skills-hub GitHub ↗

Skills

115 skills

Meta decloudz skill-writer Guide users through creating Agent Skills for Claude Code.
Plan Addy Osmani api-and-interface-design Guides stable API and interface design.
Verify Addy Osmani browser-testing-with-devtools Tests in real browsers via Chrome DevTools MCP.
Ship Addy Osmani ci-cd-and-automation Automates CI/CD pipeline setup.
Review Addy Osmani code-review-and-quality Conducts multi-axis code review.
Review Addy Osmani code-simplification Simplifies code for clarity.
Define Addy Osmani constraint-driven-development Establishes a project's quality bar as a written contract and stops agents quietly lowering it.
Meta Addy Osmani context-engineering Optimizes agent context setup.
Verify Addy Osmani debugging-and-error-recovery Guides systematic root-cause debugging.
Ship Addy Osmani deprecation-and-migration Manages deprecation and migration.
Ship Addy Osmani documentation-and-adrs Records decisions and documentation.
Verify Addy Osmani doubt-driven-development Subjects every non-trivial decision to a fresh-context adversarial review before it stands.
Build Addy Osmani frontend-ui-engineering Builds production-quality, accessible, responsive user-facing UIs.
Ship Addy Osmani git-workflow-and-versioning Structures git workflow practices.
Define Addy Osmani idea-refine Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking.
Build Addy Osmani incremental-implementation Delivers changes incrementally in thin, verifiable slices.
Define Addy Osmani interview-me Extracts what the user actually wants instead of what they think they should want.
Ship Addy Osmani observability-and-instrumentation Instruments code so production behavior is visible and diagnosable.
Review Addy Osmani performance-optimization Optimizes application performance across frontend, backend, queries, and databases.
Plan Addy Osmani planning-and-task-breakdown Breaks work into ordered tasks.
Review Addy Osmani security-and-hardening Hardens code against vulnerabilities.
Ship Addy Osmani shipping-and-launch Prepares production launches.
Build Addy Osmani source-driven-development Grounds every implementation decision in official documentation.
Define Addy Osmani spec-driven-development Creates specs before coding.
Build Addy Osmani test-driven-development Drives development with tests using the red-green-refactor loop.
Meta Addy Osmani using-agent-skills Discovers and invokes agent skills.
Meta Matt Pocock ask-matt Ask which skill or flow fits your situation.
Review Matt Pocock code-review Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and…
Plan Matt Pocock codebase-design Shared vocabulary for designing deep modules.
Verify Matt Pocock diagnosing-bugs Diagnosis loop for hard bugs and performance regressions.
Define Matt Pocock domain-modeling Build and sharpen a project's domain model.
Ship Matt Pocock git-guardrails-claude-code Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.
Define Matt Pocock grill-me A relentless interview to sharpen a plan or design.
Define Matt Pocock grill-with-docs A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
Define Matt Pocock grilling Grill the user relentlessly about a plan, decision, or idea.
Meta Matt Pocock handoff Compact the current conversation into a handoff document for another agent to pick up.
Build Matt Pocock implement Implement a piece of work based on a spec or set of tickets.
Build Matt Pocock implement-spec Implement the result of /to-spec and /to-tickets in code.
Plan Matt Pocock improve-codebase-architecture Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
Build Matt Pocock migrate-to-shoehorn Migrate test files from `as` type assertions to @total-typescript/shoehorn.
Ship Matt Pocock pr Use when writing a PR body.
Plan Matt Pocock prototype Build a throwaway prototype to answer a design question.
Define Matt Pocock research Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
Review Matt Pocock retro Conduct a retrospective on a coding session.
Build Matt Pocock scaffold-exercises Create exercise directory structures with sections, problems, solutions, and explainers that pass linting.
Meta Matt Pocock setup-matt-pocock-skills Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout.
Ship Matt Pocock setup-pre-commit Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo.
Build Matt Pocock tdd Test-driven development.
Meta Matt Pocock teach Teach the user a new skill or concept, within this workspace.
Define Matt Pocock to-questionnaire Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
Define Matt Pocock to-spec Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.
Plan Matt Pocock to-tickets Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as tex…
Plan Matt Pocock triage Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.
Meta Matt Pocock wait-what Stop.
Plan Matt Pocock wayfinder Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way…
Define Matt Pocock wizard Generate an interactive bash wizard that walks a human through steps only they can perform.
Meta Matt Pocock writing-for-agents Writing documents for agents.
Plan Lauren Tan architect Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
Build Lauren Tan arena Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.
Meta Lauren Tan automate-me Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user work…
Verify Lauren Tan benchmark-checklist Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it.
Review Lauren Tan blast-radius Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up.
Meta Lauren Tan bro Restate the last message in plain human language, with no jargon.
