Claude Skills by tomcounsell

This repo adds a third artifact type to `/new-skill`'s generic skill+agent creation: a **project Python tool** registered as a `valor-*` CLI entry point. The conventions below are this repo's; the global skill body covers skill and agent creation generically.

Interview the user to get unblocked after deep work, one question at a time. Triggered by 'ask me', 'I need your input', 'interview me to unblock this', or when only the human can answer.

Audit Claude Code hooks for safety and correctness. Use when reviewing hook health, checking hook safety, validating hooks, or after adding/modifying hooks.

Audit Popoto Redis models for gaps and naming drift. Use when reviewing data model health or the data layer, checking model integrity, validating Redis models, or scanning for model issues.

Audit skill quality: lint structure, descriptions, rot, orphans; --arch for architecture dispositions. Use when auditing, linting, or checking skills.

Audit tools/ for structure, tests, CLI quality, and docs. Use when checking tool health, validating tools, or after adding a tool. Also 'check the tools', 'which tools need work'.

Stage, launch, grade, and schedule a Claude Managed Agent (CMA) from a build-sheet. Triggered by 'build the agent', 'launch this agent', 'deploy a managed agent', or as /imagine-agent's handoff.

Reconstructs a day's work from git commit history in the current repo, groups it into time-blocked calendar events (merged by feature/goal, minimum 20 minutes each), and writes them to that repo's mapped Google Calendar — creating new events or updating existing overlapping ones so reruns stay idempotent. Replaces the old hook-based time-tracking system. Use when the user wants to log/sync their day's work to their calendar, review what they did today, or backfill a prior day. Triggered by '/...

Drive native macOS apps: click, type, screenshot windows without stealing focus. Use for desktop apps (Slack, Notes, Xcode), macOS workflow automation, or native window screenshots. macOS-only.

Create/review/maintain Claude Code Routines (cloud scheduled agents, aka 'Cowork'). Triggered by 'set up a routine', 'schedule a cloud agent', 'cowork task', 'migrate to a routine'.

Pre-publish editorial gate for external-audience content: removes AI-writing tells and blocks hollow drafts. Use on documents, presentations, emails, posts, or web copy once a first draft exists. Triggered by 'de-slop this', 'editorial pass', 'humanize this', 'remove the AI tells', or invoked as a mandatory gate by email, do-presentation, linkedin, and x-com.

Use when executing a plan document to ship a feature. Triggered by 'build this', 'execute the plan', 'implement the plan', or any request to run/ship a plan.

Send a spoken executive brief to a chat as a voice message. Triggered by 'send a voice debrief', 'speak this update', 'do-debrief', or any request to deliver an audio summary.

Template for a repo-specific /do-deploy skill. Use when creating a production deployment skill: copy to do-deploy/ and customize.

Audit a web UI against premium design criteria. Use when evaluating design quality, or on 'review this design', 'check the UI', 'audit this page', 'scan the interface', or a URL for design feedback.

Turn a moodboard into additive design-system edits. Triggered by 'apply this moodboard', 'tighten the design system', 'theme pass', 'design system pass', 'organize design files', or a moodboard URL.

Discover happy paths on a target site using BYOB MCP, producing trace JSON for deterministic test generation. Use when asked to discover paths, map site flows, or record browser traces for tests.

Cascade documentation updates after a code change. Triggered by 'update docs', 'sync the docs', or any request about documentation updates.

Deep audit of a named feature's integration health: orphan code, dead wiring, missing tests, config gaps. Use when asked to audit a feature's integration or wiring. User-invoked only.

Post a GitHub investigation issue for an unverified finding, gap, or anomaly. Use when an audit or research surfaces something suspicious, or an observed behavior is unexpected but unconfirmed.

Create a self-contained GitHub issue ready for planning. Triggered by 'create an issue', 'file an issue', 'track this', or by /sdlc at Step 1.

Use when merging a pull request that has cleared the SDLC pipeline. Triggered by 'merge this PR', 'do-merge', or automatically by /sdlc at the MERGE stage.

Apply a targeted fix to failing tests or review blockers. Triggered by 'patch this', 'fix the failures', 'fix the blockers', 'do-patch', or by do-build at test-fail and review-blocker steps.

Use when reviewing a plan before build. Triggered by 'critique this plan', 'review the plan', 'war room', or 'do-plan-critique'.

Use when creating or updating a feature plan document. Triggered by 'make a plan', 'plan this', 'flesh out the idea', or any request to scope and plan work before implementation.

