{"id":"e3d59af2-6e9e-44fd-9340-102abb4632e5","shortId":"LrEEnA","kind":"skill","title":"md-docs","tagline":"This skill should be used ONLY when the user asks to update README.md, CLAUDE.md, AGENTS.md, or CONTRIBUTING.md. Trigger phrases include \"update README\", \"init README\", \"create README\", \"update context files\", \"init context\", \"create CLAUDE.md\", \"update CLAUDE.md\", \"update AGENTS","description":"# Markdown Documentation Management\n\n## Overview\n\nManage project documentation for Claude Code workflows including context files, READMEs, and agent instructions. This skill provides structured automation for maintaining accurate, up-to-date documentation that aligns with actual codebase structure and functionality. Use this skill when initializing new projects, updating existing documentation, or ensuring context files accurately reflect current code.\n\nThe skill emphasizes verification and validation over blind generation—analyze the actual codebase structure, file contents, and patterns before creating or updating documentation. All generated content should be terse, imperative, and expert-to-expert rather than verbose or tutorial-style.\n\n## Prerequisites\n\nBefore using any documentation workflow, verify basic project structure:\n\n```bash\ngit rev-parse --git-dir\n```\n\nEnsure the output confirms you are in a git repository. If not initialized, documentation workflows may still proceed but git-specific features will be skipped.\n\nFor update workflows, verify target files exist:\n\n```bash\nls -la CLAUDE.md AGENTS.md DOCS.md README.md CONTRIBUTING.md\n```\n\nCheck which files are present before attempting updates. Missing files will show errors, which helps identify what needs initialization. Note that DOCS.md is optional and only relevant for projects with APIs or public interfaces. CONTRIBUTING.md is optional and only relevant if the repo already defines contribution guidance.\n\n## Update Context Files\n\nVerify and fix AGENTS.md, and optionally DOCS.md and CONTRIBUTING.md against the actual codebase. `CLAUDE.md` is a symlink to `AGENTS.md` and does not need separate processing. This workflow reads existing context files, analyzes the codebase structure, identifies discrepancies, and updates documentation to match reality. DOCS.md and CONTRIBUTING.md are only processed if they exist in the repository.\n\n### Workflow Steps\n\n**Parse Arguments**\n\nSupport the following arguments:\n\n- `--dry-run`: Show what would change without writing files\n- `--preserve`: Keep existing content structure, only fix inaccuracies\n- `--thorough`: Perform deep analysis of all files (slower but comprehensive)\n- `--minimal`: Quick verification focusing on high-level structure only\n\n**Verify Git Repository**\n\nConfirm working directory is a git repository. If not, warn the user but proceed with limitations (cannot analyze git history or branches).\n\n**Read Existing Context Files**\n\nRead current AGENTS.md, DOCS.md, and CONTRIBUTING.md (if present) contents. `CLAUDE.md` is a symlink to `AGENTS.md` and does not need a separate read:\n\n```bash\ncat AGENTS.md\ncat DOCS.md         # if exists\ncat CONTRIBUTING.md # if exists\n```\n\nParse the structure and extract documented information including:\n\n- Project description and purpose\n- File structure and organization\n- Build and test commands\n- Custom tooling or scripts\n- Agent configurations and triggers\n- API endpoints and methods (from DOCS.md)\n- Function signatures and parameters (from DOCS.md)\n- Type definitions and interfaces (from DOCS.md)\n- Contribution workflow and guidelines (from CONTRIBUTING.md)\n- Code review process and standards (from CONTRIBUTING.md)\n\n**Analyze Codebase**\n\nScan the project to gather accurate information:\n\n- Directory structure (`ls -la`, `tree` if available)\n- Package configuration (`package.json`, `pyproject.toml`, `Cargo.toml`, etc.)