认证鉴权
认证与授权
coaching-pms
liqiongyu
"Coach product managers and produce a PM Coaching Pack (context-specific definition of “good PM”, evidence-based assessment, growth bets + development plan, coaching cadence + session toolkit, follow-up tracker). Use for coaching PMs, developing PMs, leveling expectations, and creating growth plans. Category: Leadership."
add-feature
wasp-lang
Add Wasp's built-in features to your app — auth, email, jobs, and more. These are full-stack, batteries-included features that Wasp handles for you. Use when the user wants to add meta tags, authentication (email, social auth providers), email sending, database setup, styling (tailwind, shadcn), or other Wasp-powered functionality.
deploying-app
wasp-lang
deploy the Wasp app to Railway or Fly.io using Wasp CLI.
mcp-oauth-setup
obie
"Implement MCP server authentication with OAuth Dynamic Client Registration (RFC 7591), Authorization Server Metadata Discovery (RFC 8414), and generalized per-agent credential support. This skill should be used when building admin UIs that let users connect to third-party MCP servers, whether they use OAuth (Linear, Sentry, Granola), bearer tokens (Render, custom APIs), or API keys. Covers the full flow: metadata discovery, client registration, PKCE authorization, token exchange, token refresh, tool sync, and credential storage patterns (shared vs per-agent for any auth type). Includes hard-won lessons from production implementation."
kimaki-expert
ajoslin
Provide expert support for Kimaki setup, Discord bot wiring, OpenCode session orchestration, slash-command troubleshooting, and automation workflows. Use when users mention Kimaki, kimaki.xyz, Discord-controlled coding agents, or channel-to-project mapping.
session-export
ajoslin
Update GitHub PR or GitLab MR descriptions with AI session export summaries. Use when user asks to add session summary to PR/MR, document AI assistance in PR/MR, or export conversation summary to PR/MR description.
kimaki-tools
ajoslin
Run common Kimaki project/session operations from OpenCode, especially linking an existing OpenCode session into Discord and Kimaki session listings. Use when users ask to manage Kimaki projects, sessions, or thread mappings from CLI.
bitrix24-agent
vrtalex
Design, implement, debug, and harden integrations between AI agents and Bitrix24 REST API (webhooks, OAuth 2.0, scopes, events, batch, limits, and REST 3.0). Use when asked to connect AI assistants/agents to Bitrix24, automate CRM/tasks/chats, process Bitrix24 events, choose an auth model, or resolve Bitrix24 API errors and performance issues.
napkin
blader
Maintain a per-repo napkin as a continuously curated runbook (not a session log). Activates EVERY session. Read and curate it before work, keep only recurring high-value guidance, organize by priority-sorted categories, and cap each category at top 10 items. The napkin lives at .claude/napkin.md.
bug-investigation
nokonoko1203
Systematically investigate user-reported bugs and issues, generating detailed reports with root cause analysis, recommended fixes, symptom details, flow diagrams, error message mappings, code analysis, and prioritized fix proposals.
skill-permissions
guo-yu
Skill permission analysis, one-time authorization, analyze skill permissions, batch authorization
tasks
snarktank
"Convert a PRD markdown file to prd.json for execution. Triggers on: convert prd, create tasks, prd to json, generate tasks from prd."
rp-why
block
Gas Town × DOK Framework - A two-dimensional model for analyzing AI collaboration maturity and cognitive complexity to reveal growth opportunities.
running-interactive-commands-with-tmux
Ven0m0
Controls interactive CLI tools (vim, git rebase -i, REPLs) through tmux detached sessions and send-keys. Use when running tools requiring terminal interaction, programmatic editor control, or orchestrating Claude Code sessions. Triggers include "interactive command", "vim", "REPL", "tmux", or "git rebase -i".
Temporal Reasoning
project-minigraf
ROADMAP.md Project roadmap
dify-knowledge-base-search
tiangong-ai
Dify dataset retrieve API for knowledge base chunk search/testing. Use when integrating or debugging Dify knowledge base retrieval requests, retrieval_model options, or response shaping.
daobrew-wellness
DaoBrewAI
"DaoBrew Wellness is a biometric stress detection and micro-recovery skill powered by Traditional Chinese Medicine theory. It reads health data (Apple Health, Health Connect, or DaoBrew Cuff) and identifies five stress patterns: Wood/Tension, Fire/Overdrive, Earth/Stagnation, Metal/Constriction, Water/Depletion. Use this skill whenever: the user has been coding for 30+ minutes without a break, the user mentions feeling stressed/tired/burned out/unfocused, the user asks about their health or energy state, you notice a long unbroken work session, the user asks for a break or recovery suggestion, OR at regular intervals during extended work sessions (every 30 minutes recommended). This skill should be checked proactively — don't wait for the user to ask. Developers who install this skill want their agent to watch out for them."
wallet-encrypt-decrypt
b-open-io
This skill should be used when the user asks to "encrypt message with BSV key", "decrypt with private key", "ECDH encryption", "AES-256-GCM BSV", "EncryptedMessage", "BRC-2 encryption", or needs to encrypt/decrypt data using BSV keys and @bsv/sdk.
discovery-engine
leap-laboratories
Automatically discover novel, statistically validated patterns in tabular data. Find insights you'd otherwise miss, far faster and cheaper than doing it yourself (or prompting an agent to do it). Disco systematically searches for feature interactions, subgroup effects, and conditional relationships you wouldn't think to look for, validates each on hold-out data with FDR-corrected p-values, and checks every finding against academic literature for novelty. Returns structured patterns with conditions, effect sizes, citations, and novelty scores.
render-output
Ven0m0
Renders structured data to terminal with optimal formatting. Use when presenting agent results, displaying data to users, formatting command output, or showing validation reports. Transforms raw data into clear, scannable terminal output.
session-memory
humanplane
Maintains awareness across sessions. Spawns observer agent on start, loads context, notifies of evolution opportunities.
bsv-standards
b-open-io
This skill should be used when the user asks about any BRC standard (BRC-1 through BRC-113), "what is BRC-61", "what is BRC-42", "what is BEEF", "what is BUMP", "Compound Merkle Path", "Merkle proof format", "what is MAP protocol", "what is AIP", "what is B protocol", "what are BSV standards", "what is SIGMA", "what is BAP", "what is paymail", "what is 1Sat Ordinals", "what is BSV-20", "what is STAS", "lookup BRC", "BitCom protocols", "what is bitcoin-auth", "what is bitcoin-backup", "what is bitcoin-image", "what is Bitcoin Schema", "what is DPP", "what is PacketPay", "what is Authrite", "what is PIKE", "what is P2PKH", "what is Push Drop", "overlay network", "SPV", "outpoint format", "what is ORDFS", "Mandala token", or needs to understand any BSV ecosystem standard, protocol, or specification. Covers all 12 BRC categories: Wallet, Transactions, Scripts, Key Derivation, Payments, Overlays, Peer-to-Peer, Tokens, Outpoints, Opinions, State Machines, and Apps.
smart-commit
devstefancho
Split uncommitted working tree changes into logical, ordered commits by analyzing Claude Code session history. Use when user asks to split commits, organize commits from session, auto-commit by feature, or says "커밋 나눠줘", "커밋 분리", "세션 기반 커밋".
security-rules
rocky2431
Ultra Builder Pro security rules