Instruccions per a IA
Disseny d’instruccions i plantilles per a models d’IA
subagent
jxnl
Delegate codebase exploration or scripted actions to a non-interactive Codex exec run (codex exec / codex e). Use when you want a subagent to read lots of code or take actions without human interaction, and you can accept CLI output and optional file changes as the result.
skill-manager
ashimoon
Manage your installed Claude Code skills - install, update, rename, uninstall, and list skills from GitHub URLs. Use when the user wants to install a skill, update a skill, list installed skills, rename a skill, remove/delete/uninstall a skill, or provides a GitHub URL to a skills directory.
Claude Code Plugins Quick Reference
bfollington
Test: claude --plugin-dir ./my-plugin
skill-management
bfollington
Create, update, and manage Claude Code skills. Use when working with SKILL.md files, slash commands, or extending Claude's capabilities.
claude-code-usage
openclaw
Check Claude Code OAuth usage limits (session & weekly quotas). Use when user asks about Claude Code usage, remaining limits, rate limits, or how much Claude usage they have left. Includes automated session refresh reminders and reset detection monitoring.
glitchward-llm-shield
openclaw
Scan prompts for prompt injection attacks before sending them to any LLM. Detect jailbreaks, data exfiltration, encoding bypass, multilingual attacks, and 25+ attack categories using Glitchward's LLM Shield API.
hergunmac
openclaw
Access AI-powered football match predictions from hergunmac.com. Use when the user asks about football/soccer match predictions, betting tips, match analysis, team statistics, head-to-head data, or upcoming match insights. Covers worldwide leagues with confidence scores, AI reasoning, and historical performance tracking.
aiusd-skill
openclaw
AIUSD trading and account management skill. Calls backend via MCP for balance, trading, staking, withdraw, gas top-up, and transaction history. Auth priority: MCP_HUB_TOKEN env, then mcporter OAuth or local token file.
OpenClaw Claude Code Skill
openclaw
MCP Specification
rewrite-rustdoc
jim60105
Rewrite Rust documentation comments to ensure all documentation and comments are in English, following rustdoc guidelines. Use when the user wants to clean up Rust documentation, translate Chinese comments to English, fix missing documentation, or ensure rustdoc compliance in a Rust codebase.
bridle
openclaw
Unified configuration manager for AI coding assistants. Manage profiles, install skills/agents/commands, and switch configurations across Claude Code, OpenCode, Goose, and Amp.
appraisal-ai
openclaw
Drafts real estate appraisal reports from your project workfile. Produces Word narratives with tracked changes and Excel adjustment grids from your own master templates. You review and accept every change.
aimlapi-llm-reasoning
openclaw
Run AIMLAPI LLM and reasoning workflows through chat completions with retries, structured outputs, and explicit User-Agent headers. Use when Codex needs scripted prompting/reasoning calls against AIMLAPI models.
aiusd-skill
openclaw
AIUSD trading and account management skill. Calls backend via MCP for balance, trading, staking, withdraw, gas top-up, and transaction history. Auth priority: MCP_HUB_TOKEN env, then mcporter OAuth or local token file.
botsee
openclaw
Monitor your brand's AI visibility via BotSee API
agent-sdk
majesticlabs-dev
Guide for Claude Agent SDK - build custom AI agents powered by Claude. Covers installation, authentication providers, tool permissions, file-based configuration, TypeScript/Python code examples, and project scaffolding templates.
agentica-server
parcadei
Agentica server + Claude proxy setup - architecture, startup sequence, debugging
llm-tuning-patterns
parcadei
LLM Tuning Patterns
hooks
parcadei
Hook Development Rules
debug-hooks
parcadei
Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.
braintrust-tracing
parcadei
Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging
commit
parcadei
Create git commits with user approval and no Claude attribution
completion-check
parcadei
"Completion Check: Verify Infrastructure Is Wired"
agentica-claude-proxy
parcadei
Guide for integrating Agentica SDK with Claude Code CLI proxy