Skills matching the name, description or GitHub author.
Meta-skill for extracting and creating reusable Claude Code skills from past work sessions. Analyzes git history, code patterns, workflows, and documentation to identify harvestable skills, then generates compr...
Automatically log meaningful insights, discoveries, and decisions during coding sessions. Capture non-trivial learnings about edge cases, design decisions, patterns, and implementation details. Activate when bu...
Document for build custom AI agents with the Claude Agent SDK, include full SDK Reference and Example Codes.
Document for build custom skill for claude code, with full Reference and Example Codes.
Use this skill for large project maintenance with layered CLAUDE.md index system. Triggers when users need to (1) analyze and document existing codebases, (2) generate hierarchical CLAUDE.md files for modules,...
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or to...
Use this skill when entering a new or legacy project for the first time, to scan and localize global skills for project-specific conventions. Triggers on "onboard", "init skills", "localize skills", "project se...
Meta-skill that analyzes the Trail of Bits Testing Handbook (appsec.guide) and generates Claude Code skills for security testing tools and techniques. Use when creating new skills based on handbook content.
Use multiple Claude agents to investigate and fix independent problems concurrently
Guidelines for incremental development practices. Claude should use this skill when writing multiple similar files (tests, classes, configurations) to ensure each piece is verified before moving to the next.
Control any terminal application (TUI, CLI, or interactive program) programmatically through HTTP API or CLI commands. Use when you need to: (1) Run terminal applications like vim, htop, nano, or less, (2) Auto...
Debug, check, or restart Samara.app - the message broker. Use when messages aren't being detected, Samara crashed, need to view logs, check Full Disk Access, or restart the app. Trigger words: samara, messages...
Semantic memory recall using FTS5 and Chroma. Use PROACTIVELY whenever the user asks about past events, themes, conversations, or when historical context would enrich a response. Trigger words: remember, when d...
Monitor satellite services and sense events. Check service status, view logs, trigger manual runs, or diagnose issues. Trigger words: senses, satellites, services, watchers, bluesky, github, location.
Debug Samara session management, message batching, and task routing. Use when messages are scrambled, batching seems wrong, group chats behave oddly, or concurrent tasks interfere with each other. Trigger words...
Access past architectural and technical decisions with their rationale. Contains decisions made over time with context, alternatives considered, and reasoning. Use when asked why something was decided, checking...
Run organism maintenance checks - drift detection, symlink repair, service verification. Use for health checks and maintenance tasks.
Quick observation capture about a person. Use when noticing something about someone, wanting to record a detail, or capturing context from a conversation. Trigger words: note about, noticed, observation about,...
Current location context with nearby places and pattern insights. Use when checking where you are, understanding local context, finding nearby places, or getting location-aware information. Trigger words: locat...
View and manage calendar invitations - check pending invites, accept/decline meeting requests, create events
Query the unified event stream for recent activity across all surfaces. Use when user asks about recent conversations, what happened on iMessage/CLI/wake cycles, or wants to see cross-surface activity. Trigger...
Add non-text files to a person's artifacts folder. Use when saving images, documents, or other files related to someone. Trigger words: artifact, save image, add photo, attach file, store document.
Self-referential iteration mode for completing complex tasks autonomously. Use when a task requires multiple attempts, trial-and-error, or persistent effort until success. Based on the Ralph Wiggum methodology....
View or add to today's episode log. Use when reviewing what happened today, adding a notable event, checking daily progress, or appending to the day's record. Trigger words: episode, today, log, daily, happened...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.