Skip to content
Back to search

eliptikwu

MarketplaceWorks with Claude CodeGitHub

Claude Code skills by EliptikWu.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/eliptikwu--engineering-docs/badge.svg)](/listings/eliptikwu--engineering-docs)

HTML

<a href="/listings/eliptikwu--engineering-docs"><img src="/api/listings/eliptikwu--engineering-docs/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**Claude Code, as a plugin:**

/plugin marketplace add EliptikWu/engineering-docs
/plugin install engineering-docs@eliptikwu

Or copy `skills/engineering-docs/` to `~/.claude/skills/engineering-docs/` (every project) or to `<repo>/.claude/skills/engineering-docs/` (one project).

**Other tools:** copy `skills/engineering-docs/` to `<repo>/.agents/skills/engineering-docs/` for one project, or to `~/.agents/skills/engineering-docs/` for all of them. Then ask for it in plain words ("set up the engineering docs", "audit the docs"), or invoke it by name where your tool supports that (`/engineering-docs`, `$engineering-docs` in Codex).

The project's instructions file can be whatever your tool reads (`CLAUDE.md`, `AGENTS.md`, `GEMINI.md`…); the template is named `CLAUDE.md`, rename it as needed.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 16 lines
  1. {
  2. "name": "eliptikwu",
  3. "description": "Claude Code skills by EliptikWu.",
  4. "owner": {
  5. "name": "EliptikWu"
  6. },
  7. "plugins": [
  8. {
  9. "name": "engineering-docs",
  10. "source": "./",
  11. "description": "A small, fixed set of numbered engineering docs (01-10) shaped by your business model, with a backlog /next-task can consume and a coherence checker.",
  12. "version": "1.0.0",
  13. "license": "Apache-2.0"
  14. }
  15. ]
  16. }
README.md · README · 165 lines
  1. # engineering-docs
  2. [Leer en español](README.es.md)
  3. An agent skill that sets up and maintains a project's **engineering documentation**: a
  4. small, fixed set of numbered documents that rule over the code. The agent reads them
  5. before touching anything, and every behavior change updates them in the same pull request.
  6. It uses the open [Agent Skills](https://agentskills.io) format, so it runs in Claude Code,
  7. Codex, Gemini CLI, GitHub Copilot, Cursor and Devin Desktop.
  8. The method was battle-tested on three production projects (an internal CRM, a paid SaaS,
  9. and a standards-regulated app) before being written down as a skill. What the skill brings
  10. is **the method, not the content**: the content comes from a short interview and from your
  11. code. It never copies another project's docs.
  12. ## What you get
  13. ```
  14. CLAUDE.md short; read every session: rules, commands, "if you touch X, read Y"
  15. docs/
  16. README.md status line, "What's left" (the backlog), document index, open decisions
  17. 01-scope-and-definitions.md problem, roles, scope by phase, glossary
  18. 02-requirements.md RF-AAA-NN / RNF-AAA-NN, each with a WHEN … THE SYSTEM … scenario
  19. 03-architecture.md components, stack, permissions, decision log (ADR-NN)
  20. 04-database.md only if there's a database
  21. 05-ui-ux.md only if there's an interface
  22. 06-quality.md prioritized quality attributes, definition of done
  23. 07-optimizations.md only if there's a per-use cost (AI, paid APIs)
  24. 08-methodology.md iteration cycle, branches, phases, deployment
  25. 09-testing-qa.md only with personal data, multi-tenancy, payments or e2e flows
  26. 10-bug-fixing.md severity, the sweep, findings register (EV-NN), risks and debt
  27. history/ closed items, so live documents stay short
  28. ```
  29. The numbering is fixed: "doc 05" means the same thing in every project, even when it
  30. doesn't exist. The documents are written in your project's language (the templates are in
  31. English and their headings get translated); identifiers stay in English.
  32. ## Three modes
  33. | Mode | When | What it does |
  34. |---|---|---|
  35. | **New** | Empty or nearly empty repository | Interview → profile → documents from the templates |
  36. | **Adopt** | There's code but no docs (or different ones) | Reads the code first and only asks what the code can't say. Requirements describe what exists (`Status`, `Where`), and Phase 0 is an assessment that opens findings. The code rules are extracted from the code: only what repeats in three or more places, each citing an example file |
  37. | **Audit** | The project already uses the method | Runs the coherence checker (with `--paths` and `--traceability`) plus a "what rots" checklist, and proposes fixes instead of rewriting |
  38. ## It adapts to the business model
  39. Before writing anything it asks up to two rounds of questions: who pays, whether it
  40. charges inside the product, whether a standard or law governs it, personal data,
  41. multi-tenancy, surfaces (web, mobile, AI with per-use cost, public user docs), team and deployment,
  42. maturity. Each answer turns a **module** on or off
  43. ([`references/profiles.md`](skills/engineering-docs/references/profiles.md)):
  44. - **Payments:** "money correctness" becomes quality attribute #2, webhook rules go into
  45. CLAUDE.md, there's a Money domain in the database doc, and "charged without granting"
  46. is a critical bug.
  47. - **Regulated (ISO, data protection…):** "fidelity to the standard" goes to the top,
  48. requirements cite their clause in a `Source` column, and done means "checked against the
  49. text of the standard".
  50. - **Personal data / multi-tenant:** privacy requirements, a sensitive-data section, and a
