wcygan/agent-skills - Page 2

sloppy-commit-push

Stages all repository changes, creates a concise Conventional Commit, and pushes the current branch. Use only when you explicitly want to commit and push the entire working tree.

vercel-react-view-transitions

Guide for implementing smooth, native-feeling animations using React's View Transition API (`<ViewTransition>` component, `addTransitionType`, and CSS view transition pseudo-elements). Use this skill whenever the user wants to add page transitions, animate…

reconcile-documentation

Audit and reconcile project documentation against authoritative repository and runtime evidence. Use when READMEs, documentation sites, runbooks, examples, agent instructions, or skill directories may be stale after code, configuration, interface, workflow,…

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.

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 text in one file per ticket locally, or native blocking links on a real tracker.

triage

Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.

incident-learning-loop

Turn a closed or stabilized engineering incident into an evidence-backed Incident Learning Pack that distinguishes trigger, cause, contributing conditions, material impact, detection and recovery gaps, and verifiable corrective actions. Use after an outage,…

design-bounded-loop

Design or audit a bounded feedback loop before it runs: define an outcome, authoritative observation, baseline, bounded action, authority, sole writer, evaluator, progress, checkpoint, state, budgets, terminal conditions, escalation, wakeup, and final…

monitor-until

Watch one authoritative state source, read-only, until a declared terminal condition, timeout, access loss, or poll budget. Use when an explicitly invoked status watcher needs normalized observations, meaningful-transition evidence, bounded backoff, and…

verify-and-revise

Run a bounded producer-verifier revision loop for one explicitly authorized artifact against a fixed acceptance rubric or oracle. Use when an artifact needs repeated evidence-backed revision with actionable feedback, an attempt ledger, minimal coherent…

diagnose-difficult-bug

Diagnose one intermittent, environment-dependent, stateful, or distributed bug by establishing a faithful reproduction, tracing its failure path, modeling a counterexample schedule when concurrency matters, and defining a regression oracle and repair…

map-production-scenario

Map one bounded production request, event, job, or state transition across executable code, data lineage, and operational signals, optionally including a named failure variant. Use when a team needs an integrated explanation of how a concrete scenario…

shape-safe-change

Shape one cross-cutting or architecture-sensitive change by aligning domain meaning, module seams, blast radius, compatibility, staged transition, rollback, and verification. Use before implementing API, event, schema, configuration, dependency, ownership,…

prototype

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.

research

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.

resolving-merge-conflicts

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

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 Spec (does the code match what the originating issue/spec asked for?). Runs both reviews…

codebase-design

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…

design-verification-strategy

Design an evidence-backed verification strategy for a change, feature, migration, integration, or system claim by defining risks and invariants, authoritative oracles, test tiers, fixtures, negative and counterexample cases, environment fidelity, independent…

domain-modeling

Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

find-skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for…

grill-with-docs

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

grilling

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

handoff

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

improve-codebase-architecture

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

operate-kubernetes-gitops

Diagnose and operate Kubernetes systems managed by GitOps by reconciling repository intent, rendered manifests, controller status, Kubernetes objects, events, logs, dependencies, and user-visible health. Use for Flux or Argo CD reconciliation failures,…

setup-matt-pocock-skills

Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

tdd

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

wait-what

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

writing-for-agents

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

animate

Build an animation from scratch, making the decisions in the order that determines whether it feels right — should it animate at all, what purpose, which tool, which properties, which curve and duration, how it interrupts, how it exits. Writes the…

animation-vocabulary

Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…",…

ephemeral-chooser

Create, compare, share, and promote temporary component variants with an Ephemeral Chooser. Use when the user asks for several UI variants, a prototype switcher, query-parameter review links, Leva-style tuning controls, or to keep one winner and tear down the…

find-animation-opportunities

Search a codebase or UI for places that don't animate but should, and reject everything that shouldn't. Read-only; it proposes motion with exact values, it does not implement it. Use when the user asks "what could be animated here?" or wants to "make this…

hill-climbing

Run an explicitly invoked, bounded metric-driven Codex improvement loop: establish a mechanical baseline, change one variable, measure against noise tolerance, keep only guarded improvements, restore loop-owned regressions, and stop at the target or plateau.…

improve-animations

Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not…

pi-coding-agent

Use and investigate the Pi coding agent CLI. Covers interactive, print, JSON, and RPC modes; model and tool flags; sessions; local OpenAI-compatible models; skills; extensions; and the pi monorepo. Use when running `pi`, automating it, configuring…

pi-sdk

Build, debug, or explain TypeScript integrations with the Pi coding agent SDK. Use for @earendil-works/pi-coding-agent, createAgentSession, AgentSession, AgentSessionRuntime, ModelRuntime, ResourceLoader, custom tools, SDK events, in-process agent embedding,…

review-animations

Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.

skill-intake

Turn rambling, unstructured observations about manual, repetitive, error-prone, or agent-assisted work into a scoped skill intake decision and a self-contained paste-ready implementation handoff for this repository’s skills/new-plugin workflow. Use when a…