{"id":49235234,"url":"https://github.com/simonepri/let-em-cook","last_synced_at":"2026-04-24T15:04:17.815Z","repository":{"id":344501845,"uuid":"1182023563","full_name":"simonepri/let-em-cook","owner":"simonepri","description":"🤌🏻 Teach AI how to cook (code) the way I like it.","archived":false,"fork":false,"pushed_at":"2026-03-15T00:47:18.000Z","size":428,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-15T12:13:20.008Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Shell","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/simonepri.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":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-03-14T23:53:45.000Z","updated_at":"2026-03-15T00:47:21.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/simonepri/let-em-cook","commit_stats":null,"previous_names":["simonepri/let-em-cook"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/simonepri/let-em-cook","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/simonepri%2Flet-em-cook","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/simonepri%2Flet-em-cook/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/simonepri%2Flet-em-cook/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/simonepri%2Flet-em-cook/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/simonepri","download_url":"https://codeload.github.com/simonepri/let-em-cook/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/simonepri%2Flet-em-cook/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32228453,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-24T13:21:15.438Z","status":"ssl_error","status_checked_at":"2026-04-24T13:21:15.005Z","response_time":64,"last_error":"SSL_read: 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":[],"created_at":"2026-04-24T15:04:14.410Z","updated_at":"2026-04-24T15:04:17.807Z","avatar_url":"https://github.com/simonepri.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/simonepri/let-em-cook\"\u003e\u003cimg src=\"assets/let-em-cook.png\" alt=\"let-em-cook\" width=\"200\" /\u003e\u003c/a\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n  🤌🏻 Teach AI how to cook (code) the way I like it.\n\u003c/p\u003e\n\n## Synopsis\n\nOut of the box, AI writes bland code — generic, safe, unseasoned. This repo encodes engineering taste and development workflows so any AI coding assistant follows my style.\n\n## Philosophy\n\nAI is already smart. What it lacks is _taste_ — your preferences, your reasoning style, your workflow. This repo teaches it three things:\n\n1. **Principles** — code style priorities, what good looks like, what to avoid\n2. **Reasoning** — how to think about any change: Problem → Goal → Solution\n3. **Workflow** — how work moves from idea to shipped code\n\nEvery rule and skill is written by a human, for a human — with parenthetical hints for agents where needed. They read like team guidelines, not robot instructions.\n\n## How `/cook` works\n\n`/cook` is the full autopilot. You describe what you want, then walk away.\n\n\u003c!-- LINT.IfChange('pipeline') --\u003e\n\n```\nYou: /cook add rate limiting to the API\n\n  ┌──────────┐\n  │  /plan   │  architect, interfaces, phases\n  └────┬─────┘\n       ▼\n  ┌──────────┐\n  │ ask user │  confirm plan — or /research gaps, then revise\n  └────┬─────┘\n       ▼\n  ┌──────────┐\n  │ /execute │  phase 1 → phase 2 → …\n  └────┬─────┘\n       ▼\n  ┌──────────┐\n  │  verify  │  smoke-test the result\n  └────┬─────┘\n       ▼\n  ┌──────────┐\n  │ /commit  │  stage + commit\n  └────┬─────┘\n       ▼\n  ┌──────────┐\n  │ /polish  │  review + /amend → 3x LGTM\n  └────┬─────┘◄── design gaps loop back to /plan, else creates report\n       ▼\n  ┌──────────┐\n  │ ask user │  approve, or back to /plan\n  └────┬─────┘\n       ▼\n  ┌──────────┐\n  │   /pr    │  push + open PR\n  └──────────┘\n```\n\n\u003c!-- LINT.ThenChange('//src/.agents/skills/cook/SKILL.md:pipeline') --\u003e\n\nEach phase runs in an isolated subagent. The orchestrator stays clean, passes only what the next step needs, and can reset any phase that goes off track.\n\n## Commands\n\n| Command     | What it does                                                             |\n| ----------- | ------------------------------------------------------------------------ |\n| `/cook`     | Full autopilot — plan, execute, polish end-to-end                        |\n| `/research` | Investigate libraries, APIs, and approaches before planning              |\n| `/plan`     | Architecture-level design — interfaces, data flow, parallelizable phases |\n| `/execute`  | Execute a plan file — spawn parallel subagents per phase                 |\n| `/commit`   | Stage changes + conventional commit message                              |\n| `/amend`    | Amend the last commit safely                                             |\n| `/review`   | Two-phase code review — investigate, then report confirmed issues only   |\n| `/polish`   | Iterative review+fix loop — 3 consecutive LGTMs to converge              |\n| `/pr`       | Create a PR — description aggregated from commits                        |\n| `/diff`     | Fetch diffs for any scope (PR, commit, branch, staged, working tree)     |\n| `/fork`     | Snapshot context to a temp file — explore a rabbit hole, resume later    |\n\n## Installation\n\n```bash\ngit clone https://github.com/simonepri/let-em-cook.git /tmp/let-em-cook\n/tmp/let-em-cook/install.sh .\nrm -rf /tmp/let-em-cook\n```\n\nThe script copies rules and skills into `.agents/`, sets up `AGENTS.md` with the command table, and creates symlinks for Claude Code (`.claude/` → `.agents/`, `CLAUDE.md` → `AGENTS.md`). It asks before overwriting anything that already exists.\n\nRun the same command again to update to the latest version.\n\n## Structure\n\nAfter installation, your project will have:\n\n```\n.agents/\n  rules/\n    code.md                   # Code style principles\n    workflow.md               # Reasoning framework + focus management\n  skills/\n    cook/SKILL.md             # Full autopilot\n    research/SKILL.md         # Pre-planning investigation\n    plan/SKILL.md             # Architecture-level design\n    execute/SKILL.md          # Plan execution engine\n    commit/SKILL.md           # Commit workflow\n    amend/SKILL.md            # Amend workflow\n    review/SKILL.md           # Code review\n    polish/SKILL.md           # Review+fix loop\n    pr/SKILL.md               # PR creation\n    diff/SKILL.md             # Diff fetching\n    fork/SKILL.md             # Context snapshot for branching\nAGENTS.md                     # Entry point (works with any AI tool)\nCLAUDE.md → AGENTS.md         # Claude Code compatibility\n.claude/\n  rules → ../.agents/rules    # Claude Code native discovery\n  skills → ../.agents/skills\n```\n\n## Customization\n\nEdit `.agents/rules/code.md` to match your style. Add your own skills to `.agents/skills/`. Delete any commands you don't use.\n\n---\n\n_Let 'em cook._ 🔥\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsimonepri%2Flet-em-cook","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsimonepri%2Flet-em-cook","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsimonepri%2Flet-em-cook/lists"}