seanrobertwright

Build a complete User Acceptance Test for a codebase — an exhaustive markdown checklist written to the tester's skill level (novice / intermediate / expert), plus an HTML form the tester fills in (pass/fail/not done, look-and-feel comments, screenshots) that…

Turn a completed UAT into a prioritised fix plan and then fix it. Reads a UAT markdown file (or its results.json) that a tester has filled in, diagnoses every failure, look-and-feel complaint and tester-reported finding against the actual code, and produces a…

Audit and prune CLAUDE.md and other instruction files using progressive disclosure — move situational content out of every-session context into path-scoped rules, skills, nested CLAUDE.md files, or referenced docs, and delete what the codebase already tells…

Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.

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…

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

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.

Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.

Create runbooks, playbooks, and technical documentation for engineering teams. Use when the user wants to document a process, create a runbook, build operational docs, or formalize any repeatable technical procedure. Triggers on requests like "create a…

Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.

Create Instagram content for AI/tech educational posts. Use when the user wants to create Instagram content including carousels, reels scripts, or captions. Triggers on requests like "create an Instagram post about...", "write a carousel on...", or any…

Create and edit Remotion videos with domain-specific knowledge. TRIGGERS - Use this skill when: - User mentions "Remotion" in their request - User references a Remotion project path (remotion-videos/*, contains remotion.config.ts) - User asks to create,…

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

Generate LinkedIn posts from Content Engine + daily notes + web research

Generate YouTube Shorts scripts from Content Engine + daily notes + web research

Generate X posts/threads from Content Engine + daily notes + web research

Two connected workflows that audit a repo's PRs against its OWN documented AI layer (rules, skills, workflow command definitions) -- not generic code-quality judgment. Workflow A (audit, run via `/pr-trajectory-audit`) reads the repo's own rules/workflow…

Use when a sliced part is ready to go to the physical printer — sending a job, starting a print, checking what the printer is doing, or confirming which filament is actually loaded. Also when the user asks to "print it", "send it", or what the printer is…

Use when press fits come out wrong, when a hole prints undersize or a peg prints too fat, when the user asks to calibrate the printer or a material, or when an export warns that the calibration has never been measured. Turns caliper readings from a printed…

Use when a verified part needs turning into machine instructions — print time, filament grams, AMS slot mapping, purge waste, or a G-code preview. Also when the user asks how long a print will take or what it will cost.

Use when a mesh arrives from outside — a downloaded STL, a scan, a file from another tool — and is broken, non-manifold, inverted, or fails to load or slice. Also when the user asks to fix, heal, or clean up a model.

Use when a part needs checking for printability rather than correctness — before committing to a print, after a design change, or when the user asks whether something will print, needs supports, or is too thin.

Use when a modelled part needs verifying, measuring, or critiquing — after generating geometry, after editing a parameter, or when the user asks whether a part is correct, will fit, or will print.

Use when the user wants to see a model live in the browser, watch it update while iterating, or asks to open, start, or stop the 3D viewer.

Analyze a project's codebase, PRD, plan documents, and tech stack to recommend and install the right Claude Code hooks from HookMaster's catalog of 50 hooks. Activate this skill when: a PRD, PLAN, SPEC, or design doc is created or updated; a project manifest…

Activate when HookMaster hook conflicts are detected. Triggers when: the conflict-watchdog hook outputs a conflict warning (⚠️ HOOKMASTER CONFLICT DETECTED appears in context); the user installs or enables hooks that are known to conflict (auto-format,…

Bring an existing source into Open Knowledge Format (OKF) compliance — a code repository, a documentation set, an existing/partial knowledge bundle, or a "second brain" (Obsidian vault, Logseq graph, Notion export, Markdown notes). Use when the user wants to…

Create, maintain, validate, and consume Open Knowledge Format (OKF) bundles — vendor-neutral knowledge directories made of plain markdown files with YAML frontmatter. Use when the user wants to capture a project's datasets, schemas, APIs, architecture, domain…

Use when a user request is vague, broad, risky, underspecified, or likely to produce the wrong result unless the real intent is clarified first. Especially useful before feature design, refactoring, architecture changes, safety/compliance work, product…

Use before modifying an existing project, feature, document, architecture, or workflow when prior intent may exist. Compares a new request against stored intent files, detects drift, recommends whether to proceed, clarify, update intent, split scope, or…

Use when: User wants to run Archon workflows, CREATE workflows or commands, set up Archon, or manage Archon configuration. Triggers (run): "use archon to", "run archon", "archon workflow", "use archon for", "have archon", "let archon", "ask archon to".…

Use this skill whenever the user needs API keys, secrets, or environment variables to run code, scripts, or shell commands — even if they don't mention KeyPick by name. Trigger on phrases like "run this script", "test the API", "it needs my key", "set up my…

Work a self-hosted Kanban board from any repo — read the board, create/update/move/claim tasks, comment, and honor the approval gate. Use when the user mentions their kanban board, board tasks/tickets, sprints, or asks to file, update, pick up, or finish…

End-to-end ship pipeline for a finished slice of work: commit → code-review → execution-report → triage + fix → PR → CI → deep PR review → triage + fix → CI → merge. Use when the user says 'ship it', 'post-execute', 'take this to a merged PR', or invokes…

Use when the user asks to build, run, or integrate an "Intent Engine" that converts user goals into structured intent, executable plans, and verification—now including personal intent clarification.