Punpun1643
UserA collection of Agent Skills for docs & workflow tasks available for Claude Code and Codex
Categories
Indexed Skills (13)
dev-guide
Create and maintain a repository's developer guide — the document that explains the system's architecture, components, data flow, and design decisions to new contributors. Use this skill WHENEVER the user wants to write, update, regenerate, fact-check, or extend developer/architecture documentation, including phrasings like "update the dev guide", "the architecture doc is out of date", "document this module", "add X to the developer guide", "the DG", "regenerate the architecture docs", or "make a developer guide for this repo". Also use it proactively after significant structural code changes (new / removed / renamed components, reworked data flow) when the user mentions docs. The skill enforces that every description is grounded in the actual code and that diagrams use the correct type for what they illustrate.
excalidraw
Generate architecture diagrams as .excalidraw files from codebase analysis, with optional PNG/SVG export. Use when the user asks to create architecture diagrams, system diagrams, visualize codebase structure, generate excalidraw files, export excalidraw diagrams to PNG or SVG, or convert .excalidraw files to image formats.
git-commit
Write clear, well-structured git commit messages that follow the Conventional Commits specification. Use this whenever you are about to commit staged or unstaged changes, write or rewrite a commit message, amend or squash commits, or are asked to "commit this", "write a commit message", or "clean up the history" — even when the user never says the words "conventional commits". Also use when configuring commit linting (commitlint/husky), generating a CHANGELOG, or reasoning about which semantic-version bump a set of changes implies.
product-designer
Produce and refine product-design briefs that turn rough ideas into buildable MVP specifications with vision, personas, jobs-to-be-done, goals and non-goals, numbered requirements, key screens, a data model, user stories with acceptance criteria, journeys, metrics, risks, and milestones. Use whenever the user wants to write, expand, critique, or restructure a product brief, MVP plan, PRD, feature spec, or set of user stories, including requests such as "write a product spec", "turn this idea into an MVP plan", "draft the requirements", "design this feature", "define the MVP scope", or "make a PRD". Also use when a user describes a product idea and asks how to scope or structure it. Enforce human-centered design principles and ensure every requirement is testable and tied to a real user need.
readme-writer
Write, generate, overhaul, or fix a project's README.md (or any "readme", repo front page, or top-level project documentation). Use this skill whenever the user wants to create or improve a README, document a repo, or figure out how to present a codebase to readers — covering libraries and packages, CLI tools, research/ML repos, web apps, services, and developer tooling. Trigger even when the user only says things like "document this project", "write docs for my repo", "make a readme", or points at a codebase and asks how to present it, even if the word "README" never appears.
dev-guide
Create and maintain a repository's developer guide — the document that explains the system's architecture, components, data flow, and design decisions to new contributors. Use this skill WHENEVER the user wants to write, update, regenerate, fact-check, or extend developer/architecture documentation, including phrasings like "update the dev guide", "the architecture doc is out of date", "document this module", "add X to the developer guide", "the DG", "regenerate the architecture docs", or "make a developer guide for this repo". Also use it proactively after significant structural code changes (new / removed / renamed components, reworked data flow) when the user mentions docs. The skill enforces that every description is grounded in the actual code and that diagrams use the correct type for what they illustrate.
excalidraw
Generate architecture diagrams as .excalidraw files from codebase analysis, with optional PNG/SVG export. Use when the user asks to create architecture diagrams, system diagrams, visualize codebase structure, generate excalidraw files, export excalidraw diagrams to PNG or SVG, or convert .excalidraw files to image formats.
git-commit
Write clear, well-structured git commit messages that follow the Conventional Commits specification. Use this whenever you are about to commit staged or unstaged changes, write or rewrite a commit message, amend or squash commits, or are asked to "commit this", "write a commit message", or "clean up the history" — even when the user never says the words "conventional commits". Also use when configuring commit linting (commitlint/husky), generating a CHANGELOG, or reasoning about which semantic-version bump a set of changes implies.
product-designer
Produce and refine product-design briefs — the document that turns a rough product idea into a buildable MVP spec: vision, personas, jobs-to-be-done, goals/non-goals, numbered functional requirements, key screens, data model, user stories with acceptance criteria, user journeys, success metrics, risks, and milestones, all grounded in human-centered-design principles. Use this skill WHENEVER the user wants to write, expand, critique, or restructure a product brief, MVP plan, PRD, feature spec, or set of user stories — including phrasings like "write a product spec for X", "turn this idea into an MVP plan", "draft the requirements", "write user stories with acceptance criteria", "design this feature", "what should the MVP scope be", "critique this product plan", or "make a PRD". Also use it proactively when a user describes a product idea and asks how to scope or structure it. The skill enforces HCD principles (visible constraints, reversibility, informative feedback, traceability) and that every requirement is
readme-writer
Write, generate, overhaul, or fix a project's README.md (or any "readme", repo front page, or top-level project documentation). Use this skill whenever the user wants to create or improve a README, document a repo, or figure out how to present a codebase to readers — covering libraries and packages, CLI tools, research/ML repos, web apps, services, and developer tooling. Trigger even when the user only says things like "document this project", "write docs for my repo", "make a readme", or points at a codebase and asks how to present it, even if the word "README" never appears.
cognitive-map
Build a cognitive map for learning a topic. Use when the user wants to learn, understand, study, explore, or get oriented in a subject, especially when they want to understand why concepts matter, how ideas connect, what depends on what, what alternative paths exist, and what to learn next. Produce Markdown and an interactive local webpage when file writing is available. Do not merely produce a syllabus or an exhaustive list of subtopics.
unslop
Cut AI tells from any writing. Must always apply.
cognitive-map-open
Open a generated cognitive-map webpage in the local browser. Use when the user asks to open, launch, view, browse, or reopen a cognitive map, including requests such as "open the map", "show the cognitive map", or "launch map.html". Resolve the current project's map automatically or accept an explicit HTML, Markdown, or directory path.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.