Skip to content

Jgocunha/dynamic-neural-field-composer / .claude/skills/docs-check

docs-check

Verified

Verify documentation keeps up with a code change in dynamic-neural-field-composer - Doxygen on public API, the matching wiki page, and stale references elsewhere. Use before opening a PR, or when asked whether docs need updating.

Docs check

Three passes over git diff origin/main...HEAD. Report findings; do not silently rewrite prose that is merely different from how you would put it.

Pass 1 - Doxygen

Scope: new or changed public entities under dynamic-neural-field-composer/include/.

Each needs:

  • @brief - one line, what it does
  • one @param per parameter, names matching the signature exactly
  • @return unless the return type is void

Flag three failure modes:

  • Missing - new public function/class/struct with no block.
  • Stale - a parameter was renamed, added or removed and the block still describes the old signature. This is the most common and the easiest to miss.
  • Wrong - the description contradicts what the code now does.

Private helpers in src/ do not need Doxygen.

Pass 2 - Wiki

dynamic-neural-field-composer/wiki/ has 15 pages. Map the change to its page:

ChangedPage
Element behaviour, new element typeElements.md, Element Reference.md
Element parameters, tuning defaultsElement Reference.md, Parameter Tuning Guide.md
GUI, windows, node editorApplication and UI.md
Simulation loop, timing, recorderSimulation.md
Plots, heatmaps, visualizationVisualization.md
Build, dependencies, setupGetting Started.md, Troubleshooting.md
Public API shape, architectureArchitecture.md, How to Add New Elements.md
New example executableExamples.md, How to Create and Run Your Own Example Executable.md
Test infrastructureTesting.md

Rule of thumb: if a user could notice the change without reading the source, a wiki page owes them an explanation. Pure internal refactors do not.

Pass 3 - Stale references

Grep the repo for references the change invalidated:

grep -rn "<old_symbol>" README.md CONTRIBUTING.md CHANGELOG.md dynamic-neural-field-composer/wiki/ .claude/

Look for renamed or removed symbols, moved file paths, changed build commands or flags, and example snippets that no longer compile. Check README.md and CONTRIBUTING.md specifically when the build process or directory layout moved.

Output

For each pass: either "clean" or a concrete list of file + line + what is wrong. If nothing in the diff touches public API or user-visible behaviour, say so and stop - a refactor with no API change legitimately needs no doc update.

rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 470kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 197kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 197kUpdated Claude CodeCodexVerifiedInstall