agents-correct
Find the mistakes agents keep repeating in a repo and make each one impossible, trying architecture first, then types, lint, tests, and docs last. Use when the operator keeps correcting the same mistake, or for /agents-correct.
38,472 Skills
Search uses this published catalog; rankings and counts are snapshots.
Find the mistakes agents keep repeating in a repo and make each one impossible, trying architecture first, then types, lint, tests, and docs last. Use when the operator keeps correcting the same mistake, or for /agents-correct.
After a work session, review what went wrong and right and turn each lesson into a concrete edit to an existing skill or AGENTS.md line. Use when the user says "reflect" or /agents-reflect.
Fan out N parallel subagent workers in one turn, aggregate their results, and report PASS, ISSUES, or BLOCKED per worker. Use for /agents-swarm, "swarm this", parallel coverage across slices, races between approaches, or broad exploration.
Explain how a subsystem works, its architecture, runtime flow, and where new code belongs. Use for "how does X work", walkthroughs before changing something, and placement or ownership questions like "where should this live" or "which package owns this". Use comms-why for motivat
Multi-reviewer critique of a diff, run as parallel read-only subagents from distinct angles, then synthesized into one verdict. Use for "interrogate", "adversarial review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
Layered technical-writing standard covering document modes, sentence style, instruction rules, and unambiguous syntax. Use when writing or reviewing skills, docs, READMEs, RFCs, PR descriptions, or commit messages.
Cut machine-written patterns from prose while keeping meaning and voice, or flag them without rewriting. Use when drafting or editing prose, docs, PR descriptions, commit messages, or replies that read machine-written.
Explain why code is shaped the way it is, using git history, PRs, and connected MCP evidence, with citations and honest confidence. Use for "why does X work this way", "why did we pick Y", design rationale, regressions, and postmortems. Use comms-how for runtime behavior.
Apply Effect v4 conventions for services, layers, tagged errors, boundary runners, resources, retries, deadlines, HTTP, and tests. Use when writing or reviewing TypeScript that imports effect, adds a service or error class, chooses where to run a program, bounds external I/O, or
Move heavy or long-running work off a constrained runtime (for example the Cloudflare Workers memory or CPU ceiling) by first extracting domain logic into packages as Effect programs, then moving execution. Use when starting or continuing a runtime migration or moving a service a
A scoring scale for evaluating how well a CLI is designed for AI agents, based on the "Rewrite Your CLI for AI Agents" principles. Use when reviewing, designing, or comparing a CLI for agent use, or scoring its agent readiness.
Vet a performance measurement for limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened before you report or act on it. Use when you run a benchmark or report a measured speedup or regression.
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it is safe because of by running real code. Use when asked for the "blast radius of X" or "what could this break", or when reviewing a small diff you do not trust.
Short checklist of engineering principles to apply before and after non-trivial work. Use when planning or reviewing a non-trivial change, debugging a stubborn failure, designing types or boundaries, or deciding how to sequence a migration.
Model an entity's lifecycle (status, state, phase) as an explicit state machine with a pure decide function, one guarded write path, and events from a durable record. Use when adding or changing a status field, a transition, or a reaction to one, when several writers set the same
Fix a bug test-first when there is a clear, cheap regression test path. Use when the user asks for TDD, a failing test, or a regression test, or when the bug has an obvious cheap local test target.
Catalog captured:2026-11-21