Review Lauren Tan correct Find the mistakes agents keep repeating in this repo and make each one impossible.
Verify Lauren Tan create-formal-verification-skill Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fi…
Verify Lauren Tan create-verification-skill Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
Plan Lauren Tan figure-it-out Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away.
Meta Lauren Tan how Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns thi…
Meta Lauren Tan in-your-own-words Restate in your own words what you think the user's goals are and what problem they're trying to solve.
Review Lauren Tan interrogate Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
Meta Lauren Tan ketchup Catch the user up on what changed in this chat since their last message, in plain words and small visuals.
Meta Lauren Tan ketchup-video Catch the user up like /ketchup, with a short subtitled video of slides for what happened and the waiting calls as text under it.
Verify Lauren Tan maintain-formal-verification-skill Bring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or prope…
Verify Lauren Tan maintain-verification-skill Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one…
Build Lauren Tan make-bot-ui Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing th…
Review Lauren Tan no-comments Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
Meta Lauren Tan poteto-help Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task.
Meta Lauren Tan poteto-mode poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.
Principles Lauren Tan principle-attack-the-premise Apply when two or more fixes that share one premise have failed the same gate.
Principles Lauren Tan principle-boundary-discipline Apply when wiring validation, error handling, or framework adapters.
Principles Lauren Tan principle-build-the-lever Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks.
Principles Lauren Tan principle-encode-lessons-in-structure Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction.
Principles Lauren Tan principle-exhaust-the-design-space Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase.
Principles Lauren Tan principle-experience-first Apply when product, UX, or feature-scope tradeoffs come up.
Principles Lauren Tan principle-explain-the-number Apply before you measure, and before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result.
Principles Lauren Tan principle-fix-root-causes Apply when debugging.
Principles Lauren Tan principle-foundational-thinking Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share.
Principles Lauren Tan principle-guard-the-context-window Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning.
Principles Lauren Tan principle-laziness-protocol Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading.
Principles Lauren Tan principle-make-operations-idempotent Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries.
Principles Lauren Tan principle-migrate-callers-then-delete-legacy-apis Apply when introducing a new internal API while old callers still exist.
Principles Lauren Tan principle-minimize-reader-load Apply when reviewing or shaping code that's hard to trace.
Principles Lauren Tan principle-model-the-domain Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files.
Principles Lauren Tan principle-never-block-on-the-human Apply when tempted to ask 'should I do X?' on reversible work.
Principles Lauren Tan principle-outcome-oriented-execution Apply during planned rewrites and migrations with explicit phase boundaries.
Principles Lauren Tan principle-prove-it-works Apply after completing a task, before declaring done.
Principles Lauren Tan principle-redesign-from-first-principles Apply when integrating a new requirement into an existing design.
Principles Lauren Tan principle-separate-before-serializing-shared-state Apply when concurrent actors might write to the same file, branch, key, or state object.
Principles Lauren Tan principle-sequence-verifiable-units Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs.
Principles Lauren Tan principle-subtract-before-you-add Apply when sequencing an addition, refactor, or rewrite.
Principles Lauren Tan principle-test-behavior-not-implementation Apply when you write, change, or keep a test.
Principles Lauren Tan principle-type-system-discipline Apply when designing types, reviewing a function signature, or writing code in any statically-typed language.
Meta Lauren Tan recall Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight curr…
Meta Lauren Tan reflect Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill.
Meta Lauren Tan setup-pstack Configure which models pstack uses per role and at what reasoning budget.
Define Lauren Tan sharpen Make a task deeper, not bigger, then rewrite the prompt.
Build Lauren Tan show-me-your-work Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result).
Plan Lauren Tan statechart Check a TLA+ model of a system that moves between states, such as a product flow, a protocol, or a service, and draw it as a Mermaid statechart.
Build Lauren Tan swarm Fan out N parallel workers, drain them, and return one report.
Build Lauren Tan tdd Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target.
Meta Lauren Tan teach Explain a body of work plainly so a person actually understands it.
Meta Lauren Tan technical-writing Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax.
Build Lauren Tan typescript-best-practices TypeScript best practices.
Meta Lauren Tan unslop Cut AI tells from any writing.
Meta Lauren Tan why Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds.