{"id":48321115,"url":"https://github.com/espensev/ai-skills","last_synced_at":"2026-04-05T00:40:46.143Z","repository":{"id":345428180,"uuid":"1185843682","full_name":"espensev/ai-skills","owner":"espensev","description":"Portable multi-agent skill packages for Codex, Claude, and Gemini, plus worktree tooling for parallel agent workflows.","archived":false,"fork":false,"pushed_at":"2026-03-19T04:08:33.000Z","size":409,"stargazers_count":0,"open_issues_count":2,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-19T16:33:21.153Z","etag":null,"topics":["agents","ai","claude-code","codex","developer-tools","gemini","git-worktree","multi-agent"],"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/espensev.png","metadata":{"files":{"readme":"README.md","changelog":null,"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":"2026-03-19T02:01:19.000Z","updated_at":"2026-03-19T02:31:33.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/espensev/ai-skills","commit_stats":null,"previous_names":["espensev/ai-skills"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/espensev/ai-skills","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/espensev%2Fai-skills","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/espensev%2Fai-skills/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/espensev%2Fai-skills/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/espensev%2Fai-skills/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/espensev","download_url":"https://codeload.github.com/espensev/ai-skills/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/espensev%2Fai-skills/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31420640,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-05T00:25:07.052Z","status":"ssl_error","status_checked_at":"2026-04-05T00:25:05.923Z","response_time":60,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["agents","ai","claude-code","codex","developer-tools","gemini","git-worktree","multi-agent"],"created_at":"2026-04-05T00:40:45.623Z","updated_at":"2026-04-05T00:40:46.123Z","avatar_url":"https://github.com/espensev.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AI Skills\n\n**Portable, production-ready skill packages that give AI coding agents structured workflows for planning, testing, shipping, and multi-agent orchestration.**\n\n65 skills across three provider-specific packages — drop them into any project and your agents gain campaign planning, parallel worktree coordination, QA pipelines, and more.\n\n| Package | Skills | What it adds |\n|---|:---:|---|\n| **claude-skills** | 9 | Core campaign orchestration for Claude Code — planning, multi-agent management, QA, shipping |\n| **codex-skills** | 18 | Extended toolkit for Codex — adds API design, research, e2e testing, frontend/backend patterns |\n| **gemini-skills** | 38 | Full Gemini adapter with bootstrap installer, guardrails, and 30+ domain-specific skills |\n| **wt-cli** | — | TypeScript CLI for cross-platform worktree orchestration in parallel agent flows |\n\n## Quick Start\n\n**Export all ready packages** into a target folder:\n\n```powershell\n.\\scripts\\export-ready-skill-packages.ps1 -TargetDir \".\\dist\\ai-skills-ready-packages\" -Force\n```\n\n**Bootstrap Gemini skills** into another repo:\n\n```powershell\n.\\gemini-skills\\scripts\\bootstrap.ps1 -TargetDir \"C:\\path\\to\\target-repo\"\n```\n\nThe bootstrap script creates `.gemini/skills/` and `.gemini/commands/`, copies skill wrappers, and injects multi-agent guardrails into `GEMINI.md`.\n\n## What's Inside\n\n### Core Skills (shared across packages)\n\n| Skill | Purpose |\n|---|---|\n| **planner** | Design structured multi-agent campaign plans with work decomposition and dependency mapping |\n| **manager** | Orchestrate parallel agents in worktrees — launch, merge, verify builds |\n| **discover** | Research a codebase before planning — map dependencies, assess feasibility, identify constraints |\n| **qa** | Run tests, check coverage, triage failures, smoke-test endpoints, generate regression tests |\n| **ship** | Stage, commit, push validated work with campaign-aware commit grouping |\n| **observer** | Passive project intelligence — observe patterns over time without interfering |\n| **loop** | Run focused work loops with repeated inspect-edit-verify cycles |\n\n### Codex Extras\n\nAPI design, backend/frontend patterns, deep research, Playwright e2e testing, documentation lookup, MCP server patterns, and more.\n\n### Gemini Extras\n\nArchitecture decision records, codebase onboarding, forensic debugger, epic refactor, Django TDD, Rust/Go/Kotlin/C# patterns, security scanning, doc weaver, and a full guardrail system enforcing contract-first execution and scoped writes.\n\n## Architecture\n\nEach package follows a **contract-first, read-all write-scoped** design:\n\n- Skills reference shared contracts (`planning-contract.md`, `system-map.md`) that define required plan elements and agent specs\n- Agents read the full repo for context but only write to explicitly scoped files\n- All material claims require source evidence (file path, line number, or command output)\n\nThe export script reads `release-manifest.json` to determine which packages are ready and applies the correct export strategy — `portable-runtime` for Claude/Codex, `gemini-adapter` for Gemini.\n\n## Repository Layout\n\n```\ncodex-skills/       Codex package — skills, contracts, Python runtime\nclaude-skills/      Claude package — skills, contracts, Python runtime\ngemini-skills/      Gemini package — skills, commands, bootstrap, guardrails\nwt-cli/             Worktree orchestration CLI (TypeScript)\nscripts/            Export automation\ndocs/               Release notes and readiness tracking\n```\n\n## License\n\n[MIT](LICENSE) — Espen Severinsen\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fespensev%2Fai-skills","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fespensev%2Fai-skills","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fespensev%2Fai-skills/lists"}