\n- Build scripts and commands\n- Test frameworks and configurations\n- README badges and metadata\n\nFor `--thorough` mode, also analyze:\n\n- File content patterns (imports, exports, interfaces)\n- Code organization conventions\n- Dependency relationships\n\n**Identify Discrepancies**\n\nCompare documented information against actual codebase:\n\n- Outdated file paths or structure\n- Incorrect build commands\n- Missing or removed features\n- Deprecated dependencies\n- Stale agent configurations\n- Outdated API endpoints or routes (DOCS.md)\n- Changed function signatures (DOCS.md)\n- Modified type definitions (DOCS.md)\n- Outdated contribution guidelines (CONTRIBUTING.md)\n- Stale branch naming or PR process (CONTRIBUTING.md)\n- Missing `CLAUDE.md` symlink (should point to `AGENTS.md`)\n\n**Create Backups**\n\nBefore overwriting, create backup files. `CLAUDE.md` is a symlink to `AGENTS.md` and does not need a separate backup:\n\n```bash\ncp AGENTS.md AGENTS.md.backup\ntest -f DOCS.md && cp DOCS.md DOCS.md.backup\ntest -f CONTRIBUTING.md && cp CONTRIBUTING.md CONTRIBUTING.md.backup\n```\n\n**Update Context Files**\n\nWrite corrected versions maintaining the existing structure when `--preserve` is used, or reorganizing for clarity when not. Ensure the `CLAUDE.md` symlink exists (`ln -sf AGENTS.md CLAUDE.md`). For `--dry-run`, display the diff without writing:\n\n```bash\ndiff -u AGENTS.md.backup AGENTS.md\n```\n\n**Generate Report**\n\nDisplay a summary of changes.\n\nWhen DOCS.md exists:\n\n```\n✓ Updated AGENTS.md\n  - Fixed outdated build command\n  - Added new /api directory to structure\n  - Updated test-runner trigger pattern\n\n✓ Updated DOCS.md\n  - Fixed outdated endpoint path /api/v1/users\n  - Updated function signature for createUser()\n\n✓ Updated CONTRIBUTING.md\n  - Updated branch naming convention\n  - Fixed outdated PR template reference\n\n✓ CLAUDE.md symlink verified\n```\n\nWhen optional files are absent:\n\n```\n✓ Updated AGENTS.md\n  - Fixed outdated build command\n\n✓ CLAUDE.md symlink verified\n\n⊘ DOCS.md not found (skipped)\n⊘ CONTRIBUTING.md not found (skipped)\n```\n\nFor the complete update context files workflow with verification strategies, diff examples, and edge cases, refer to `references/update-agents.md`.\n\n## Update README\n\nGenerate or update README.md based on project structure, package metadata, and codebase analysis. This workflow creates comprehensive, accurate READMEs that reflect the actual state of the project.\n\n### Workflow Steps\n\n**Parse Arguments**\n\nSupport the following arguments:\n\n- `--dry-run`: Preview README content without writing\n- `--preserve`: Keep existing sections, only update outdated information\n- `--minimal`: Generate minimal README (title, description, installation, usage)\n- `--full`: Generate comprehensive README with all optional sections\n\n**Analyze Project Structure**\n\nGather information from multiple sources:\n\n```bash\n# Package metadata\ncat package.json\ncat pyproject.toml\ncat Cargo.toml\n\n# Git information\ngit remote get-url origin\ngit describe --tags\n\n# Directory structure\nls -la\n```\n\nExtract:\n\n- Project name and description\n- Version number\n- Repository URL\n- License\n- Dependencies\n- Scripts/commands\n\n**Read Existing README**\n\nIf README.md exists and `--preserve` is used:\n\n```bash\ncat README.md\n```\n\nParse existing sections to preserve custom content while updating technical details.\n\n**Read CONTRIBUTING.md (Optional)**\n\nIf CONTRIBUTING.md exists, read it and treat it as the source of truth for contribution guidance. Do not duplicate detailed contribution steps in README; link to CONTRIBUTING.md instead.\n\n```bash\ntest -f CONTRIBUTING.md && cat CONTRIBUTING.md\n```\n\n**Create Backup**\n\nBefore overwriting existing README:\n\n```bash\ncp README.md README.md.backup\n```\n\n**Generate README Content**\n\nCreate structured content with appropriate sections:\n\n- **Title and badges** (version, license, build status)\n- **Description** (concise project summary)\n- **Installation** (package manager commands)\n- **Usage** (basic examples)\n- **Development** (build, test, lint commands)\n- **Contributing** (if applicable; link to CONTRIBUTING.md when it exists)\n- **License** (based on package metadata)\n\nFor `--minimal` mode, include only title, description, installation, and usage.