Loading...
Loading...
Found 2,778 Skills
List pending todos and select one to work on
Fetch latest from origin, prune remote-tracking refs, delete stale local branches and worktrees, and fast-forward important branches. Use when tidying up a worktree-based repo layout.
Auto-extract GTME metrics from work sessions. Lines shipped, bugs fixed, PRs merged, cost per feature. Weekly digests and executive summaries. Use when: capture metrics, portfolio report, what did I ship, weekly summary.
Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy's autoresearch. USE FOR: autonomous improvement, iterative optimization, experiment loop, auto research, performance tuning, automated experimentation, hill climbing, try things automatically, optimize code, run experiments, autonomous coding loop. DO NOT USE FOR: one-shot tasks, simple bug fixes, code review, or tasks without a measurable metric.
Bulk resolve unresolved PR review threads. Useful after manually addressing threads or after using /pr-threads-address.
Plan a new feature from concept to approved implementation plan. Activates Product Council for strategic evaluation, then Feature Council for technical planning. Produces a documented decision and scoped task breakdown. Use when starting any new feature work.
Implement a full-stack feature following an approved plan. Builds database layer, backend API, frontend components, and tests. Use after plan-feature has produced an approved implementation plan, or when you have a clear set of tasks to implement across the stack.
This skill should be used when the user asks to "run autoresearch", "optimize X in a loop", "set up autonomous experiments", "start autoresearch", "optimize X overnight", or "experiment loop". Sets up and runs an autonomous experiment loop for any optimization target.
Audit PostHog survey SDK features and version requirements
UPDATE-DOCS phase. Refresh README.md, CLAUDE.md, and docs/index.html to reflect changes made this session. Commits and pushes doc updates. Terminal phase — declares COMPLETE.
Verifies the agent's current work against a specific question by analyzing unstaged changes, staged changes, recent commits, and codebase context. Answers succinctly for a senior audience. Use when user says "/check", "verify that", "confirm that", "check if", "is X done?", or asks about current session changes.
Request or contribute a new sales/marketing/GTM skill that doesn't exist yet. Use when no existing skill covers the user's need — helps them build the skill and submit a PR, or file an issue requesting it. Also use when the user says 'there should be a skill for this', 'can we make a skill', 'I want to contribute a skill', or 'none of the sales skills cover my use case'.