Comentaris
Comentaris i anotacions del codi
trace-annotation-tool
maragudk
Generate a custom trace annotation web app for open coding during LLM error analysis. Use when the user wants to review LLM traces, annotate failures with freeform comments, and do first-pass qualitative labeling (open coding). Also use when the user mentions "annotate traces", "trace review tool", "open coding tool", "label traces", "build an annotation interface", "review LLM outputs", or wants to manually inspect pipeline traces before building a failure taxonomy. This skill produces a tailored Python web application using FastHTML, TailwindCSS, and HTMX.
articulation
kluless13
Framework for articulating ideas intelligently in writing and speaking. Based on Dan Koe's methods. TRIGGERS: - When user asks to write a post, thread, or newsletter - When user is preparing for a podcast or presentation - When user wants to explain a complex idea - When user says "help me articulate" or "how do I explain" - When drafting content that needs to be compelling and clear CAPABILITIES: - Structure ideas using Problem-Amplify-Solution (beginner) - Apply Pyramid Principle for logical arguments (intermediate) - Cross-domain synthesis for unique perspectives (advanced) - Build "greatest hits" library of core ideas
clickhouse-query-optimization
obsessiondb
"20+ optimization rules for ClickHouse queries. Load when writing queries, debugging slow queries, fixing memory errors, or optimizing JOINs. Achieves 10-100x faster queries, 90% less memory usage."
moltbook
cklxx
Interact with Moltbook (the AI agent social network) — post, browse, comment, vote, search — via shell curl.
samhvw8
"PDF document processing and manipulation. Tools: Python (PyPDF2, pdfplumber, reportlab), CLI tools. Capabilities: text extraction, table extraction, form filling, merge/split documents, create PDFs, add annotations, watermarks, page manipulation. Actions: extract, create, merge, split, fill, annotate PDFs. Keywords: PDF, text extraction, table extraction, form fill, PDF form, merge PDF, split PDF, create PDF, reportlab, PyPDF2, pdfplumber, annotation, watermark, page rotation, PDF metadata, bookmarks, OCR. Use when: extracting text/tables from PDFs, filling PDF forms, merging/splitting documents, creating PDFs programmatically, adding annotations/watermarks, processing PDFs at scale."
code-patterns
xu-cell
后端代码禁令和编码规范速查。本项目是纯后端项目，前端代码在分离的项目中开发。 触发场景： - 查看项目禁止事项（后端代码） - 命名规范速查 - Git 提交规范 - 代码风格检查 - 避免过度工程 触发词：规范、禁止、命名、Git提交、代码风格、不能用、不允许、包名、架构 注意：后端 CRUD 开发规范请激活 crud-development，API 开发规范请激活 api-development，数据库设计规范请激活 database-ops。
backend-annotations
xu-cell
后端高级注解使用指南。包含 @RateLimiter、@RepeatSubmit、@Sensitive、@EncryptField、@ApiEncrypt、@DataPermission 等注解的用法。 触发场景： - 配置接口限流（@RateLimiter） - 配置防重复提交（@RepeatSubmit） - 配置数据脱敏（@Sensitive） - 配置字段加密（@EncryptField） - 配置接口加密（@ApiEncrypt） - 配置数据权限注解（@DataPermission） 触发词：注解、@RateLimiter、@RepeatSubmit、@Sensitive、@EncryptField、@ApiEncrypt、@DataPermission、@DataColumn、限流、防重复、脱敏、加密、数据权限注解
ty-skills
jiatastic
Python type checking expertise using ty - the extremely fast type checker by Astral. Use when: (1) Adding type annotations to Python code, (2) Fixing type errors reported by ty, (3) Migrating from mypy/pyright to ty, (4) Configuring ty for projects, (5) Understanding advanced type patterns (generics, protocols, intersection types), (6) Setting up ty in editors (VS Code, Cursor, Neovim, PyCharm).
screengrabs
inkeep
"Capture, annotate, and include screenshots in pull requests for UI changes. Use when creating or updating PRs that touch frontend components, pages, or any web-facing surface. Also use when asked to add before/after screenshots, visual diffs, or enrich PR descriptions. Triggers on: PR screenshots, before/after, visual diff, PR description, capture screenshot, PR images, enrich PR."
