit
18. agent-evalsifxprime/kodelyth-ecc

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

    otherbashyamlReadWriteEdit
19. skill-complysifxprime/kodelyth-ecc

    Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences,

    otherbashReadBash
20. rerun-catalog-queriesrerun-io/rerun

    Performance patterns and gotchas for querying a Rerun catalog from Python. Reach for this when a CatalogClient/dataset query is unexpectedly slow, or when shaping a per-segment / p

    otherpythonReadGrepBash
21. rerun-urdfrerun-io/rerun

    Drive the Rerun URDF API (rerun.urdf.UrdfTree) to ingest a URDF as a Transform3D layer on a robot recording. Read when logging a robot model, running forward kinematics from joint

    otherpythonReadGrepBash
22. rerun-chunk-processingrerun-io/rerun

    Core mechanics of the Rerun Chunk Processing API (rerun.experimental) — LazyChunkStream pipelines, Chunk, lenses (MutateLens/DeriveLens/Selector), RrdReader, writing optimized RRDs

    otherpythonReadGrepBash
23. rerun-mcaprerun-io/rerun

    Ingest MCAP files into Rerun chunk streams with rerun.chunk.McapReader. Read when converting an MCAP recording, selecting topics or decoders, decoding custom protobuf messages, or

    otherpythonReadGrepBash
24. rerun-data-modelrerun-io/rerun

    How raw multimodal robot data maps onto the Rerun data model. Read FIRST, before modeling or converting a dataset — and whenever you are about to convert/ingest/preprocess robot da

    otherReadGrepBash
25. rerun-blueprintrerun-io/rerun

    Design a Rerun blueprint from the data, then iterate on it from headless screenshots. Read this when laying out a recording or dataset in the viewer, designing a default blueprint,

    otherpythonReadGrepBash
26. rerun-lerobotrerun-io/rerun

    Ingest a LeRobot (HuggingFace) dataset into Rerun. Read when converting a LeRobot dataset to RRDs, splitting it into per-episode segments, or registering it on a Rerun catalog. Cov

    otherpythonReadGrepBash
27. rerun-mp4rerun-io/rerun

    Ingest .mp4 video into Rerun chunk streams with rerun.experimental.Mp4Reader. Read when converting video into a VideoStream, choosing stream vs asset mode, transcoding (B-frames, o

    otherpythonReadGrepBash
28. rerun-parquetrerun-io/rerun

    Ingest tabular Parquet files into Rerun chunk streams with rerun.experimental.ParquetReader. Read when converting trajectory or sensor tables (LeRobot-style parquet, exported logs)

    otherpythonReadGrepBash
29. opencli-adapter-authorjackwener/OpenCLI

    Use when writing an OpenCLI adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, adapter coding, and verif

    othermarkdownBash(opencli:*)Bash(jsluice:*)Read+2 files
30. opencli-browserjackwener/OpenCLI

    Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selector-first tar

    otherbashjsonBash(opencli:*)ReadEdit
31. opencli-usagejackwener/OpenCLI

    Use at the start of any OpenCLI session — this is the top-level map of what `opencli` can do, how to discover adapters, what flags and output formats are universal, and which speci

    otherbashBash(opencli:*)Read
32. opencli-browser-sitemapjackwener/OpenCLI

    Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily

    othermarkdownBash(opencli:*)ReadEdit
33. opencli-autofixjackwener/OpenCLI

    Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapte

    otherbashmarkdowntypescriptyamlBash(opencli:*)Bash(gh:*)Read
34. opencli-sitemap-authorjackwener/OpenCLI

    Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use aft

    othermarkdownyamlBash(opencli:*)ReadEdit+1 files
35. doctorjihe520/MathModelAgent

    环境检查与安装向导。检查数学建模工作流所需的全部依赖是否已安装，对缺失项提供安装命令，并在用户确认后执行安装。手动触发。

    otherbashBash(*)ReadWrite
36. 3coding-visualjihe520/MathModelAgent

    数学建模编程实现与数据图表生成阶段。根据 ANALYSIS_MODELING_REPORT.md 编写可复现代码、运行求解、验证约束、输出 RESULTS_REPORT.md 并生成论文可用的数据驱动图表 PDF。

    othermarkdownBash(*)ReadWrite
37. 1start-mathmodeljihe520/MathModelAgent

    数学建模竞赛工作流入口。用于启动完整建模流程：询问用户偏好，生成 plan.md 和 todo.md，并按阶段调用赛题分析、建模、代码与图表、流程图、论文撰写、验证验收等 skills。

    othermarkdownBash(*)ReadWrite
38. 2analysis-modelingjihe520/MathModelAgent

    数学建模赛题分析与建模设计合并阶段。用于读取题面和附件，完成子问题拆解、数据理解、假设预检、变量定义、模型公式、目标函数、约束条件、求解策略和可交给代码实现的建模报告。

    othermarkdownBash(*)ReadWrite
39. mathmodel-figure-templatesjihe520/MathModelAgent

