Browse by the job you need done. Each skill is a single SKILL.md you can
drop into Claude — here’s what it’s for, what it helps you do, and what it can touch.
Harvest every `ponytail:` comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves behind get tracked instead of ro...
Generates an Apple-compliant account deletion flow with multi-step confirmation UI, optional data export, configurable grace period, Keychain cleanup, and serve...
How to read paid media dashboards without fooling yourself. Attribution models, platform reporting quirks, multi-platform reconciliation, ROAS vs LTV horizon tr...
Reviews a diff or a whole repository for over-engineering only, and returns a delete list rather than prose. Finds reinvented standard library calls, dependenci...
Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration
Architecture patterns, design principles, and proven recipes for building robust robotics software. Use this skill when designing robot software architectures,...
Use huge-plan for open-ended high-risk repo efforts needing websearch during brainstorming and refinement until convergence; exclude direct implementation-only,...
Use when the user wants to review or revise the ordering/model/effort/fableplan assignments on a milestone's GitHub issues — "review the execution plan", "/exec...
Extract the learning signal from execution traces — the textual analogue of a gradient. Use between evaluation and proposing edits. Reads a candidate's val roll...
Use when an agent keeps guessing wrong about a UniFi network, when starting recurring agent work against a gateway, or when asked to "map my network", "document...
Renders the /assess report from the deterministic run-context.json and the layer scorecard - the scorecard, the verbatim cross-layer findings, lying signals, an...
Reports how much hush's compression hook actually saved this session — a per-decision byte rollup from the HUSH_DEBUG manifest plus a per-model token breakdown...
Use when writing project instructions for a coding agent (CLAUDE.md, AGENTS.md, or equivalent). Covers what belongs in them, what does not, structure, and keepi...