{"id":48879217,"url":"https://github.com/chrislacey89/skills","last_synced_at":"2026-04-16T02:02:55.048Z","repository":{"id":349849094,"uuid":"1204049898","full_name":"chrislacey89/skills","owner":"chrislacey89","description":"Pipeline-first Claude Code skills pack — 19 composable skills for structured feature delivery from shape to ship","archived":false,"fork":false,"pushed_at":"2026-04-07T19:41:40.000Z","size":162,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"prod","last_synced_at":"2026-04-07T21:27:18.219Z","etag":null,"topics":["agent-skills","ai-workflow","claude-code","claude-code-skills","claude-skills","feature-delivery","skills-pack"],"latest_commit_sha":null,"homepage":"https://skills.sh/chrislacey89/skills","language":"JavaScript","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/chrislacey89.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","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":null,"dco":null,"cla":null}},"created_at":"2026-04-07T16:35:25.000Z","updated_at":"2026-04-07T19:41:45.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/chrislacey89/skills","commit_stats":null,"previous_names":["chrislacey89/skills"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/chrislacey89/skills","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chrislacey89%2Fskills","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chrislacey89%2Fskills/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chrislacey89%2Fskills/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chrislacey89%2Fskills/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/chrislacey89","download_url":"https://codeload.github.com/chrislacey89/skills/tar.gz/refs/heads/prod","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chrislacey89%2Fskills/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31867712,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-15T15:24:51.572Z","status":"online","status_checked_at":"2026-04-16T02:00:06.042Z","response_time":69,"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-workflow","claude-code","claude-code-skills","claude-skills","feature-delivery","skills-pack"],"created_at":"2026-04-16T02:02:54.306Z","updated_at":"2026-04-16T02:02:55.030Z","avatar_url":"https://github.com/chrislacey89.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Skills\n\n[![License: MIT](https://img.shields.io/github/license/chrislacey89/skills)](LICENSE)\n![Skills](https://img.shields.io/badge/skills-23-blue)\n![CLI](https://img.shields.io/badge/npx%20skills-compatible-green)\n\nA pipeline-first Claude Code skills pack for structured feature delivery. 23 composable skills that take a feature from idea to shipped — with explicit handoffs, verified research, and a compounding knowledge loop.\n\nBuilt around structured research, GitHub-native state, and a compounding knowledge loop in `docs/solutions/`. Compatible with Claude Code, Cursor, Windsurf, and any agent that can consume SKILL.md files.\n\n## Installation\n\nGlobal install (all skills, Claude Code):\n\n```bash\nnpx skills@latest add chrislacey89/skills --skill '*' --agent claude-code --global -y\n```\n\n## Keeping skills updated\n\nThe skills CLI tracks content hashes. When this repo updates, your installed copies know about it:\n\n```bash\nnpx skills@latest check    # see what changed upstream\nnpx skills@latest update   # pull latest versions\n```\n\n## What this pack optimizes for\n\n- **GitHub-native state** — PRDs, slices, QA bugs, and lineage live in GitHub issues and PRs, not a sprawling local planning filesystem.\n- **Explicit handoffs** — skills declare what they expect, what they produce, and what comes next.\n- **Verified research before PRD writing** — `/research` is a first-class step, not an optional extra.\n- **Compounded knowledge** — shipped lessons feed future work through `docs/solutions/`.\n\n## Canonical pipeline\n\n```\n/shape → /research → /write-a-prd → /prd-to-issues → /execute → QA → /pre-merge → merge → /compound → cleanup\n```\n\nThe pipeline is the default path, not a prison. Skills can backtrack when assumptions fail or branch to helper and side-route skills when the work demands it. For blank-project or major-tranche work that is too large for a single PRD, `/shape` can branch to `/create-milestone`, which creates a GitHub milestone plus feature issues that mature from `roadmap bet` to `research-ready` to `prd` before re-entering the normal pipeline at `/research`. `Ralph` is the AFK execution mode/persona for the `/execute` stage, not a separate pipeline step — it stops on repeated failure *or* repeated non-progress, whichever trips first.\n\n## Skills\n\n### Planning \u0026 Design\n\n| Skill | Description |\n|-------|-------------|\n| [shape](shape/) | Structured requirements discovery — shared understanding before research |\n| [create-milestone](create-milestone/) | Turn a shaped app-sized or tranche-sized idea into a GitHub milestone with sequenced feature bets |\n| [research](research/) | Mandatory pre-PRD research with auto-calibrated depth |\n| [write-a-prd](write-a-prd/) | PRD creation via interview, filed as GitHub issue |\n| [prd-to-issues](prd-to-issues/) | Break PRD into vertical slices with boundary maps |\n| [design-an-interface](design-an-interface/) | Generate multiple radically different interface designs |\n| [api-design-review](api-design-review/) | Focused contract review for higher-risk API design decisions |\n\n### Development\n\n| Skill | Description |\n|-------|-------------|\n| [execute](execute/) | Execute a unit of work end-to-end with verification |\n| [tdd](tdd/) | Test-driven development with red-green-refactor loop (invoked from `/execute`) |\n| [triage-issue](triage-issue/) | Deep bug diagnosis + root cause + TDD fix plan (invoked from `/qa` per issue) |\n| [improve-codebase-architecture](improve-codebase-architecture/) | Surface deepening opportunities for shallow modules |\n| [request-refactor-plan](request-refactor-plan/) | Plan refactors with tiny commits |\n| [ts-audit](ts-audit/) | Audit TypeScript code against Total TypeScript best practices |\n\n### Tooling \u0026 Setup\n\n| Skill | Description |\n|-------|-------------|\n| [init-pipeline](init-pipeline/) | Scaffold pipeline enforcement — Claude Code hooks, git guardrails, pre-commit setup (auto-invoked by `/execute`) |\n| [setup-pre-commit](setup-pre-commit/) | Lefthook + Biome pre-commit hooks (detects existing tools) |\n| [git-guardrails-claude-code](git-guardrails-claude-code/) | Block dangerous git commands |\n\n### Knowledge \u0026 QA\n\n| Skill | Description |\n|-------|-------------|\n| [qa](qa/) | Single entry point for bug conversations; files lightweight issues and delegates per-issue to `/triage-issue` for deep diagnosis |\n| [pre-merge](pre-merge/) | Create the PR and run an architectural review before merge |\n| [compound](compound/) | Capture lessons learned into docs/solutions/ |\n| [ubiquitous-language](ubiquitous-language/) | DDD glossary with decisions register |\n\n### Orientation \u0026 Recovery\n\n| Skill | Description |\n|-------|-------------|\n| [help](help/) | Read repo state and recommend the next pipeline step |\n| [correct-course](correct-course/) | Diagnose stale artifacts and walk the cleanup before backtracking |\n\n## Repo guide\n\n- **[docs/using-this-pack.md](docs/using-this-pack.md)** — how to operate the pack end-to-end\n- **[SYSTEM-OVERVIEW.md](SYSTEM-OVERVIEW.md)** — workflow philosophy, state model, and detailed pipeline rationale\n- **[CLAUDE.md](CLAUDE.md)** — editing conventions for agents working on this repository itself\n- **[docs/skill-anatomy.md](docs/skill-anatomy.md)** — structure and quality bar for `SKILL.md` files\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchrislacey89%2Fskills","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fchrislacey89%2Fskills","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchrislacey89%2Fskills/lists"}