注释
代码注释与标注
bid-software-design
youyouhe
基于需求规格编写软件概要设计和详细设计文档。从需求元数据和各系统需求规格中读取业务对象、 接口、用例等信息，生成数据库设计、API设计、模块设计等工程级设计文档。 采用三阶段架构：Phase 0 生成设计元数据，Phase 1 按系统生成概要设计，Phase 2 按子模块生成详细设计。 核心特性：大文档自动拆分，按系统规模分级处理（小/中/大），避免单次输出过大。 当用户要求编写软件设计、概要设计、详细设计、数据库设计、API设计时触发。 也支持修复模式：当用户要求修复/补充设计文档时触发。 前置条件：需已完成 bid-requirements 生成需求规格文件。
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.
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.
gene-database
hxk622
Query NCBI Gene via E-utilities/Datasets API. Search by symbol/ID, retrieve gene info (RefSeqs, GO, locations, phenotypes), batch lookups, for gene annotation and functional analysis.
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.
development-philosophy
ilude
Personal development philosophy emphasizing experiment-driven, fail-fast approach. Activate when planning implementations, reviewing code architecture, making design decisions, or when user asks to apply development principles. Guides against over-engineering and towards solving real problems with simple solutions. (project, gitignored)
-- RDF 1.2 specification references ------------------------------------------
kurtcagle
This code lets you access a jena-fuseki database from within a Claude chat instance, as well as host it.
implement-plan
ferueda
Implement a spec document phase-by-phase, writing robust idiomatic code that follows codebase patterns.
wp-malware-remediation
maitret
"Analizar, detectar y limpiar malware PHP en sitios WordPress alojados en servidores Linux (CWP/cPanel). Cubre el ciclo completo: triage, backup, escaneo heurístico, clasificación de hallazgos, limpieza quirúrgica de código inyectado, eliminación de archivos 100% maliciosos, restauración de WordPress core, validación post-limpieza y hardening. WHEN: malware en WordPress, limpiar sitio hackeado, código ofuscado PHP, webshell, backdoor, hacklink, archivos sospechosos en uploads, eval base64_decode, archivo PHP inyectado, limpiar servidor comprometido, cuarentena malware, restaurar WordPress core."
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.
agentic-cadence
Chef-Code
Manage durable agent handoffs, Cadence state, pickup signatures, and clean-square shutdowns for long-running or self-evolving workflows.
enforcing-type-safety
sumik5
REQUIRED for all TypeScript/Python code. Automatically load when writing type annotations or handling external data. Any/any types strictly prohibited. Enforces strict mode configuration and type guard implementation.
coderabbit-loop
Mzeey-Empire
Iteratively improves a GitHub PR or GitLab MR until CodeRabbit leaves zero unresolved actionable comments. Triggers a CodeRabbit review, fixes all actionable comments, pushes, re-triggers review, and repeats. Use when the user wants to fully resolve a PR/MR against CodeRabbit's review feedback before requesting human review.
github-optimization
inquisitive-production852
"Optimize any GitHub repo for maximum stars, traffic, followers, and discoverability. Rewrites README as a high-converting landing page with SEO-optimized headers, shields.io badges, star/follow CTAs, keyword-rich description and topics, humanized copywriting, and author attribution. Includes a star growth knowledge base with launch strategies, channel playbooks, and ROI rankings. Use when user says 'optimize GitHub', 'improve my repo', 'GitHub SEO', 'optimize README', 'get more stars', 'improve my GitHub', 'make repo better', 'polish GitHub', 'github-optimization', '/github-optimization', 'how to get stars', 'launch strategy', 'promote my repo'."
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.
TBS Policy Hawk: Policy Evolution Analysis Skill
PatLittle
```
peat-mesh
defenseunicorns
Per-repo skill for the Peat mesh networking layer — pluggable transport, peer discovery, topology, routing, optional Automerge/Iroh CRDT sync, optional HTTP/WS broker.
coderabbit-loop
Mzeey-Emipre
Iteratively improves a GitHub PR or GitLab MR until CodeRabbit leaves zero unresolved actionable comments. Triggers a CodeRabbit review, fixes all actionable comments, pushes, re-triggers review, and repeats. Use when the user wants to fully resolve a PR/MR against CodeRabbit's review feedback before requesting human review.
ct-c-style
experiencenow-ai
C coding style for Tockchain/Valis firmware development. Use when writing, reviewing, or modifying C code for this project. Enforces compact Allman bracing, stdint types, zero-copy wire structs, dependency-ordered functions, unique negative error codes, and high-performance patterns. Triggers on any C code generation, editing, or review request.
code-explain
dmonteroh
"Explain complex code clearly for humans and agents. Produce a structured walkthrough (high-level intent -> data/control flow -> key invariants -> edge cases) with optional Mermaid diagrams and actionable next steps. Use for onboarding, debugging understanding, and “how it works” docs."
pr-review-loop
xpepper
Use when addressing open PR review comments from any reviewer (human or bot) within the current agent session. For a fresh-context-per-comment approach, use ralph-wiggum-loop instead.
explain-like-senior
manastalukdar
Senior-level code explanations with deep technical insights and context