xiaohongshu-mcp
tclawde
Xiaohongshu MCP Skill - Full automation solution with login fix. Features: (1) Login management, (2) Search, publish, interact, (3) Complete MCP protocol support (13 tools), (4) Comment strategy. Built-in Feishu notification, iflow integration. Triggers: xiaohongshu, rednote, 小红书 automation.
dependabot-alert-issue
shoji9x9
Dependabot alerts または外部 audit findings（例 pnpm audit の正規化 JSON）を確認し、解消 Issue を gh で作成するスキル。対象を「すぐ着手できるか」で分類し、着手可能なものは severity 毎、ブロック中のものは脆弱パッケージ＋解決バージョン毎にまとめる。既存 Issue/PR はスキップし、特定 alert の ignore/dismiss も設定できる。pnpm.overrides 等の品質が保証されない回避策は採らない。「Dependabot alerts から Issue」「pnpm audit の結果から Issue」「脆弱性対応の Issue」「dependabot-alert-issue」で必ず発動する。
libdestruct Skills
libdebug
libdestruct integrates with libdebug for live process memory inspection. The debugger's memory view can be passed directly to inflater.
documentation-templates
benshapyro
Generates README files, API documentation, and inline code comments following best practices. Use when creating project documentation, writing READMEs, documenting APIs, or explaining complex code.
bitbucket-server
skempken
This skill enables interaction with BitBucket Server REST API for Pull Request management. Use when the user wants to create, review, comment on, merge, list pull requests, read comments, or manage tasks on BitBucket Server.
docs
thechandanbhagat
Generate documentation, API docs, README files, and code comments. Use for creating or improving project documentation.
anndata
hxk622
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Designing Before Coding
obra
Design in pseudocode first, iterate approaches, then translate to code
ocm-sdk
andreibesleaga
How to use the ocm SDK. For access to more information, try out the ocm MCP server.
fan-skill
AI4S-YB
AI-powered plant bioinformatics and breeding analysis engine. From biological question to publication-ready results — consultation, analysis, interpretation, and visualization. Knowledge-base driven with B+C dual-mode decision architecture.
IOBRskill
IOBR
End-to-end bulk RNA-seq / microarray tumor microenvironment (TME) analysis using the IOBR R package. Covers data preprocessing, gene annotation, TME deconvolution (CIBERSORT/MCPcounter/EPIC/xCell/ESTIMATE/TIMER/quanTIseq/IPS), signature scoring (PCA/ssGSEA/Z-score), ligand-receptor analysis, pathway enrichment, survival modeling, and Nature-style visualization. Use this skill when the user mentions: tumor microenvironment analysis, TME deconvolution, immune infiltration analysis, 肿瘤微环境分析, 肿瘤微环境解析, 免疫浸润分析, ligand-receptor analysis, 受体配体分析, IOBR, immune cell deconvolution, CIBERSORT, MCPcounter, ESTIMATE, or any bulk RNA-seq immuno-oncology workflow. Also trigger on /IOBRskill.
code-documentation
ilude
Guidelines for self-explanatory code and meaningful documentation. Activate when working with comments, docstrings, documentation, code clarity, API documentation, JSDoc, or discussing code commenting strategies. Guides on why over what, anti-patterns, decision frameworks, and language-specific examples.
optimizing-queries
galihcitta
Analyzes and optimizes SQL/NoSQL queries for performance. Use when reviewing query performance, optimizing slow queries, analyzing EXPLAIN output, suggesting indexes, identifying N+1 problems, recommending query rewrites, or improving database access patterns. Supports PostgreSQL, MySQL, SQLite, MongoDB, Redis, DynamoDB, and Elasticsearch.
refactor
peth-eth
Maintenance-day runner — deletes dead weight (legacy, deprecated, AI slop, stubs, bad comments), then runs jscpd, knip/vulture, madge (circular deps), ESLint/Biome/ruff, fixes weak types properly (research + replace), removes unjustified try/catch, consolidates shared types, and scans for structural issues. Language-agnostic. Use when paying down tech debt or doing periodic cleanup.
Schema
andrueandersoncs
This skill should be used when the user asks about "Effect Schema", "Schema.Struct", "Schema.decodeUnknown", "data validation", "parsing", "Schema.transform", "Schema filters", "Schema annotations", "JSON Schema", "Schema.Class", "Schema branded types", "encoding", "decoding", "Schema.parseJson", or needs to understand how Effect handles data validation and transformation.