{
  "markdown": "<img src=\"./tracerkit.png?c=2\" alt=\"TracerKit\" width=\"100%\" />\n\n<br />\n\n> **Archived.** This repository is no longer maintained. Use [agent-skills](https://github.com/helderberto/agent-skills) instead.\n\n<br />\n\n<div align=\"center\">\n\n[![CI](https://github.com/helderberto/tracerkit/actions/workflows/ci.yml/badge.svg)](https://github.com/helderberto/tracerkit/actions/workflows/ci.yml)\n[![npm version](https://img.shields.io/npm/v/tracerkit)](https://www.npmjs.com/package/tracerkit)\n[![npm downloads](https://img.shields.io/npm/dm/tracerkit)](https://www.npmjs.com/package/tracerkit)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n\nReplace ad-hoc AI prompts with a repeatable spec-driven workflow: from idea to verified spec.\n\nNamed after the tracer-bullet technique from _The Pragmatic Programmer_: **Tracer** + **Kit**.\n\n**Markdown skills, zero runtime deps.** No build step, no project dependencies.\n\n</div>\n\n## Why TracerKit?\n\nAI assistants work best with small, well-scoped tasks — not sprawling layers or flat task lists. TracerKit structures every feature as **tracer-bullet vertical slices**: each phase cuts through every layer (schema → service → API → UI → tests) and is demoable on its own. Integration problems surface early, not at the end.\n\nFour skills drive the workflow: **define** (`/tk:prd`), **plan** (`/tk:plan`), **build** (`/tk:build`), **verify** (`/tk:check`). The AI reads your specs directly, counts progress, and marks completed work done. Pure Markdown, zero runtime deps.\n\n```\nDEFINE          PLAN           BUILD            VERIFY\n/tk:prd  ───▶  /tk:plan  ───▶  /tk:build  ───▶  /tk:check\n  │               │               │                 │\n  ▼               ▼               ▼                 ▼\nPRD doc       Phased plan    Implement phase    Pass/fail\n                              + feedback loops\n```\n\n## Get Started\n\n<details open>\n<summary><b>Claude Code (recommended)</b></summary>\n\n**Marketplace install:**\n\n```\n/plugin marketplace add helderberto/tracerkit\n/plugin install tk@tracerkit-marketplace\n```\n\n**CLI install:**\n\n```bash\nnpm install -g tracerkit\ntracerkit init\n```\n\nSkills are installed to `~/.claude/skills/`, available in every project. Safe to re-run.\n\n<details>\n<summary>Per-project install (team members get skills via git)</summary>\n\n```bash\ntracerkit init .              # install to .claude/skills/ in current dir\ntracerkit update .            # update project-scoped skills\ntracerkit uninstall .         # remove project-scoped skills\n```\n\n</details>\n\n</details>\n\n<details>\n<summary><b>Cursor</b></summary>\n\nCopy skills into `.cursor/rules/`, or use Notepads for on-demand context. See [docs/cursor-setup.md](docs/cursor-setup.md).\n\n</details>\n\n<details>\n<summary><b>Gemini CLI</b></summary>\n\nInstall as native skills for auto-discovery:\n\n```bash\ngemini skills install https://github.com/helderberto/tracerkit.git --path skills\n```\n\nOr add to `GEMINI.md` for persistent context. See [docs/gemini-cli-setup.md](docs/gemini-cli-setup.md).\n\n</details>\n\n<details>\n<summary><b>GitHub Copilot</b></summary>\n\nCopy skills to `.github/skills/` or add workflow rules to `.github/copilot-instructions.md`. See [docs/copilot-setup.md](docs/copilot-setup.md).\n\n</details>\n\n<details>\n<summary><b>OpenCode</b></summary>\n\nUses agent-driven skill execution via `AGENTS.md`. See [docs/opencode-setup.md](docs/opencode-setup.md).\n\n</details>\n\n<details>\n<summary><b>Other agents</b></summary>\n\nSkills are plain Markdown with YAML frontmatter — they work with any agent that accepts instruction files. Clone the repo and point your agent at the `skills/` directory.\n\n</details>\n\n### Workflow\n\n```\nYou: /tk:prd add dark mode support\nAI:  Written .tracerkit/prds/dark-mode-support.md\n     Run `/tk:plan dark-mode-support` next?