{"id":51861641,"url":"https://github.com/juninmd/skills","last_synced_at":"2026-07-24T08:02:15.842Z","repository":{"id":355447121,"uuid":"1226060503","full_name":"juninmd/skills","owner":"juninmd","description":null,"archived":false,"fork":false,"pushed_at":"2026-07-17T04:12:48.000Z","size":75128,"stargazers_count":1,"open_issues_count":4,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2026-07-17T06:11:21.759Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/juninmd.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-04-30T23:50:01.000Z","updated_at":"2026-07-17T04:12:51.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/juninmd/skills","commit_stats":null,"previous_names":["juninmd/skills"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/juninmd/skills","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/juninmd%2Fskills","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/juninmd%2Fskills/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/juninmd%2Fskills/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/juninmd%2Fskills/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/juninmd","download_url":"https://codeload.github.com/juninmd/skills/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/juninmd%2Fskills/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35832970,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-07-20T02:08:10.276Z","status":"online","status_checked_at":"2026-07-24T02:00:07.870Z","response_time":62,"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":[],"created_at":"2026-07-24T08:02:15.125Z","updated_at":"2026-07-24T08:02:15.837Z","avatar_url":"https://github.com/juninmd.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n\u003cimg src=\"./docs/public/images/hero-banner.svg\" alt=\"Agent skills with reproducible engineering checks\" width=\"100%\" /\u003e\n\n\u003ch3\u003eCompact engineering skills with focused procedures and reproducible checks.\u003c/h3\u003e\n\n\u003cp\u003e\u003cstrong\u003e17 skills · 4 agents · 4 prompts\u003c/strong\u003e for coding assistants that inspect first, change narrowly, and finish with evidence.\u003c/p\u003e\n\n\u003c/div\u003e\n\n## Why this exists\n\nGeneric skill catalogs often fail in two ways:\n\n- Many narrow skills overlap and waste context.\n- Broad skills contain generic advice, stale links, or no executable workflow.\n\nThis catalog uses 17 domain skills. Every skill has:\n\n- Spec-compliant frontmatter containing only `name` and `description`.\n- A description that states what the skill does and when to use it.\n- A short operational workflow.\n- Conditional links to real local references.\n- A concise completion checklist.\n- A maximum of 400 words in `SKILL.md`.\n\n## Install\n\n```bash\n# Everything\nnpx skills add juninmd/skills --all\n\n# Inspect available skills\nnpx skills add juninmd/skills --list\n\n# Install one domain\nnpx skills add juninmd/skills --skill diagnostics\n```\n\nThe repository also works as a VS Code/Copilot plugin or as an `.agents` directory:\n\n```bash\ngit submodule add https://github.com/juninmd/skills .agents\n```\n\n## Skill Catalog\n\n\u003c!-- skill-catalog:start --\u003e\n| Skill | Use it for |\n|---|---|\n| `agent-engineering` | agent loops, tool schemas, handoffs, prompt-injection defenses, tracing, and agent evaluations |\n| `backend-node` | NestJS services, pnpm workspaces, strict TypeScript, REST or GraphQL APIs, DTO validation, tests, builds, and API contracts |\n| `backend-python` | uv and pyproject setup, Ruff, typed Python, Pydantic v2, async boundaries, pytest, and Alembic integration |\n| `backend-systems` | APIs, concurrency, cancellation, error handling, EF Core, resource lifetimes, performance-sensitive code, tests, and builds |\n| `cloud-devops` | pipelines, Dockerfiles, Terraform or Pulumi, deployment safety, logs, metrics, and traces |\n| `data-engineering` | PostgreSQL, MongoDB, Redis, query plans, indexes, locks, rollback, backups, and vector database performance |\n| `diagnostics` | bugs, regressions, flaky tests, crashes, timeouts, DNS, ports, HTTP, TLS, and root-cause analysis |\n| `expert-review` | pull-request review, design review, plan stress-testing, risk analysis, and evidence-based findings |\n| `frontend-engineering` | React, Next.js, Vite, Tailwind, shadcn/ui, responsive design, component systems, browser performance, hydration, keyboard behavior, and accessibility |\n| `incident-response` | outages, error spikes, failed deploys, rollback decisions, data-integrity incidents, on-call triage, severity assessment, and corrective-action follow-up |\n| `mobile-engineering` | mobile UI, lifecycle, navigation, permissions, offline behavior, accessibility, device integration, tests, and builds |\n| `performance-engineering` | slow endpoints, N+1 queries, memory leaks, event-loop blocking, bundle size, load testing, caching decisions, and performance regressions |\n| `project-lifecycle` | PRDs, implementation plans, issue slicing, GitHub triage, worktrees, branch completion, and delivery documentation |\n| `security-ops` | CVE or SBOM scans, Gitleaks findings, secret rotation, access control, injection risk, least privilege, and zero-trust reviews |\n| `software-architecture` | modularization, dependency direction, technical debt, distributed systems, Electron architecture, failure modes, and ADRs |\n| `test-engineering` | TDD, Vitest, pytest, unhappy paths, flaky tests, fixtures, mocks, fuzzing, coverage gaps, and regression benchmarks |\n| `tooling-dev` | CLI arguments, exit codes, non-interactive execution, config discovery, structured output, packaging, and integration tests |\n\u003c!-- skill-catalog:end --\u003e\n\n## Skill Example\n\n```yaml\n---\nname: diagnostics\ndescription: |\n  Reproduce and isolate software, test, performance, and network failures. Use for bugs, regressions, flaky tests, DNS, HTTP, TLS, timeouts, and root-cause analysis.\n---\n```\n\nThe description is the discovery signal. The body loads only after the skill is selected.\n\n## Quality Contract\n\n[`AGENTS.md`](./AGENTS.md) defines the shared operating contract:\n\n- SecOps before QA, QA before DevOps, DevOps before SWE.\n- Read before write.\n- Minimum, surgical changes.\n- Reproduce bugs before fixing.\n- No destructive Git, database, or infrastructure operations without confirmation.\n- No claim of completion without lint, scoped tests, and a smoke check.\n\n## Validate\n\n```bash\npnpm install --frozen-lockfile\npnpm run validate\npnpm run docs:build\n```\n\n`pnpm run validate` checks:\n\n- Plugin manifest and referenced directories.\n- Skill name/folder consistency.\n- YAML-parsed frontmatter limited to `name` and `description`.\n- Useful description and valid skill name.\n- `## Checklist` presence.\n- 400-word skill budget.\n- 1024-character description limit (Agent Skills spec).\n- Local reference links and no orphan reference files.\n- Linked topic maps for large reference collections.\n- Token budgets: tier-1 catalog ≤ 2000 tokens, each `SKILL.md` ≤ 700 tokens (`pnpm run tokens:report` for the full breakdown).\n- Generated README catalog consistency.\n- Validator unit tests.\n\n## Layout\n\n```text\n.\n├── plugin.json\n├── AGENTS.md\n├── .agents/\n│   ├── agents/\n│   ├── prompts/\n│   ├── skills/\n│   └── tools/\n└── docs/\n```\n\n## Contributing\n\n1. Add or update `.agents/skills/\u003cname\u003e/SKILL.md`.\n2. Keep `name` equal to the folder.\n3. State what the skill does and when to use it in `description`.\n4. Link detailed material from `references/`; do not duplicate it in `SKILL.md`.\n5. Run `pnpm run catalog:generate` after adding or renaming a skill.\n6. Run `pnpm run validate` and `pnpm run docs:build`.\n\n## License\n\nMIT.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjuninmd%2Fskills","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjuninmd%2Fskills","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjuninmd%2Fskills/lists"}