\n\nFor `--full` mode, also include:\n\n- API documentation\n- Examples directory listing\n- Deployment instructions\n- Troubleshooting section\n- Credits and acknowledgments\n\n**Write README**\n\nSave the generated content. For `--dry-run`, display without writing.\n\n**Generate Report**\n\nDisplay summary:\n\n```\n✓ Updated README.md\n  - Added installation section\n  - Updated build commands to match package.json\n  - Added badges for license and version\n```\n\nFor the complete update README workflow with section templates, metadata extraction strategies, and formatting examples, refer to `references/update-readme.md`.\n\n## Initialize README\n\nCreate project-specific README.md from scratch based on codebase analysis or a user-provided description. This workflow is ideal for new projects or repositories lacking a README. Unlike `update-readme`, this workflow refuses to overwrite an existing README unless explicitly forced, and supports guided mode for focusing content on user intent.\n\n### Workflow Steps\n\n**Parse Arguments**\n\nSupport the following arguments:\n\n- `[description?]`: Freeform description to focus content generation (guided mode)\n- `--dry-run`: Preview generated content without writing\n- `--minimal`: Create minimal README (title, description, installation, usage)\n- `--full`: Create comprehensive README with all applicable sections\n- `--force`: Overwrite existing README.md without prompting\n\nGuided mode examples:\n\n- `/md-docs:init-readme TypeScript library for parsing dates with zero deps`\n- `/md-docs:init-readme Foundry lending protocol with audit-ready docs`\n\n**Verify No Existing README**\n\nCheck if README.md already exists at the repository root:\n\n```bash\ntest -f README.md && echo \"exists\" || echo \"missing\"\n```\n\nIf exists without `--force`, use `AskUserQuestion` with options:\n\n- **Overwrite**: Replace existing README completely\n- **Abort**: Cancel operation (suggest `/md-docs:update-readme --preserve` instead)\n\n**Analyze Project**\n\nGather comprehensive information:\n\n- Language and framework (detect from files and package configs)\n- Package metadata (name, version, description, license, scripts)\n- Directory structure and organization\n- Entry points and public APIs\n- Existing assets (LICENSE, CONTRIBUTING.md, CHANGELOG.md, examples/)\n- Git remote for repository URL and badges\n\n**Generate README Content**\n\nCreate structured content guided by the mode and optional description:\n\n- **Guided mode (description provided)**: Emphasize sections aligned with keywords and intent (e.g., \"security-first\" → audit/testing emphasis; \"library\" → API reference focus)\n- **Automatic inference (no description)**: Derive sections and tone entirely from project analysis\n\nAdapt section order to project type (library, application, smart contract). For `--minimal`, include only title, description, installation, usage. For `--full`, include all applicable sections. Follow the writing style, formatting rules, and section templates documented in `references/update-readme.md`.\n\n**Write README**\n\nSave generated content to `./README.md`. For `--dry-run`, display without writing.\n\n**Generate Report**\n\nDisplay summary:\n\n```\n✓ Created README.md\n  - Detected TypeScript library\n  - Added installation (pnpm detected)\n  - Generated usage example from src/index.ts\n  - Added MIT license badge\n```\n\nFor the complete initialize README workflow with section templates, guided-mode strategies, and formatting examples, refer to `references/init-readme.md`.\n\n## Update CONTRIBUTING\n\nUpdate CONTRIBUTING.md based on current codebase tooling and workflows. **This workflow only runs when CONTRIBUTING.md already exists in the repository.** If CONTRIBUTING.md is absent, skip this workflow entirely—do not auto-create contribution guidelines.\n\n### Prerequisite Check\n\nBefore proceeding, verify the file exists:\n\n```bash\ntest -f CONTRIBUTING.md && echo \"exists\" || echo \"missing\"\n```\n\nIf missing, report to the user and stop. Do not create CONTRIBUTING.md unless explicitly requested.\n\n### Workflow Steps\n\n**Parse Arguments**\n\nSupport the following arguments:\n\n- `--dry-run`: Show what would change without writing files\n- `--preserve`: Maximum preservation; only fix broken commands/links\n- `--thorough`: Deep analysis; verify all links and commands work\n\n**Read Existing CONTRIBUTING.md**\n\n```bash\ncat CONTRIBUTING.md\n```\n\nParse the document structure:\n\n- Section headings and organization\n- Code blocks with commands\n- URLs and file path references\n- Mentioned tooling (test runners, linters, formatters)\n\n**Gather Codebase Intelligence**\n\nDetect current tooling and compare against documented content:\n\n- Package manager (npm, pnpm, yarn, bun) from lock files\n- Available scripts from package.json/Makefile/justfile\n- Branch conventions (main vs master)\n- Linting/formatting tools in use\n\n**Identify Discrepancies**\n\nCompare documented information against actual codebase:\n\n- Outdated CLI commands (npm → pnpm)\n- Incorrect branch references (master → main)\n- Broken links to issue templates or docs\n- Stale tooling references (Jest → Vitest)\n\n**Update Content**\n\nFix technical inaccuracies while preserving:\n\n- Contribution policies (CLA, DCO, licensing)\n- Review processes and expectations\n- Code of conduct references\n- Governance decisions\n\n**Generate Report**\n\nDisplay summary:\n\n```\n✓ Updated CONTRIBUTING.md\n  - Fixed package manager: npm → pnpm\n  - Corrected branch reference: master → main\n  - Updated test command\n\n⊘ Policy sections preserved (CLA, review process)\n```\n\nFor the complete update CONTRIBUTING workflow with verification strategies and examples, refer to `references/update-contributing.md`.\n\n## Initialize Context\n\nCreate project-specific AGENTS.md from scratch based on codebase analysis. This workflow is ideal for new projects or repositories lacking context documentation.\n\n### Workflow Steps\n\n**Parse Arguments**\n\nSupport the following arguments:\n\n- `--dry-run`: Preview generated content without writing\n- `--minimal`: Create minimal context file (project description, structure)\n- `--full`: Create comprehensive context file with all relevant sections\n\n**Verify No Existing AGENTS.md**\n\nCheck if AGENTS.md already exists:\n\n```bash\ntest -f AGENTS.md && echo \"exists\" || echo \"missing\"\n```\n\nIf exists, warn the user and suggest using the update workflow instead. Allow override with `--force` flag.\n\n**Analyze Project**\n\nGather comprehensive information:\n\n- Language and framework (detect from files and package configs)\n- Directory structure and organization patterns\n- Build system (npm, cargo, poetry, gradle, etc.)\n- Test framework (jest, pytest, cargo test, etc.)\n- Linting and formatting tools\n- Environment variables or configuration files\n\n**Generate AGENTS.md Content**\n\nCreate structured sections:\n\n```markdown\n# Context\n\nBrief project description and purpose.\n\n## Structure\n\nDirectory organization and key files.\n\n## Build\n\nCommands for building the project.\n\n## Test\n\nCommands for running tests.\n\n## Development\n\nConventions, patterns, and workflows.\n```\n\nAdapt sections based on project type. For `--minimal`, include only Context and Structure. For `--full`, add all applicable sections including deployment, troubleshooting, and custom tooling.\n\n**Write AGENTS.md**\n\nSave generated content and create `CLAUDE.md` symlink (`ln -sf AGENTS.md CLAUDE.md`). For `--dry-run`, display without writing.\n\n**Generate Report**\n\nDisplay summary:\n\n```\n✓ Created AGENTS.md\n  - Detected Next.js project\n  - Added npm scripts from package.json\n  - Documented project structure\n  - Added testing section for Jest\n✓ Created CLAUDE.md symlink\n```\n\nFor the complete initialize context workflow with language-specific templates, detection strategies, and customization options, refer to `references/init-agents.md`.\n\n### DOCS.md Initialization\n\nDOCS.md is optional and not created by default. Create DOCS.md manually when the project has:\n\n- Public API endpoints requiring documentation\n- Exported functions or classes intended for external use\n- Complex type definitions users need to understand\n\nThe update context workflow will suggest creating DOCS.md if it detects significant APIs without corresponding documentation.\n\n## Additional Resources\n\nFor detailed workflows, examples, and implementation guidance, refer to these reference documents:\n\n- **`references/common-patterns.md`** - Argument parsing, backup handling, writing style, report formatting, file detection, and metadata extraction\n- **`references/update-agents.md`** - Complete context file update workflow including verification strategies, diff generation, and discrepancy detection\n- **`references/update-readme.md`** - Complete README update workflow including section templates, metadata extraction, and formatting conventions\n- **`references/update-contributing.md`** - Complete CONTRIBUTING.md update workflow including scope, templates, and validation (only when CONTRIBUTING.md exists)\n- **`references/init-readme.md`** - Complete README initialization workflow including guided-mode strategies, section templates, and project-type detection\n- **`references/init-agents.md`** - Complete context initialization workflow including language-specific templates, detection strategies, and customization options\n\nThese references provide implementation details, code examples, and troubleshooting guidance for each workflow type.","tags":["docs","agent","skills","paulrberg","agent-skills","ai-agents"],"capabilities":["skill","source-paulrberg","skill-md-docs","topic-agent-skills","topic-ai-agents"],"categories":["agent-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/PaulRBerg/agent-skills/md-docs","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add PaulRBerg/agent-skills","source_repo":"https://github.com/PaulRBerg/agent-skills","install_from":"skills.sh"}},"qualityScore":"0.475","qualityRationale":"deterministic score 0.47 from registry signals: · indexed on github topic:agent-skills · 50 github stars · SKILL.md body (16,956 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-04-22T00:56:18.679Z","embedding":null,"createdAt":"2026-04-18T22:17:46.357Z","updatedAt":"2026-04-22T00:56:18.679Z","lastSeenAt":"2026-04-22T00:56:18.679Z","tsv":"'/api':675 '/api/v1/users':691 '/makefile/justfile':1570 '/md-docs':1166,1178,1228 '/readme.md':1365 'abort':1224 'absent':715,1439 'accur':66,94,478,770 'acknowledg':1007 'actual':75,109,260,527,775,1586 'ad':673,1027,1036,1382,1391,1894,1902 'adapt':1323,1840 'add':1855 'addit':1982 'agent':40,57,436,544 'agents.md':18,195,252,267,381,393,403,577,590,600,641,656,668,717,1677,1732,1735,1741,1806,1866,1876,1890 'agents.md.backup':601,655 'align':73,1296 'allow':1758 'alreadi':242,1197,1431,1736 'also':508,994 'analysi':333,765,1072,1322,1509,1683 'analyz':107,280,370,471,509,820,1234,1763 'api':229,440,547,996,1263,1308,1947,1978 'applic':969,1155,1330,1345,1857 'appropri':942 'argument':307,311,783,787,1119,1123,1485,1489,1699,1703,1997 'ask':13 'askuserquest':1216 'asset':1265 'attempt':205 'audit':1187 'audit-readi':1186 'audit/testing':1305 'auto':1447 'auto-cr':1446 'autom':63 'automat':1311 'avail':486,1565 'backup':579,583,597,926,1999 'badg':502,946,1037,1276,1394 'base':757,977,1069,1418,1680,1842 'bash':150,191,401,598,652,828,874,919,931,1203,1459,1519,1738 'basic':147,960 'blind':105 'block':1531 'branch':374,565,700,1571,1594,1644 'brief':1813 'broken':1505,1598 'build':428,493,535,671,720,949,963,1031,1782,1824,1827 'bun':1561 'cancel':1225 'cannot':369 'cargo':1785,1793 'cargo.toml':491,836 