Published skills
smart-explore
Token-optimized structural code search using tree-sitter AST parsing. Use this instead of reading full files when you need to understand code structure, find functions, or explore a codebase efficiently.
claude-mem
Captures agent actions across sessions, compresses them with AI, and injects relevant context into future interactions. Compatible with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode, and more.
babysit
Monitors a pull request or review cycle until it is ready to merge. This skill is used to track PR comments, reviews, and CI status until all actionable issues are resolved.
oh-my-issues
This skill clusters GitHub issue backlogs by root cause into plan-master issues, redirects related children, and bundles architectural-fix PRs to close clusters atomically. It's ideal for triaging and consolidating numerous issues sharing underlying defects, or for building a plan series or roadmap.
claude-mem
Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More.
claude-mem
Persistent Context Across Sessions for Every Agent – This feature captures all agent activity during sessions, compresses it with AI, and re-injects relevant context into future interactions. It supports Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode, and more.
design-is
Audits a design against Dieter Rams' ten "Good design is..." principles, then provides a /make-plan prompt for a new design, refinement, or redesign. Use when the user requests a design audit, review, or critique that should lead to a plan.
how-it-works
This skill explains how claude-mem captures observations, when memory injection occurs, and where its data is stored.
knowledge-agent
Build and query AI-powered knowledge bases from claude-mem observations. Use when users want to create focused "brains" from their observation history, ask questions about past work patterns, or compile expertise on specific topics.
learn-codebase
Prime a codebase by reading every source file in full. Use when starting work on a new or unfamiliar project, or when the user asks to "learn the codebase", "read the codebase", "prime", or "get up to speed".
mem-search
Searches claude-mem's persistent cross-session memory database. Use this to answer questions about previous solutions or retrieve work from past sessions.
pathfinder
Maps a codebase into feature-grouped flowcharts, identifies duplicated concerns across features, and proposes a unified architecture. Use when asked to "find the ideal path," unify duplicated systems, or audit architecture before a refactor, emitting a proposed unified flowchart plus per-system /make-plan prompts.
timeline-report
Generates a Journey Into [Project] narrative report analyzing a project's entire development history from claude-mem's timeline. Use it when asked for a timeline report, project history analysis, development journey, or full project report.
claude-code-plugin-release
Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, npm publishing (so npx claude-mem@X.Y.Z resolves), build verification, git tagging, GitHub releases, and changelog generation.
weekly-digests
Generates a week-by-week narrative digest of a project's Claude-mem timeline, splitting it into ISO-week files and using subagents to produce weekly chapters. Ideal for "weekly digests" or "narrative chapters" of a project's history.
wowerpoint
Converts a single document into a kawaii NotebookLM slide-deck PDF. It's used to generate shareable narrative slides from a single file, responding to commands like wowerpoint this, make a deck about <file>, or turn this report into slides.
make-plan
Create a detailed, phased implementation plan including documentation discovery. Use this when asked to plan a feature, task, or multi-step implementation, especially before executing with 'do'.
do
Execute a phased implementation plan using subagents. Use when asked to execute, run, or carry out a plan — especially one created by make-plan.
crabspace
Interact with CrabSpace, a MySpace-style social network for AI agents. It handles profile creation, appearance customization, friend management, comment wall posting, registration, tweet verification, and profile updates.
Category alert