tomcounsell
UserA productive AI coworker that learns, self-improves, and ships work.
Categories
Indexed Skills (49)
claude-standards
Audit Claude Code assets — skills, commands, subagents, hooks, and MCP servers — against best practices and optionally apply conservative conformance changes. Use when reviewing overall Claude Code hygiene, bringing the system in line with documented standards, or after adding new skills/commands/subagents. Invoke explicitly; do not use for feature changes.
do-debrief
Use when sending a spoken debrief to a Telegram chat. Collects context, drafts a 30-second executive brief, synthesizes it via TTS, and delivers it as a native voice message. Triggered by 'send a voice debrief', 'speak this update', 'do-debrief', or any request to deliver an audio summary.
do-deploy-example
Template for creating a repo-specific /do-deploy skill. Copy this directory to do-deploy/ and customize DEPLOYMENT_PROCESS.md and HEALTH_CHECKS.md for your repo's production deployment process.
do-integration-audit
Deep audit of a named feature's integration health: orphan code, dead wiring, missing tests, config gaps. User-invoked only.
do-presentation
Use when creating a presentation about a feature, concept, or system. Researches the topic, structures content for accessibility, generates diagrams, and exports polished Marp slides styled to the repo's design system. Triggered by 'make a presentation', 'create slides', 'do-presentation', or 'explain this as a deck'.
do-skills-audit
Audit all Claude Code skills for compliance with canonical template standards. Use when checking skill quality, validating skill structure, linting SKILL.md files, verifying frontmatter, or scanning for skill issues. Runs deterministic validation rules and best practices sync against latest Anthropic docs by default.
mermaid-render
Render Mermaid .mmd diagrams as hand-drawn style PNG exports via Excalidraw. Use when converting .mmd files to presentation-quality images with a sketch/hand-drawn aesthetic. Triggered by 'render this diagram', 'export mermaid as PNG', 'convert mmd to image', or 'excalidraw export'. Also handles .excalidraw → PNG directly.
skillify
Capture this session's repeatable process into a reusable skill. Call at end of a process you want to automate.
do-voice-recording
Turn text into a spoken-audio file (OGG/Opus) from any project or directory. Kokoro local voice with OpenAI tts-1 cloud fallback. The canonical text-to-speech step — other skills (/do-presentation, /do-debrief) defer to this for synthesis. 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', e.g. recording narration after building a presentation.
computer-use
Use when driving native macOS apps -- click buttons, type text, screenshot windows -- without moving the user's cursor or stealing focus. Triggered by requests to control desktop apps (Slack, Notes, Xcode, Telegram Desktop, VS Code), automate macOS workflows, or take screenshots of native windows. macOS-only.
deepen
Use when adding structured logging, metrics, and tracing to a specified module. Triggered by 'deepen this module', 'add logging to', 'instrument this', 'make this debuggable', or any request to improve a module's observability at the code level.
do-build
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.
do-deploy
Use when deploying merged changes to production across all bridge machines. Triggered by 'deploy to prod', 'ship it', 'push to prod', or 'do-deploy'. Not part of the SDLC pipeline -- merge already handles the local dev environment.
do-design-audit
Audit an existing web UI against premium design criteria. Screenshots pages and evaluates visual hierarchy, typography, color, spacing, consistency, and more. Use when the user wants to evaluate design quality, audit a UI, or says 'review this design', 'check the UI', 'audit this page', 'scan the interface', or provides a URL for design feedback.
do-design-system
Use when translating a moodboard (Cosmos, Pinterest, Are.na, image folder) into additive edits to a design system — tokens, components, charter, downstream CSS. Also use when organizing design files to the canonical docs/designs/ structure (design-system.pen, charter.md, gap-audit.md, inspiration/, product/). Triggered by 'apply this moodboard', 'tighten the design system', 'theme pass', 'design system pass', 'organize design files', or a moodboard URL with a design-system ask.
do-discover-paths
Discover happy paths on a target site using BYOB MCP, producing structured trace JSON for deterministic test generation.
do-investigation-issue
Use when posting a GitHub investigation issue for an unverified finding, potential gap, or anomaly that needs root-cause analysis before any action is taken. Also use when an audit skill surfaces something suspicious, research reveals a possible gap in the current implementation, or an observed behavior is unexpected but unconfirmed. Issues are labeled 'investigation' only — never 'bug' unless the defect is already confirmed.
do-issue
Use when creating a new GitHub issue. Ensures issues are self-contained, define domain terms, and provide enough context for the /do-plan skill to produce a quality plan. Triggered by 'create an issue', 'file an issue', or automatically by /sdlc at Step 1.
do-oop-audit
Audit Python classes and OOP code for structural anti-patterns, naming inconsistencies, and data modeling issues. Use when reviewing class design, checking model health, validating object boundaries, or after refactoring. Also triggered by 'check my classes', 'review the data model', 'are there OOP problems', 'scan for design issues', 'lint class structure', 'audit models', 'validate OOP', or 'review object hierarchy'.
do-patch
Apply a targeted fix to failing tests or review blockers. Use when the user says 'patch this', 'fix the failures', 'fix the blockers', or 'do-patch'. Also called automatically by do-build at test-fail and review-blocker lifecycle steps.
do-plan-critique
Use when reviewing a plan before build. Spawns parallel war-room critics (Skeptic, Operator, Archaeologist, Adversary, Simplifier, User) plus automated structural checks. Triggered by 'critique this plan', 'review the plan', 'war room', or 'do-plan-critique'.
do-plan
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.
do-pr-review
Use when reviewing a pull request. Analyzes code changes, validates against plan requirements, and captures visual proof via screenshots. Triggered by 'review this PR', 'check the pull request', 'do a PR review', or a PR URL.
do-test
Use when running the test suite. Parses arguments, dispatches test runners (potentially in parallel), and aggregates results. Triggered by 'run tests', 'test this', or any request about testing.
grill-me
Use when probing assumptions and surfacing gaps via Socratic interrogation. Triggered by 'grill me', 'challenge my thinking', 'probe this', 'stress test this idea', or any request to pressure-test a plan, belief, or understanding.
new-audit-skill
Use when creating a new audit skill for validating code, configuration, or documentation quality. Also use when the user says 'create an audit', 'new audit skill', 'add an audit', 'make an audit for', or 'I want to check X for problems'. Generates audit skills that follow established patterns from the 8 existing audit skills in this repo. Make sure to use this skill whenever someone wants systematic validation of any codebase artifact.
observability
Use when wiring up dashboards, alerts, and health checks for a module or service. Triggered by 'add observability to', 'set up monitoring for', 'create a health check for', 'wire up alerts', 'observability pass', or any request to build external monitoring surfaces.
ontologies
Use when building or updating a project's domain vocabulary. Triggered by 'ontologies', 'build vocabulary', 'name things', 'define terms', 'ONTOLOGIES.md', or any request to establish precise domain language for a codebase.
prime
Use when onboarding to the Valor AI codebase, understanding the system architecture, or when the user asks 'how does this work'. Comprehensive codebase orientation guide.
pthread
Use when facing multiple independent tasks that can run concurrently. Scales compute by spawning multiple agents in parallel. Triggered by 'parallelize', 'run these in parallel', or when independent subtasks are detected.
sdlc
Single-stage router for development work. Assesses current state, dispatches ONE sub-skill, then returns. The PM session handles pipeline progression.
setup
Use when configuring a new machine to run the Valor Telegram bridge. Installs all dependencies, authentication, and service startup. Triggered by 'setup', 'configure this machine', or 'new machine setup'.
tdd
Use when building with test-driven development discipline. Triggered by 'tdd this', 'write tests first', 'red-green-refactor', 'test-driven', or any request to implement a feature using the TDD cycle.
weekly-review
Use when the user asks for a weekly review, engineering review, team review, or summary of recent commits. Also use for bi-weekly, monthly, or sprint reviews ("review the last N days"). Produces a concise, stakeholder-friendly engineering summary organized by category with contributor stats.
zoom-out
Use when course-correcting mid-session or reassessing priorities. Triggered by 'zoom out', 'am I solving the right problem', 'step back', 'reassess', 'am I on track', or any request to check whether current work aligns with real goals.
authenticity-pass
Pre-publish human-signal gate for social media content. Checks that a draft contains specific metrics, real constraints, and genuine opinions before allowing publish. Required by /linkedin and /x-com before any post goes live. Can also be invoked directly on any draft file.
google-workspace
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.
Use when browsing LinkedIn, reading posts, writing comments, checking DMs, or engaging with content. Triggered by requests to comment on LinkedIn, browse feed, interact with posts, or read/reply to LinkedIn messages.
Use when reading or sending email — checking the inbox, searching mail, reading a specific message, drafting or sending a reply. 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.
do-sdlc
Use when supervising a full SDLC pipeline run in a local Claude Code session. Loops the /sdlc router — dispatching each stage to a subagent on the stage-appropriate model (opus/sonnet) — until merge, a blocking guard, or the iteration cap. Triggered by 'do-sdlc', 'run the full pipeline', 'