Claude Skills by toverux

Reconcile this repo's forked skills with a new upstream release. Use when the user says an upstream (compound-engineering, mattpocock/skills) was updated, asks to merge/sync upstream changes into the forks, or wants the forks' divergence audited.

Keep the session's prompt cache warm while you step away.

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

Scan the session for compound-worthy learnings, then commit the working tree with a repo-appropriate, value-communicating message.

Garbage-collect the knowledge stores — audit AGENTS.md, and docs/solutions/ where that store is enabled, against the current code.

Capture this session's durable learnings and route each to the right knowledge store, every write user-gated. Use at loop end when /commit's opening scan finds candidates, when /diagnosing-bugs closes out a fix, or when the user wants to capture, remember, or write down a learning, convention, gotcha, decision, or preference.

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to be grilled about a plan, wants a decision stress-tested, or when requirements are fuzzy before a spec is written.

Compact the current conversation into a handoff document for another agent to pick up.

Implement a spec or a single ticket, driving TDD at the seams agreed in the spec.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

Use when you need to resolve an in-progress git merge/rebase conflict.

The review gate — effort-scaled, multi-angle review of the working diff or the changes since a fixed point, every finding independently verified.

Configure this repo's cantrips loop — knowledge stores and storage backend — by writing docs/agents/cantrips-loop.md.

Set up a hook that blocks dangerous git commands before they execute, in Claude Code or Codex CLI.

Optional pre-review quality pass — preserving fixes through the reuse, simplification, and efficiency lenses. Bug hunting is /review-gate's job.

Synthesize the current conversation into a published spec, test seams included.

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

Teach the user a new skill or concept, within this workspace.

Break a spec, plan, or the current conversation into tracer-bullet tickets, each declaring its blocking edges.

Stop. That last message did not land — re-pitch it.

Load before writing or editing any file an agent will load and act on — a skill (SKILL.md), an AGENTS.md or CLAUDE.md, or a rules file. The vocabulary and principles that make those files predictable. A session that only reads them leaves this unloaded.