Skills
A skill is a folder of instructions a compatible client loads when it becomes relevant. Filter by what a skill ships and what its author declares, then read it before you install it.
Ordered one entry per publisher in turn, so a page shows as many publishers as it has rows. Every skill is listed.
- benchmark-checklistby pleasefixaiVet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened)…
- blast-radiusby pleasefixaiFind what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe…
- broby pleasefixaiRestate the last message in plain human language, with no jargon.
- correctby pleasefixaiFind the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types,…
- create-formal-verification-skillby pleasefixaiGenerate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in…
- OctoparseSponsoredNo-code web scraping, on a schedule.Scrape with Octoparse
- create-verification-skillby pleasefixaiGenerate a project-local verification skill that drives your app the way a user does — any language, framework, or…
- figure-it-outby pleasefixaiDesign an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a…
- howby pleasefixaiUse for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions…
- in-your-own-wordsby pleasefixaiRestate in your own words what you think the user's goals are and what problem they're trying to solve. Use for…
- interrogateby pleasefixaiUse for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find…
- ketchupby pleasefixaiCatch the user up on what changed in this chat since their last message, in plain words and small visuals. List every…
- ketchup-videoby pleasefixaiCatch the user up like pstack:ketchup, with a short subtitled video of slides for what happened and the waiting calls…
- maintain-formal-verification-skillby pleasefixaiBring a project's formal verification back in line with the code after the code changes: find the commits that touched…
- maintain-verification-skillby pleasefixaiPeriodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature,…
- make-bot-uiby pleasefixaiUse when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must…
- principle-attack-the-premiseby pleasefixaiApply when two or more fixes that share one premise have failed the same gate. Write the premise down and test it…
- principle-boundary-disciplineby pleasefixaiApply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI,…
- principle-build-the-leverby pleasefixaiApply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or…
- principle-encode-lessons-in-structureby pleasefixaiApply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the…
- principle-exhaust-the-design-spaceby pleasefixaiApply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3…
- principle-experience-firstby pleasefixaiApply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship…
- principle-explain-the-numberby pleasefixaiApply before you measure, and before you trust, report, or act on a number you measured: a speedup, a regression, a…
- principle-fix-root-causesby pleasefixaiApply when debugging. Trace each symptom back to the first place the system went wrong and fix it there. A guard is a…
- principle-foundational-thinkingby pleasefixaiApply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what…
- principle-guard-the-context-windowby pleasefixaiApply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents;…
- principle-laziness-protocolby pleasefixaiApply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward…
- principle-make-operations-idempotentby pleasefixaiApply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries.…
- principle-migrate-callers-then-delete-legacy-apisby pleasefixaiApply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the…
- principle-minimize-reader-loadby pleasefixaiApply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state…
- principle-model-the-domainby pleasefixaiApply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files.
- principle-never-block-on-the-humanby pleasefixaiApply when tempted to ask 'should I do X?' on reversible work.
- principle-outcome-oriented-executionby pleasefixaiApply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't…
- principle-prove-it-worksby pleasefixaiApply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the…
- principle-redesign-from-first-principlesby pleasefixaiApply when integrating a new requirement into an existing design.
- principle-separate-before-serializing-shared-stateby pleasefixaiApply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first;…
- principle-sequence-verifiable-unitsby pleasefixaiApply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work…
- principle-subtract-before-you-addby pleasefixaiApply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references…
- principle-test-behavior-not-implementationby pleasefixaiApply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when…
- principle-type-system-disciplineby pleasefixaiApply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make…
- sharpenby pleasefixaiMake a task deeper, not bigger, then rewrite the prompt. Use for pstack:sharpen.
- show-me-your-workby pleasefixaiKeep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why,…
- statechartby pleasefixaiCheck a TLA+ model of a system that moves between states, such as a product flow, a protocol, or a service, and draw it…
- tddby pleasefixaiUse only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious…
- teachby pleasefixaiExplain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what…
- technical-writingby pleasefixaiLayered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global…
- typescript-best-practicesby pleasefixaiTypeScript best practices. Use when reading or editing any .ts or .tsx file.
- unslopby pleasefixaiCut AI tells from any writing.
- whyby pleasefixaiUse for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed…