Review a pull request against its plan. Triggered by 'review this PR', 'check the pull request', 'do a PR review', or a PR URL.

Create a polished Marp slide deck about a feature, concept, or system. Triggered by 'make a presentation', 'create slides', 'do-presentation', or 'explain this as a deck'.

Supervise a full SDLC pipeline run to merge in a local Claude Code session. Triggered by 'do-sdlc', 'run the full pipeline', 'ship this issue end to end', 'supervise the sdlc'. Also the home of the single-stage router contract that /sdlc (in this repo) executes.

Run the project's test suite and aggregate results. Triggered by 'run tests', 'test this', or any request about testing.

Turn text into spoken audio (OGG/Opus). Use when asked to 'record a voiceover', 'narrate this', 'speak this', 'read this aloud', 'say this', 'make an audio/voice clip', or 'text to speech'.

Use when reading, searching, drafting, or sending email. Triggered by 'read my email', 'check my inbox', 'send an email', 'reply to that email', 'search my mail', or any request to read/send mail.

Create distinctive frontend interfaces that avoid generic AI aesthetics. Use when building web components, pages, artifacts, posters, or applications.

Use when accessing Google Workspace services including Gmail, Calendar, Docs, Sheets, Slides, Drive, and Chat. Triggered by requests for email, scheduling, document creation, or file management.

Socratic interrogation to probe assumptions and surface gaps. Triggered by 'grill me', 'challenge my thinking', 'probe this', 'stress test this idea', or pressure-testing a plan or belief.

Turn client goals into a build-sheet for /build-agent. Triggered by 'imagine an agent', 'help a client design an agent', 'what agent should we build for them', 'scope an agent with the client'.

Render .mmd (and .excalidraw) files as hand-drawn PNGs via Excalidraw. Triggered by 'render this diagram', 'export mermaid as PNG', 'convert mmd to image', or 'excalidraw export'.

Create a new audit skill from established patterns. Use when creating an audit, or on 'create an audit', 'new audit skill', 'add an audit', 'make an audit for', 'I want to check X for problems'.

Use when creating a Claude Code skill, subagent, or tool, or capturing this session as a skill. Triggered by 'new skill', 'new agent', 'skillify', 'capture this as a skill', 'save this workflow'.

Build or update a project's domain vocabulary in ONTOLOGIES.md. Triggered by 'ontologies', 'build vocabulary', 'name things', 'define terms', or establishing precise domain language.

Create high-quality visual designs — websites, app screens, dashboards, slides, marketing materials, social media graphics — using the pen.dev CLI tool. Use this skill whenever the user wants to create, generate, or visualize any kind of UI design, mockup, wireframe, layout, webpage, app screen, presentation slide, poster, banner, or marketing asset. Also use it when the user says things like "design me a...", "make a visual for...", "create a mockup of...", "what would X look like?", or want...

Turn what's being communicated into a crafted single-page HTML explainer with diagrams. Triggered by 'present this', 'make this visual', 'show me this as a page'.

Change a plan's type (bug/feature/chore) during the Planning phase. Use when the initial classification was wrong or scope changed; only works before plan approval.

Stakeholder-friendly summary of recent commits by category with contributor stats. Use when asked for a weekly, bi-weekly, monthly, sprint, engineering, or team review, or 'review the last N days'.

Course-correct mid-session and reassess priorities. Triggered by 'zoom out', 'step back', 'reassess', 'am I on track', 'am I solving the right problem', or checking work against real goals.

Pre-publish human-signal gate for social media drafts. Use when /linkedin or /x-com is about to publish a post, or when asked to run an authenticity check on any draft file.

Use when finding bridge events, agent responses, timeouts, or errors in system logs. Triggered by requests to debug system behavior, investigate errors, or check what the agent did.

Use when deploying merged changes to production across bridge machines. Triggered by 'deploy to prod', 'ship it', 'push to prod', or 'do-deploy'.

Find, download, and prep an ebook as clean Markdown for AI ingestion. Use when digitizing an owned print book, converting EPUB/PDF/MOBI, or chunking for RAG. NOT academic papers or DRM'd ebooks.

Use when reading posts or engaging on LinkedIn. Triggered by requests to comment on LinkedIn, browse the feed, write or interact with posts, check DMs, or read/reply to LinkedIn messages.

Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) via officecli. Use when creating, inspecting, checking formatting, finding issues, adding charts, or editing Office files.