Docs Gen
Generate and maintain documentation
afp-product-builder
by autonity
Build valid AFP products by composing on-chain PredictionProductV1, extended metadata DAG, and API-backed resolution rules. Use when creating or validating AFP product JSON for Forecastathon, selecting public data sources, or preparing IPFS pinning and registration.
research-web
by doodledood
"Comprehensive multi-wave web research with strategic source selection. Gathers information from official docs, community resources, and advanced sources. Use for deep technical research, API documentation, best practices. Triggers: research web, deep research, comprehensive research, find documentation."
evaluating-skills-with-models
by taisukeoe
Evaluate skills by executing them across sonnet, opus, and haiku models using sub-agents. Use when testing if a skill works correctly, comparing model performance, or finding the cheapest compatible model. Returns numeric scores (0-100) to differentiate model capabilities.
canvas-feedback-template
by vishalsachdev
Generate learning science-backed feedback templates for Canvas assignments. Use when educators need feedback templates for grading, want to create rubric comments, need encouraging feedback language aligned with Pillar 3 principles (targeted, encouraging, immediate), or want to set up SpeedGrader comment libraries. Works with canvas-mcp for bulk grading.
apisix-adc
by SkyeYoung
Use ADC (APISIX Declarative CLI) to manage all Apache APISIX resources. Trigger when user mentions "APISIX", "manage APISIX", "configure APISIX", "APISIX route", "APISIX service", "APISIX upstream", "APISIX consumer", "APISIX plugin", "APISIX SSL", "APISIX gateway", "global rules", "install adc", "adc ping", "adc sync", "adc diff", "adc dump", "adc lint", "create route", "add consumer", "configure upstream", "rate limiting", "API authentication", "API gateway", or any APISIX/ADC configuration task.
feature-sliced-design
by aiko-atami
Apply Feature-Sliced Design (FSD) v2.1 architectural methodology to frontend projects. Use when organizing code structure, decomposing features, creating new components or features, refactoring existing codebases, or when users mention "FSD", "Feature-Sliced", layers, slices, or frontend architecture patterns.
llms-txt
by marcelo-earth
Generate an llms.txt file for any project or website following the llmstxt.org specification. Use when asked to create llms.txt, generate LLM-friendly documentation, make a project AI-readable, or prepare documentation for language models.
google-docs-daemon
by fast-gateway-protocol
Fast Google Docs operations via FGP daemon - 30-60x faster than MCP. Use when user needs to read documents, create docs, insert text, format content, or export to PDF. Triggers on "read document", "create doc", "google docs", "insert text", "document content", "export doc", "format document".
polymarket-market-discovery
by lubluniky
Procedural workflow for finding markets, extracting token IDs, and reading orderbooks on Polymarket using Gamma and CLOB APIs. Read-only, no auth required.
export-public-types
by marius-townhouse
Use when publishing libraries. Use when types appear in public APIs. Use when users need to reference types. Use when building reusable components. Use when designing library interfaces.
polymarket-clob-auth-trade
by lubluniky
Advanced procedural workflow for L1/L2 authentication, EIP-712 signing, and placing trades on Polymarket CLOB API.
claude-agent-pr-review-toolkit-comment-analyzer
by monkey1sai
Converted from Claude plugin agent "comment-analyzer" (pr-review-toolkit).
anthropic-daemon
by fast-gateway-protocol
Fast Anthropic Claude API operations via FGP daemon - 15-30x faster than spawning API clients per request. Use when user needs Claude chat completions, streaming responses, token counting, or batch requests. Triggers on "claude chat", "anthropic api", "claude completion", "claude stream".
three-layer-agent-stack
by Coowoolf
Use when building AI-powered products or agents, when raw model intelligence isn't enough to solve user problems, or when designing the architecture for agentic workflows
review-docs
by doodledood
"Audit documentation accuracy against code changes. Identifies stale docs, incorrect examples, and missing documentation. Read-only analysis. Use before PR or after implementation. Triggers: review docs, check documentation, docs up to date."
python-fastapi-ddd-testing-skill
by iktakahiro
Guides unit testing for Python DDD + Onion Architecture apps (Domain Entities/Value Objects and UseCases) using pytest and repository mocks, based on the dddpy reference. Use when adding tests, choosing what to mock, or structuring test folders for a DDD FastAPI project.
architectural-decision-records
by Agentient
Architecture Decision Records (ADRs) format, templates, and best practices for documenting technical decisions. PROACTIVELY activate for: (1) documenting significant technical decisions, (2) recording design trade-offs, (3) creating technology selection rationales. Triggers: "ADR", "decision record", "architecture"
GitHub Push
by alfredang
Secure git push with automatic secret detection, README generation, and repository setup. Scans for secrets, auto-generates README, configures repo description/topics/discussions, and pushes to GitHub.
api
by mrsknetwork
Designs and implements HTTP APIs in Python using FastAPI (REST) or Strawberry (GraphQL). Enforces contract-first design, standard response envelopes, authentication dependency injection, and rate limiting. Trigger when building API endpoints, designing schemas, or handling client-server communication. Always choose REST vs GraphQL based on application complexity.
callback-this-type
by marius-townhouse
Use when callbacks use this. Use when API provides this context. Use when typing event handlers. Use when library sets this in callbacks. Use when documenting callback context.
doc-writer
by ks6088ts-labs
ドキュメント執筆をサポートするスキル。ユーザーがPRDに基づいてドキュメントを作成、編集、または更新したい場合に使用します。このスキルは、docs/prd.md に記載されたプロダクト要求仕様書を参照しながら、技術ドキュメント、設計ドキュメント、ユーザーガイド、APIドキュメントなどの執筆を支援します。「ドキュメントを書く」「仕様書を作成」「ガイドを作る」などのドキュメント作成タスクに言及した場合にトリガーします。
architectural-decision-records
by Agentient
[STUB - Not implemented] Lightweight architectural decision tracking in Markdown (ADR) format. PROACTIVELY activate for: [TODO: Define on implementation]. Triggers: [TODO: Define on implementation]
resend-box
by tomaspozo
Resend Box is a local email sandbox that mocks the Resend API and captures emails for inspection. Use this skill when working with the Resend SDK or SMTP to send emails during development. It captures all emails sent via the Resend SDK (when RESEND_BASE_URL points to the sandbox) or via SMTP (port 1025). Use to verify emails are sent correctly, inspect email content, or test email templates without sending real emails.
commerce-pm
by violetio
Commerce product management