{"id":50729172,"url":"https://github.com/snowfluke/my-tech-lead-flow","last_synced_at":"2026-06-10T07:02:48.206Z","repository":{"id":359423574,"uuid":"1246016625","full_name":"snowfluke/my-tech-lead-flow","owner":"snowfluke","description":"AI Agent Skills library to facilitate technical lead in a software project","archived":false,"fork":false,"pushed_at":"2026-05-30T14:58:16.000Z","size":231,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-30T16:20:47.820Z","etag":null,"topics":["ai-agent","claude-code","coding-agents","skill"],"latest_commit_sha":null,"homepage":"","language":"Python","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/snowfluke.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":null,"dco":null,"cla":null}},"created_at":"2026-05-21T19:40:27.000Z","updated_at":"2026-05-30T14:58:19.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/snowfluke/my-tech-lead-flow","commit_stats":null,"previous_names":["snowfluke/my-tech-lead-flow"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/snowfluke/my-tech-lead-flow","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snowfluke%2Fmy-tech-lead-flow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snowfluke%2Fmy-tech-lead-flow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snowfluke%2Fmy-tech-lead-flow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snowfluke%2Fmy-tech-lead-flow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/snowfluke","download_url":"https://codeload.github.com/snowfluke/my-tech-lead-flow/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snowfluke%2Fmy-tech-lead-flow/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34140776,"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":["ai-agent","claude-code","coding-agents","skill"],"created_at":"2026-06-10T07:02:47.350Z","updated_at":"2026-06-10T07:02:48.199Z","avatar_url":"https://github.com/snowfluke.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Claude Code Skills\n\nPersonal skill library for Claude Code. The core of this repository is a\n**technical lead pipeline**: a sequence of skills that takes a product idea\nfrom raw user stories all the way to a reviewed, documented, deployable\ncodebase. Each stage is a skill that reads the artifacts produced by the\nprevious stage and writes the next one, so the project documentation stays\nconsistent and every decision is traceable back to an acceptance criterion.\n\n## The technical lead pipeline\n\nThe pipeline runs in order. Steps 1 and 3 are manual (the human supplies or\nedits the source material); every other step is a skill invoked with `/\u003cname\u003e`.\nStep 0 is optional, for projects that start from an idea rather than a written\nspec.\n\n| Step | Stage | Skill | Produces |\n| ---- | ----- | ----- | -------- |\n| 0 | Discover (optional) | `product-discovery` | The step-1 requirements table, elicited by interview, when no user stories or AC exist yet |\n| 1 | Capture requirements | (manual or step 0) | A Markdown table of user stories, acceptance criteria, and a sprint breakdown |\n| 2 | Groom | `grooming` | Engineering's gaps before commitment. Two modes: blast every question into a file with recommendations (to take to a BA/PO), or interview the user one question at a time and refine the US/AC from their answers |\n| 3 | Refine | (manual) | Edits to the US and AC based on grooming output |\n| 4 | Format | `us-ac-formatter` | `docs/business/`: `user-story.md`, `sprint-breakdown.md`, and per-sprint Gherkin acceptance criteria |\n| 5 | Specify | `technical-spec` | `docs/technical-specs/`: numbered `NN-topic.md` files plus `_index.md`, including ad-hoc trailing specs. Grills on tech stack and tooling first |\n| 6 | Spec the API | `api-spec` | `docs/api-specs/`: numbered `NN-topic.md` files plus `_index.md`, deriving every operation, its inputs/outputs, errors, and access rules from the module definitions and data model, in the project's chosen protocol (REST/GraphQL/gRPC/SOAP) |\n| 7 | Plan work | `task-breakdown` | `docs/TASK_BREAKDOWN.md`: sprint-by-sprint, role-assigned cards, with frontend/backend wiring as its own owned card. Grills on team shape and scope first |\n| 8 | Set up project | `tech-lead-setups` | The Sprint 0 scaffold: folder structure, architectural patterns, commit hooks, tooling config, and endpoint/page stubs returning mock responses. Grills first, then executes |\n| 9 | Set standards | `coding-standard` | `CODING_STANDARD.md` and `CODE_REVIEW_CHECKLIST.md`. Grills on every open rule first |\n| 10 | Init GitHub project | `github-project-init` | Issues from every task card (assigned, labelled, milestoned, in the board Backlog), the Projects v2 Kanban board, `dev`/`test`/`main` branches with protection, issue and PR templates, CI quality and build workflows, dependabot, and a release template |\n| 11 | Plan deployment | `deployment-plan` | `DEPLOYMENT_PLAN.md`: an operational runbook. Grills on infrastructure first |\n| 12 | Orient newcomers | `project-docs` | `README.md`, `GLOSSARY.md`, `DEVELOPMENT_SCENARIO_GUIDE.md`, `ONBOARDING_GUIDE.md` |\n| 13 | Document failures | `troubleshooting` | `TROUBLESHOOTING.md`: symptom-indexed guide, scaffolded from the architecture seams |\n| 14 | Init agent manual | `init-claude` | `CLAUDE.md`: a dense agent operating manual distilled from the specs, standard, task breakdown, and deployment plan. Grills on the gaps the docs leave open first |\n| 15 | Build | (manual + skills below) | The implementation |\n| 16 | Review | `code-review` | A structured PR review against the standards, run in an isolated git worktree |\n\n### How the stages connect\n\n- `product-discovery` (step 0) is the on-ramp when no requirements exist yet: it\n  interviews and emits the step-1 table, then hands off to `grooming`.\n- `grooming`, `us-ac-formatter`, and `technical-spec` all treat `docs/business/`\n  as the product source of truth.\n- `technical-spec` is the architectural keystone: the tech stack, data model,\n  and module boundaries it fixes are what `api-spec`, `task-breakdown`,\n  `tech-lead-setups`, `coding-standard`, and `deployment-plan` build on.\n- `api-spec` turns the module definitions and data model into concrete operation\n  contracts; `task-breakdown` and `tech-lead-setups` cite those contracts when\n  carving cards and stubbing endpoints.\n- `tech-lead-setups` reads the technical specs to build the scaffold that\n  `coding-standard` then describes and `code-review` enforces.\n- `coding-standard` writes the two documents that `code-review` consumes as its\n  source of truth.\n- `github-project-init` turns `task-breakdown`'s cards into GitHub issues on a\n  board, and its CI quality gate and PR template reference the coding standard.\n- `deployment-plan` writes the runbook that `troubleshooting` references rather\n  than duplicates.\n- `init-claude` runs last, distilling the specs, standard, task breakdown, and\n  deployment plan into the `CLAUDE.md` an agent reads before building.\n- Every doc cross-links its siblings instead of restating their content, so\n  facts live in exactly one place.\n\n## Supporting skills\n\nGeneral-purpose skills that assist the pipeline at any stage:\n\n- `grill-me`, `grill-with-docs`: stress-test a plan or design before building.\n- `diagnose`: disciplined debugging loop. Feeds confirmed incidents back into\n  `troubleshooting`.\n- `tdd`: red-green-refactor build loop.\n- `to-prd`, `to-issues`, `triage`: convert context into tracked work.\n- `improve-codebase-architecture`, `zoom-out`, `prototype`, `simplify`.\n- `git-commit`, `setup-pre-commit`, `git-guardrails-claude-code`.\n- `stop-slop`: remove AI writing patterns from prose.\n- `handoff`, `caveman`, `skill-creator`, `write-a-skill`.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsnowfluke%2Fmy-tech-lead-flow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsnowfluke%2Fmy-tech-lead-flow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsnowfluke%2Fmy-tech-lead-flow/lists"}