'case':747 'cat':402,404,408,831,833,835,875,923,1520 'chang':318,552,663,1496 'changelog.md':1268 'check':199,1194,1452,1733 'cla':1619,1654 'clariti':631 'class':1954 'claud':49 'claude.md':17,36,38,194,262,388,572,585,636,642,708,722,1872,1877,1908 'cli':1589 'code':50,97,464,516,1530,1626,2088 'codebas':76,110,261,282,472,528,764,1071,1421,1546,1587,1682 'command':431,496,536,672,721,958,966,1032,1514,1533,1590,1650,1825,1831 'commands/links':1506 'compar':523,1552,1582 'complet':735,1044,1223,1397,1659,1912,2011,2025,2038,2052,2069 'complex':1959 'comprehens':339,769,814,1151,1237,1722,1766 'concis':952 'conduct':1628 'config':1247,1776 'configur':437,488,500,545,1803 'confirm':161,353 'content':113,123,325,387,511,793,883,937,940,1013,1112,1129,1138,1279,1282,1363,1555,1611,1709,1807,1869 'context':31,34,53,92,247,278,377,615,737,1672,1694,1715,1723,1812,1850,1914,1968,2012,2070 'contract':1332 'contribut':244,458,561,905,911,967,1415,1449,1617,1661 'contributing.md':20,198,233,257,294,384,409,463,470,563,570,610,612,698,729,889,892,917,922,924,972,1267,1417,1430,1437,1462,1478,1518,1521,1637,2039,2049 'contributing.md.backup':613 'convent':518,702,1572,1836,2036 'correct':618,1643 'correspond':1980 'cp':599,605,611,932 'creat':28,35,117,578,582,768,925,938,1062,1142,1150,1280,1377,1448,1477,1673,1713,1721,1808,1871,1889,1907,1936,1939,1972 'createus':696 'credit':1005 'current':96,380,1420,1549 'custom':432,882,1863,1924,2081 'date':70,1174 'dco':1620 'decis':1631 'deep':332,1508 'default':1938 'defin':243 'definit':453,558,1961 'dep':1177 'depend':519,542,862 'deploy':1001,1860 'deprec':541 'deriv':1315 'describ':846 'descript':421,809,856,951,987,1078,1124,1126,1146,1252,1289,1292,1314,1338,1718,1815 'detail':887,910,1985,2087 'detect':1242,1379,1385,1548,1771,1891,1921,1976,2006,2023,2067,2078 'develop':962,1835 'diff':649,653,743,2019 'dir':157 'directori':355,480,676,848,999,1255,1777,1819 'discrep':285,522,1581,2022 'display':647,659,1018,1023,1370,1375,1634,1882,1887 'doc':3,1189,1604 'docs.md':196,220,255,292,382,405,445,451,457,551,555,559,604,606,665,686,725,1929,1931,1940,1973 'docs.md.backup':607 'document':42,47,71,89,120,144,171,288,417,524,997,1356,1524,1554,1583,1695,1899,1950,1981,1995 'dri':313,645,789,1016,1134,1368,1491,1705,1880 'dry-run':312,644,788,1015,1133,1367,1490,1704,1879 'duplic':909 'e.g':1301 'echo':1207,1209,1463,1465,1742,1744 'edg':746 'emphas':100,1294 'emphasi':1306 'endpoint':441,548,689,1948 'ensur':91,158,634 'entir':1319,1443 'entri':1259 'environ':1800 'error':211 'etc':492,1788,1795 'exampl':744,961,998,1056,1165,1269,1388,1410,1667,1987,2089 'exist':88,190,277,300,324,376,407,411,622,638,666,798,865,869,878,893,929,975,1101,1159,1192,1198,1208,1212,1221,1264,1432,1458,1464,1517,1731,1737,1743,1747,2050 'expect':1625 'expert':130,132 'expert-to-expert':129 'explicit':1104,1480 'export':514,1951 'extern':1957 'extract':416,852,1052,2009,2033 'f':603,609,921,1205,1461,1740 'featur':180,540 'file':32,54,93,112,189,201,208,248,279,321,336,378,424,510,530,584,616,713,738,1244,1457,1499,1536,1564,1716,1724,1773,1804,1823,2005,2013 'first':1304 'fix':251,328,669,687,703,718,1504,1612,1638 'flag':1762 'focus':343,1111,1128,1310 'follow':310,786,1122,1347,1488,1702 'forc':1105,1157,1214,1761 'format':1055,1351,1409,1798,2004,2035 'formatt':1544 'found':727,731 'foundri':1182 'framework':498,1241,1770,1790 'freeform':1125 'full':812,992,1149,1342,1720,1854 'function':79,446,553,693,1952 'gather':477,823,1236,1545,1765 'generat':106,122,657,753,805,813,935,1012,1021,1130,1137,1277,1362,1373,1386,1632,1708,1805,1868,1885,2020 'get':842 'get-url':841 'git':151,156,166,178,351,358,371,837,839,845,1270 'git-dir':155 'git-specif':177 'govern':1630 'gradl':1787 'guid':1108,1131,1163,1283,1290,1405,2058 'guidanc':245,906,1990,2092 'guided-mod':1404,2057 'guidelin':461,562,1450 'handl':2000 'head':1527 'help':213 'high':346 'high-level':345 'histori':372 'ideal':1082,1687 'identifi':214,284,521,1580 