  51. mandatory test with two users or two organizations.
  52. - **User documentation and runbooks:** each page is one Diátaxis type (tutorial, how-to,
  53. reference or explanation), and a user-visible change updates its page in the same PR.
  54. - **Interface, AI cost, own database, deployment, team size:** turn on 05, 07, 04,
  55. runbooks, or a role table, as needed.
  56. You see the resulting profile (5–10 lines) before anything is generated. What the
  57. interview can't answer becomes `TBD (who)` plus an open decision `D<n>`; nothing is
  58. invented.
  59. ## The coherence checker
  60. `scripts/coherence.py` is a stdlib-only Python script that checks, without changing
  61. anything:
  62. - duplicate IDs;
  63. - IDs cited but never defined;
  64. - a broken `Superseded by ADR-NN`;
  65. - links to documents that don't exist;
  66. - a README status date older than the latest date the README mentions;
  67. - unfilled template placeholders;
  68. - documents that have grown too long;
  69. - optionally, `Done` requirements that no code or test cites (`--traceability`);
  70. - optionally, code paths the docs name in backticks that don't exist (`--paths`);
  71. - optionally, IDs cited in a PR or commit message that don't exist (`--citations`).
  72. It understands English and Spanish keywords.
  73. ```bash
  74. python skills/engineering-docs/scripts/coherence.py /path/to/project [--traceability] [--paths]
  75. git log origin/main..HEAD --format=%B | python skills/engineering-docs/scripts/coherence.py . --citations -
  76. python -m unittest discover -s tests -v # the checker's own tests
  77. ```
  78. ## Works with next-task
  79. The backlog lives in one place: "What's left" in `docs/README.md`, with a table of
  80. batches, their dependencies and their appetite (a cap in PRs or sessions, from Shape Up:
  81. when it's spent, the batch is re-cut instead of dragging on). `CLAUDE.md` gets the line
  82. `Backlog: docs/README.md ("What's left")`, which is how
  83. [next-task](https://github.com/EliptikWu/next-task) finds the next item. Use this skill to
  84. lay the docs down and keep them honest, and next-task to work through the backlog one task
  85. per session.
  86. ## What it borrows, and what it leaves out
  87. It borrows from:
  88. - **Spec Kit:** a short set of non-negotiable project rules read before every change
  89. (here, `CLAUDE.md`). And a requirement exists before its code: an ID in 02 before
  90. implementation.
  91. - **Kiro:** EARS-style acceptance criteria. Every requirement has a verifiable
  92. `WHEN <situation> THE SYSTEM <result>` scenario, and the test that covers it cites the
  93. ID. Always-loaded steering becomes the "if you're going to touch X, read Y" table.
  94. - **BMAD:** discovery before planning (the interview), and scale-adaptive tracks. A small
  95. fix only touches its finding, while a new feature gets an ID, an ADR and scenarios.
  96. - **OpenSpec:** changes expressed as deltas. Every PR carries a "Documentation" section
  97. listing the requirements added, changed or removed and the ADRs added or superseded.
  98. - **Taskmaster:** tasks with dependencies. The next task is the first batch that isn't
  99. done and whose dependencies are.
  100. - **arc42:** the architecture skeleton: context, building blocks, deployment, decisions,
  101. prioritized quality attributes, risks and technical debt, glossary.
  102. It leaves out (see "What we left out" in
  103. [`references/rules.md`](skills/engineering-docs/references/rules.md)):
  104. - **A spec folder per feature.** It's written for one branch and then nobody maintains it.
  105. Requirements live in one living document.
  106. - **A separate `tasks.json` or task plan.** That's a second source of truth that drifts
  107. from the backlog.
  108. - **Agent personas (PM, architect…).** They're ceremony; skills and subagents are enough.
  109. - **The spec as the only source, with generated code.** Generation isn't deterministic.
  110. - **Giant instruction files.** Context rots, so `CLAUDE.md` stays short and the rest is
  111. read on demand.
  112. There's no benchmark for this skill: we haven't measured it, so we don't claim numbers.
  113. ## Install
  114. **Claude Code, as a plugin:**
  115. ```
  116. /plugin marketplace add EliptikWu/engineering-docs
  117. /plugin install engineering-docs@eliptikwu
  118. ```
  119. Or copy `skills/engineering-docs/` to `~/.claude/skills/engineering-docs/` (every project)
  120. or to `<repo>/.claude/skills/engineering-docs/` (one project).
  121. **Other tools:** copy `skills/engineering-docs/` to `<repo>/.agents/skills/engineering-docs/`
  122. for one project, or to `~/.agents/skills/engineering-docs/` for all of them. Then ask for
  123. it in plain words ("set up the engineering docs", "audit the docs"), or invoke it by name
  124. where your tool supports that (`/engineering-docs`, `$engineering-docs` in Codex).
  125. The project's instructions file can be whatever your tool reads (`CLAUDE.md`, `AGENTS.md`,
  126. `GEMINI.md`…); the template is named `CLAUDE.md`, rename it as needed.
  127. ## License
  128. [Apache 2.0](LICENSE). You can use, change and share it. Copies and derived works must
  129. keep the copyright and the [NOTICE](NOTICE) file, and must say what was changed. The
  130. license doesn't grant use of the author's name to promote a derived work.
  131. Made by [EliptikWu](https://github.com/EliptikWu).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.