\n\nYou: /tk:plan dark-mode-support\nAI:  Phase 1 — Theme visible end-to-end\n     Phase 2 — User can toggle and persist preference\n     Written .tracerkit/plans/dark-mode-support.md\n     Run `/tk:check dark-mode-support` when ready?\n\nYou: /tk:build dark-mode-support\nAI:  Phase 1 — Theme visible end-to-end (3 remaining)\n     Implementing... all checks pass. Commit?\n\nYou: /tk:check dark-mode-support\nAI:  Total: 7/7\n     All phases complete — implementation verified.\n```\n\nBetween sessions, `/tk:brief` shows active features and picks up where you left off:\n\n```\nYou: /tk:brief\nAI:  dark-mode-support (3/7)\n       Phase 1 — Theme visible end-to-end: 3/3\n     > Phase 2 — User can toggle and persist preference: 0/4\n\n     **Focus → dark-mode-support**\n```\n\nSee [Examples](docs/examples.md) for full walkthroughs.\n\n## Skills\n\n| Skill              | What it does                                           | Output                               |\n| ------------------ | ------------------------------------------------------ | ------------------------------------ |\n| `/tk:prd <idea>`   | Interview → codebase scan → structured PRD             | `.tracerkit/prds/<slug>.md`          |\n| `/tk:plan <slug>`  | PRD → phased vertical slices, each demoable on its own | `.tracerkit/plans/<slug>.md`         |\n| `/tk:build <slug>` | Implement next incomplete phase, run feedback loops    | Code changes + checked items in plan |\n| `/tk:brief`        | Feature dashboard with progress and suggested focus    | Terminal only, no files              |\n| `/tk:check [slug]` | Verify done-when checkboxes against codebase and tests | Checkboxes updated in plan           |\n\n## Docs\n\n| Document                                     | Description                                       |\n| -------------------------------------------- | ------------------------------------------------- |\n| [Examples](docs/examples.md)                 | Walk through end-to-end usage scenarios           |\n| [CLI Reference](docs/cli-reference.md)       | Commands: init, update, uninstall                 |\n| [Comparison](docs/comparison.md)             | Compare TracerKit to Spec Kit, Kiro, and OpenSpec |\n| [Cursor Setup](docs/cursor-setup.md)         | Use TracerKit skills in Cursor                    |\n| [Gemini CLI Setup](docs/gemini-cli-setup.md) | Use TracerKit skills in Gemini CLI                |\n| [Copilot Setup](docs/copilot-setup.md)       | Use TracerKit skills in GitHub Copilot            |\n| [OpenCode Setup](docs/opencode-setup.md)     | Use TracerKit skills in OpenCode                  |\n\n## Contributing\n\n1. Fork the repo and create a feature branch\n2. Use TracerKit itself to plan your change (`/tk:prd` + `/tk:plan`)\n3. Implement following the plan phases\n4. `npm run lint:fix && npm run test:run && npm run typecheck`\n5. [Conventional Commits](https://www.conventionalcommits.org/) (enforced by commitlint)\n6. Open a PR against `main`\n\n## Support\n\nFor support, please [open a GitHub issue](https://github.com/helderberto/tracerkit/issues). We welcome bug reports, feature requests, and questions.\n\n## Acknowledgments\n\nThis project was born out of [Claude Code for Real Engineers](https://www.aihero.dev/cohorts/claude-code-for-real-engineers-2026-04), a cohort by [Matt Pocock](https://github.com/mattpocock). The hands-on approach to building real things with Claude Code sparked the idea for TracerKit. If you're serious about AI-assisted engineering, I can't recommend Matt's cohorts and content highly enough.\n\n## License\n\n[MIT License](LICENSE) © [helderberto](https://helderberto.com)\n",
  "bytes": 7404,
  "sha": "3ae30c9b478564c65a55a9e37414c5afe19a1f46176c0839b51ea0afc06b0182",
  "repo_slug": "helderberto/tracerkit",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_helderberto_tracerkit_tk_b7471d5c/readme"
}