'imper':127 'implement':1989,2086 'import':513 'inaccuraci':329,1614 'includ':23,52,419,984,995,1335,1343,1848,1859,2016,2029,2042,2056,2073 'incorrect':534,1593 'infer':1312 'inform':418,479,525,803,824,838,1238,1584,1767 'init':26,33,1168,1180 'init-readm':1167,1179 'initi':84,170,217,1060,1398,1671,1913,1930,2054,2071 'instal':810,955,988,1028,1147,1339,1383 'instead':918,1233,1757 'instruct':58,1002 'intellig':1547 'intend':1955 'intent':1115,1300 'interfac':232,455,515 'issu':1601 'jest':1608,1791,1906 'keep':323,797 'key':1822 'keyword':1298 'la':193,483,851 'lack':1088,1693 'languag':1239,1768,1918,2075 'language-specif':1917,2074 'lend':1183 'level':347 'librari':1171,1307,1329,1381 'licens':861,948,976,1039,1253,1266,1393,1621 'limit':368 'link':915,970,1512,1599 'lint':965,1796 'linter':1543 'linting/formatting':1576 'list':1000 'ln':639,1874 'lock':1563 'ls':192,482,850 'main':1573,1597,1647 'maintain':65,620 'manag':43,45,957,1557,1640 'manual':1941 'markdown':41,1811 'master':1575,1596,1646 'match':290,1034 'maximum':1501 'may':173 'md':2 'md-doc':1 'mention':1539 'metadata':504,762,830,980,1051,1249,2008,2032 'method':443 'minim':340,804,806,982,1141,1143,1334,1712,1714,1847 'miss':207,537,571,1210,1466,1468,1745 'mit':1392 'mode':507,983,993,1109,1132,1164,1286,1291,1406,2059 'modifi':556 'multipl':826 'name':566,701,854,1250 'need':216,271,397,594,1963 'new':85,674,1084,1689 'next.js':1892 'note':218 'npm':1558,1591,1641,1784,1895 'number':858 'oper':1226 'option':222,235,254,712,818,890,1218,1288,1925,1933,2082 'order':1325 'organ':427,517,1258,1529,1780,1820 'origin':844 'outdat':529,546,560,670,688,704,719,802,1588 'output':160 'overrid':1759 'overview':44 'overwrit':581,928,1099,1158,1219 'packag':487,761,829,956,979,1246,1248,1556,1639,1775 'package.json':489,832,1035,1569,1898 'package.json/makefile/justfile':1568 'paramet':449 'pars':154,306,412,782,877,1118,1173,1484,1522,1698,1998 'path':531,690,1537 'pattern':115,512,684,1781,1837 'perform':331 'phrase':22 'pnpm':1384,1559,1592,1642 'poetri':1786 'point':575,1260 'polici':1618,1651 'pr':568,705 'prerequisit':140,1451 'present':203,386 'preserv':322,625,796,871,881,1232,1500,1502,1616,1653 'preview':791,1136,1707 'proceed':175,366,1454 'process':273,297,466,569,1623,1656 'project':46,86,148,227,420,475,759,779,821,853,953,1064,1085,1235,1321,1327,1675,1690,1717,1764,1814,1829,1844,1893,1900,1944,2065 'project-specif':1063,1674 'project-typ':2064 'prompt':1162 'protocol':1184 'provid':61,1077,1293,2085 'public':231,1262,1946 'purpos':423,1817 'pyproject.toml':490,834 'pytest':1792 'quick':341 'rather':133 'read':276,375,379,400,864,888,894,1516 'readi':1188 'readm':25,27,29,55,501,752,771,792,807,815,866,914,930,936,1009,1046,1061,1090,1094,1102,1144,1152,1169,1181,1193,1222,1231,1278,1360,1399,2026,2053 'readme.md':16,197,756,868,876,933,1026,1066,1160,1196,1206,1378 'readme.md.backup':934 'realiti':291 'refer':707,748,1057,1309,1411,1538,1595,1607,1629,1645,1668,1926,1991,1994,2084 'references/common-patterns.md':1996 'references/init-agents.md':1928,2068 'references/init-readme.md':1413,2051 'references/update-agents.md':750,2010 'references/update-contributing.md':1670,2037 'references/update-readme.md':1059,1358,2024 'reflect':95,773 'refus':1097 'relationship':520 'relev':225,238,1727 'remot':840,1271 'remov':539 'reorgan':629 'replac':1220 'repo':241 'report':658,1022,1374,1469,1633,1886,2003 'repositori':167,303,352,359,859,1087,1201,1273,1435,1692 'request':1481 'requir':1949 'resourc':1983 'rev':153 'rev-pars':152 'review':465,1622,1655 'root':1202 'rout':550 'rule':1352 'run':314,646,790,1017,1135,1369,1428,1492,1706,1833,1881 'runner':682,1542 'save':1010,1361,1867 'scan':473 'scope':2043 'scratch':1068,1679 'script':435,494,1254,1566,1896 'scripts/commands':863 'section':799,819,879,943,1004,1029,1049,1156,1295,1316,1324,1346,1354,1402,1526,1652,1728,1810,1841,1858,1904,2030,2061 'secur':1303 'security-first':1302 'separ':272,399,596 'sf':640,1875 'show':210,315,1493 'signatur':447,554,694 'signific':1977 'skill':5,60,82,99 'skill-md-docs' 'skip':183,728,732,1440 'slower':337 'smart':1331 'sourc':827,901 'source-paulrberg' 'specif':179,1065,1676,1919,2076 'src/index.ts':1390 'stale':543,564,1605 'standard':468 'state':776 'status':950 'step':305,781,912,1117,1483,1697 'still':174 'stop':1474 'strategi':742,1053,1407,1665,1922,2018,2060,2079 'structur':62,77,111,149,283,326,348,414,425,481,533,623,678,760,822,849,939,1256,1281,1525,1719,1778,1809,1818,1852,1901 'style':139,1350,2002 'suggest':1227,1752,1971 'summari':661,954,1024,1376,1635,1888 'support':308,784,1107,1120,1486,1700 'symlink':265,391,573,588,637,709,723,1873,1909 'system':1783 'tag':847 'target':188 'technic':886,1613 'templat':706,1050,1355,1403,1602,1920,2031,2044,2062,2077 'ters':126 'test':430,497,602,608,681,920,964,1204,1460,1541,1649,1739,1789,1794,1830,1834,1903 'test-runn':680 'thorough':330,506,1507 'titl':808,944,986,1145,1337 'tone':1318 'tool':433,1422,1540,1550,1577,1606,1799,1864 'topic-agent-skills' 'topic-ai-agents' 'treat':897 'tree':484 'trigger':21,439,683 'troubleshoot':1003,1861,2091 'truth':903 'tutori':138 'tutorial-styl':137 'type':452,557,1328,1845,1960,2066,2096 'typescript':1170,1380 'u':654 'understand':1965 'unless':1103,1479 'unlik':1091 'up-to-d':67 'updat':15,24,30,37,39,87,119,185,206,246,287,614,667,679,685,692,697,699,716,736,751,755,801,885,1025,1030,1045,1093,1230,1414,1416,1610,1636,1648,1660,1755,1967,2014,2027,2040 'update-readm':1092,1229 'url':843,860,1274,1534 'usag':811,959,990,1148,1340,1387 'use':8,80,142,627,873,1215,1579,1753,1958 'user':12,364,1076,1114,1472,1750,1962 'user-provid':1075 'valid':103,2046 'variabl':1801 'verbos':135 'verif':101,342,741,1664,2017 'verifi':146,187,249,350,710,724,1190,1455,1510,1729 'version':619,857,947,1041,1251 'vitest':1609 'vs':1574 'warn':362,1748 'without':319,650,794,1019,1139,1161,1213,1371,1497,1710,1883,1979 'work':354,1515 'workflow':51,145,172,186,275,304,459,739,767,780,1047,1080,1096,1116,1400,1424,1426,1442,1482,1662,1685,1696,1756,1839,1915,1969,1986,2015,2028,2041,2055,2072,2095 'would':317,1495 'write':320,617,651,795,1008,1020,1140,1349,1359,1372,1498,1711,1865,1884,2001 'yarn':1560 'zero':1176","prices":[{"id":"6d341565-b6dd-485c-895c-3ca56db79125","listingId":"e3d59af2-6e9e-44fd-9340-102abb4632e5","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"PaulRBerg","category":"agent-skills","install_from":"skills.sh"},"createdAt":"2026-04-18T22:17:46.357Z"}],"sources":[{"listingId":"e3d59af2-6e9e-44fd-9340-102abb4632e5","source":"github","sourceId":"PaulRBerg/agent-skills/md-docs","sourceUrl":"https://github.com/PaulRBerg/agent-skills/tree/main/skills/md-docs","isPrimary":false,"firstSeenAt":"2026-04-18T22:17:46.357Z","lastSeenAt":"2026-04-22T00:56:18.679Z"}],"details":{"listingId":"e3d59af2-6e9e-44fd-9340-102abb4632e5","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"PaulRBerg","slug":"md-docs","github":{"repo":"PaulRBerg/agent-skills","stars":50,"topics":["agent-skills","ai-agents"],"license":"mit","html_url":"https://github.com/PaulRBerg/agent-skills","pushed_at":"2026-04-20T16:22:56Z","description":"PRB's collection of agent skills","skill_md_sha":"c318972425d4aa1f290eb5cfca1e85c900a62a29","skill_md_path":"skills/md-docs/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/PaulRBerg/agent-skills/tree/main/skills/md-docs"},"layout":"multi","source":"github","category":"agent-skills","frontmatter":{"name":"md-docs","description":"This skill should be used ONLY when the user asks to update README.md, CLAUDE.md, AGENTS.md, or CONTRIBUTING.md. Trigger phrases include \"update README\", \"init README\", \"create README\", \"update context files\", \"init context\", \"create CLAUDE.md\", \"update CLAUDE.md\", \"update AGENTS.md\", \"update CONTRIBUTING\". Do NOT activate this skill for any other Markdown file updates."},"skills_sh_url":"https://skills.sh/PaulRBerg/agent-skills/md-docs"},"updatedAt":"2026-04-22T00:56:18.679Z"}}