{"id":50749902,"url":"https://github.com/ribeirogab/agent-skills","last_synced_at":"2026-06-11T00:30:43.940Z","repository":{"id":355079655,"uuid":"1225944065","full_name":"ribeirogab/agent-skills","owner":"ribeirogab","description":"Reusable agent skills for any tool that supports the open agent skills standard.","archived":false,"fork":false,"pushed_at":"2026-05-15T18:01:54.000Z","size":584,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-15T19:55:28.219Z","etag":null,"topics":["agent-skills","ai-agents","anthropic","claude-code","claude-skills","harness","skills"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ribeirogab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":"NOTICE.md","maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-04-30T20:10:14.000Z","updated_at":"2026-05-15T18:01:55.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/ribeirogab/agent-skills","commit_stats":null,"previous_names":["ribeirogab/agent-skills"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ribeirogab/agent-skills","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ribeirogab%2Fagent-skills","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ribeirogab%2Fagent-skills/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ribeirogab%2Fagent-skills/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ribeirogab%2Fagent-skills/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ribeirogab","download_url":"https://codeload.github.com/ribeirogab/agent-skills/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ribeirogab%2Fagent-skills/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34177445,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-10T02:00:07.152Z","response_time":89,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-skills","ai-agents","anthropic","claude-code","claude-skills","harness","skills"],"created_at":"2026-06-11T00:30:43.030Z","updated_at":"2026-06-11T00:30:43.922Z","avatar_url":"https://github.com/ribeirogab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# agent-skills\n\nReusable agent skills for any tool that supports the open agent skills standard — Claude Code, Codex, Cursor, OpenCode, Gemini CLI, Aider, Cline, Augment, and others. Skills are framework-agnostic by design: a skill is a folder with a `SKILL.md` and any helpers it needs; agents discover them by description.\n\n\u003e Personal project, solo maintenance, best-effort, no SLA. Published so anyone can pull a skill into their setup.\n\n---\n\n## Skills\n\n### `memex`\n\nIdempotently scaffolds a memex — an externalized, navigable project memory for agents — into any repository: a `.vault/` knowledge vault, an `AGENTS.md` (with a `CLAUDE.md` symlink for back-compat), spec/plan/task templates, plus a set of bundled `memex-*` slash commands (open-pr, learn, spec, review-spec, sweep) and companion skills (brainstorming, recall, writing-plans). Audit-first, autonomous-fix, with a Phase-5 validator. Safe to re-run.\n\n**Install:**\n\n```bash\nnpx skills add ribeirogab/agent-skills --skill memex\n```\n\n**Use:** point an agent at any repo where you want the memex installed.\n\n\u003e \"Audit the memex in this repo and scaffold whatever is missing.\"\n\nAfter the first run the repo has a working `.vault/` vault, the `memex-*` commands, and the companion skills, all dogfood-tested by the memex's own 13-check validator.\n\n**Source:** [`skills/memex/SKILL.md`](skills/memex/SKILL.md)\n\n---\n\n### `skill-improver`\n\nAudits an existing agent skill against the canonical authoring rules (frontmatter, layout, body style, progressive disclosure, description quality, degrees of freedom) and applies safe fixes autonomously. Defers high-regression-risk findings for manual review. Self-contained — bundles vendored copies of `quick_validate.py` and `package_skill.py` so it does not require the upstream `skill-creator` to be installed.\n\n**Install:**\n\n```bash\nnpx skills add ribeirogab/agent-skills --skill skill-improver\n```\n\n**Use:** point it at any skill folder.\n\n\u003e \"Audit the skill at `skills/my-skill` and apply safe fixes.\"\n\nThe skill walks a 10-section canonical checklist, applies anything `Low` or `Medium` regression-risk autonomously, and produces a final report with a `Skipped` section for `High`-risk findings the maintainer should review by hand.\n\n**Source:** [`skills/skill-improver/SKILL.md`](skills/skill-improver/SKILL.md)\n\n---\n\n## Repository layout\n\nWhat matters for users is just `skills/`. Each subfolder is one publishable skill:\n\n```\nagent-skills/\n├── skills/\n│   ├── memex/\n│   └── skill-improver/\n├── LICENSE                    # MIT, this repository's original work\n├── NOTICE.md                  # attribution for any vendored content inside skills/\n├── CONTRIBUTING.md\n├── CODE_OF_CONDUCT.md\n├── SECURITY.md\n└── README.md\n```\n\nThe repository also contains `.agents/`, `.claude/`, `.vault/`, and `evals/` — local-only dirs used by the maintainer to dogfood the memex, run skill evaluations, and store personal project notes. They are not part of the published surface and are not what `npx skills add` installs.\n\n## License\n\nThis repository's original work is licensed under the [MIT License](LICENSE). Any vendored third-party content inside the published skills is governed by its upstream license; see [`NOTICE.md`](NOTICE.md) for the full attribution.\n\n## Contributing\n\nPull requests welcome — see [`CONTRIBUTING.md`](CONTRIBUTING.md) for scope, the quality bar, and the per-PR checklist. By participating, you agree to the [Code of Conduct](CODE_OF_CONDUCT.md). Security concerns go to [`SECURITY.md`](SECURITY.md).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fribeirogab%2Fagent-skills","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fribeirogab%2Fagent-skills","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fribeirogab%2Fagent-skills/lists"}