    Use this skill in the MathModel LaTeX sandbox when the user asks to reproduce built-in scientific visualization templates, especially prompts from the Improve tab mentioning $mathm

    otherbashBash(*)ReadWrite
40. 5writingjihe520/MathModelAgent

    数学建模竞赛论文撰写阶段，支持 Typst 和 LaTeX 双引擎。根据 ANALYSIS_MODELING_REPORT.md、RESULTS_REPORT.md 和 figures/*.pdf 选择比赛模板、排版引擎、组织章节，并在论文正文中按章节直接插入图表。

    otherbashlatextypstBash(*)ReadWrite
41. 6verityjihe520/MathModelAgent

    数学建模竞赛最终验证和验收阶段，支持 Typst 和 LaTeX 双引擎。用于论文写完后检查章节数量、标题顺序、图表引用、数值一致性、占位符、内部文件泄露、参考文献、代码可复现性、编译和提交就绪状态。

    otherbashmarkdownBash(*)ReadWrite
42. 4drawiojihe520/MathModelAgent

    数学建模非数据型图示绘制阶段。根据 ANALYSIS_MODELING_REPORT.md、RESULTS_REPORT.md 和已有 figures/ 生成技术路线图、子问题求解流程图、模型结构图、数据处理流程图等 DrawIO 图，并导出论文可引用 PDF。

    otherbashmarkdownBash(*)ReadWrite
43. ripwire-security-scanredhat-et/ripwire

    Security review: (1) vet an untrusted SKILL.md or .mcp.json BEFORE installing it — the injection/exfiltration scanner; CRITICAL blocks the install; (2) audit code on an untrusted-i

    otherBashRead
44. ripwire-write-testsredhat-et/ripwire

    Write tests for EXISTING code that has none — 'this is untested, add coverage', 'add a safety net first'. Finds what no test reaches: --seams ranks untested cross-module edges, --c

    otherBashRead
45. ripwire-before-you-buildredhat-et/ripwire

    Starting a FEATURE (multi-symbol work): the plan, the API boundary, the scope — how big does this change get — from the codebase's real structure; --lego=Iface lists an interface's

    otherBashRead
46. ripwire-perf-targetredhat-et/ripwire

    A MEASURED performance problem: start from a benchmark, flame graph, perf sample or profiler run, locate the hot symbol the profile names, test structural hypotheses (memory-bound

    otherBashRead
47. ripwire-orientredhat-et/ripwire

    Landing COLD in an unfamiliar repo or subsystem, or about to open several files for one question: map first, read only the files it ranks highest. Main subsystems and entry points,

    otherbashBashRead+2 files
48. ripwire-navigateredhat-et/ripwire

    You can NAME the symbol: who calls it, what it calls, the path from A to B, its full body, or an exact literal/regex match. 'Safe to change or rename X — what breaks downstream?' =

    otherbashBashRead
49. ripwire-graph-queryredhat-et/ripwire

    A call-graph question the fixed verbs can't phrase — 'which high-complexity functions can reach X?', 'what has 10+ callers in src/?', 'untested symbols within one hop of main'. --g

    otherBashRead
50. ripwire-reuse-firstredhat-et/ripwire

    About to write ONE symbol (even a 'quick' one-liner) or add a dependency: reuse before you reinvent. Finds the building block that already exists, the house pattern to imitate, the

    otherBashRead
51. ripwire-routerredhat-et/ripwire

    Start HERE when unsure which ripwire skill fits, or asked 'how do I use ripwire / where do I start'. A moment→skill map, cold start to handoff, plus the two reflexes that leak most

    otherBashRead
52. ripwire-change-checkredhat-et/ripwire

    Merge-SAFETY of an existing diff — yours before you push, or a PR you review: blast radius, tests to run, a broken contract (--edit-check=SYM), branch conflicts and landing order,

    otherBashRead
53. ripwire-mcpredhat-et/ripwire

    Wire ripwire into an agent as an MCP server — `ripwire wrap AGENT` (Claude Code, Cursor, Codex, Gemini…) — and choose the server verb mid-task. Also tool HEALTH: a symbol you expec

    otherBashRead+1 files
54. ripwire-fresh-eyesredhat-et/ripwire

    Maintenance risk in code you did NOT write — inheriting a module, a suspected god object, 'what's gnarly / where's the rot / safe to touch?': hotspots, dead code, clones, a functio

    otherBashRead+1 files
55. ripwire-quality-barredhat-et/ripwire

    Code QUALITY of what YOU just wrote, before you commit or say 'done': --quality-delta reports only what got WORSE across 10 kinds and exits non-zero on new debt; then which restruc

    otherbashBashRead+1 files
56. ripwire-handoffredhat-et/ripwire

    Brief someone ELSE on a subsystem — 'hand this area off' to a successor, teammate or fresh session: purpose, the 2-3 entry points with bodies, the design docs that say WHY, hotspot

    otherBashRead
57. ripwire-layersredhat-et/ripwire

    Architecture HEALTH and ENFORCEMENT — 'is this a dependency mess / does the UI reach into the database / enforce module boundaries in CI?': cycles, the godfile, propagation cost (h

    otherBashRead
58. ripwire-find-bugredhat-et/ripwire

    You have a SYMPTOM — crash, exception, wrong output, failing test, error string — and don't know which code is responsible. Ranks candidates; a stack trace or sanitizer output maps

    otherBashRead
59. ripwire-opt-remarksredhat-et/ripwire

    Triage clang optimization remarks (-Rpass, -Rpass-missed, opt-record YAML) while editing ripwire's OWN C++: 'loop not vectorized', 'will not be inlined' — worth a diff, or is LTO/P

    otherbashBashReadEdit
60. research-litwanshuiyin/Auto-claude-code-research-in-sleep

    Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or ne

    otherbashBash(*)ReadGlob+6 files

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.