注释
代码注释与标注
explaining-code
oNo500
Explains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks "how does this work?"
ask-explaining-code
NavanithanS
Explain code via analogies, ASCII diagrams, step-by-step walkthroughs.
ocean-paper-writer
441837297
helps ocean science researchers turn proposals, figures, code, data descriptions, target-journal plans, Zotero-supported literature, and advisor feedback into staged manuscript materials through prepare, methods, structure, writing, review, and polish workflows.
agent-kanban
abpai
Operate the agent-kanban board via its stdio MCP server (preferred) or the kanban CLI — supports local (SQLite), Linear, and Jira providers.
explain
laststance
Deep, systematic explanation of code, concepts, and system behavior. Always operates at advanced level with introspection markers and validation. Analyzes target thoroughly before explaining, verifies accuracy after. Use when: - User asks "what does this do", "how does this work", "explain this" - User wants to understand code, architecture, or a concept in depth - User points to a file, function, or system and asks for explanation - User says "explain", "walk me through", "teach me", "break down" Keywords: explain, understand, how, what, why, walk through, teach, break down, clarify
agent-notion
shhac
Notion CLI for humans and LLMs. Use when: - Searching Notion pages or databases by title - Querying database rows with filters and sorts - Reading page properties and content (as markdown or structured blocks) - Creating, updating, or archiving pages - Reading or appending block content (markdown or JSON blocks) - Listing or adding comments on pages (page-level or inline on specific text) - Exporting pages or entire workspaces as markdown/HTML - Finding backlinks (pages that link to a given page) - Viewing version history snapshots of a page - Checking recent workspace or page activity - Chatting with Notion AI (send messages, list threads, stream responses) - Listing available Notion AI models - Managing Notion OAuth, integration token, or desktop session auth Triggers: "notion page", "notion database", "notion search", "query notion", "notion block", "notion comment", "notion auth", "notion content", "search notion", "create notion page", "notion workspace", "notion export", "notion backlinks", "notion history", "notion activity", "inline comment", "version history", "page activity", "notion ai", "ai chat", "notion chat", "ai model"
skill-name
feed-mob
A clear, complete description of what this skill does and when Claude should use it
no-type-in-docs
marius-townhouse
Use when writing comments about types. Use when documenting function parameters. Use when naming variables.
ai-humanizer
ofershap
Prevent AI-detectable patterns in all generated content - prose, code comments, commit messages,
avoid-inferable-annotations
marius-townhouse
Use when writing type annotations on variables. Use when TypeScript can infer the type. Use when code feels cluttered with types.
evolving-types
marius-townhouse
Use when types change as code executes. Use when arrays are built incrementally. Use when working with any[] that narrows.
deepwiki
lambda610
"AI-powered local codebase documentation generator. Use for: (1) Deep code analysis with business logic extraction, (2) Comprehensive API documentation with signatures, (3) Architecture diagrams and data flow mapping, (4) Code patterns identification and design decisions. Not for: Simple file listings or code comments only."
pdd
dtinth
'Skills for Puzzle Driven Development (PDD). Refer to this skill when a project uses PDD or the operator mentions PDD or puzzle-driven development. Use this skill when: (1) Breaking a large feature into incremental deliverables, (2) Writing @todo stub comments to mark unimplemented code, (3) Picking up an existing @todo puzzle to implement, (4) Deciding whether to wrap up a task with a stub or keep working.'
unity-review-code-pr
cuozg
GitHub PR C# logic review — posts inline comments via gh api. Use this skill whenever the user wants to review a PR, check a pull request, post review comments to GitHub, or run automated review before merge — even if they don't say "PR review" explicitly. Triggers — 'review PR', 'review pull request', 'PR review', 'check this PR', 'give feedback on this PR', 'review before merge'.
docs
lukeslp
"Documentation generation and technical writing skill. Use when: creating README files, writing API documentation, generating code documentation (Python docstrings, JSDoc), building user guides, producing architecture overviews, or improving existing documentation quality."
ai-review
zawlinnnaing
Review a GitLab Merge Request using the ai-review CLI. Fetches the MR diff, analyses it as a senior software engineer, produces structured inline comments by severity, and optionally posts them back to GitLab. Use when the user wants to review, analyse, or post feedback on a GitLab MR.
technical-writing
tenzir
Write clear technical documentation following Google's style guide. Use when writing docs, README files, API documentation, code comments, user guides, or asking about documentation style.
linkedin-thought-leadership
ktg0066
Comprehensive system for building LinkedIn thought leadership through algorithmic understanding, strategic consistency, and authentic engagement. Updated November 2025 with critical 360Brew algorithm changes - LinkedIn now validates your profile BEFORE distributing content. Combines tactical content creation with systematic growth frameworks. Includes profile optimization for the new AI-first paradigm, free analytics tools, and methods for moving beyond baseline competence to exceptional performance by discovering YOUR unique patterns.
pr-review-response
ttokit
"Handles PR review comments through analyze-confirm-execute workflow. Analyzes comment validity, confirms response approach with user, executes code changes, and replies to reviewers. Use when responding to PR review comments, addressing feedback, handling code review, replying to reviewers, or managing review threads."
learning-education
spitoglou
Create learning materials, explain concepts, generate quizzes and study aids. Use when asked to explain topics, create tutorials, generate practice questions, make flashcards, design curricula, or help study. Triggers include "explain this", "help me learn", "create a quiz", "tutorial for", "study guide", "how does X work", "teach me", "practice questions".
turn-this-feature-into-a-blog-post
GhostScientist
Generates a technical blog post from code implementation. Use when asked to write a blog post about a feature, explain an implementation for a blog, document code as a blog article, or create technical content from source code. Triggers on phrases like "write a blog post about", "turn this into a blog", "create a technical article", or "explain this for a blog".
liquidity-and-price-dynamics-explainer
SanctifiedOps
Explain Solana AMM liquidity, slippage, volatility, and LP mechanics for tokens. Use to brief teams or design initial liquidity.
commit
trancong12102
Generates git commit messages following Conventional Commits 1.0.0 specification with semantic types (feat, fix, etc.), optional scope, and breaking change annotations. Use when committing code changes or creating commit messages. Triggers on phrases like 'commit', 'commit and push', 'make a commit', 'git commit', or when commit is part of a compound action (e.g., 'bump version and commit').
brainstorming
trancong12102
"Collaboratively explore ideas and design solutions through guided dialogue before implementation. Use this skill when creating features, building components, adding functionality, designing systems, or when the user says \"brainstorm\", \"design this\", \"help me think through\", or \"let's plan\"."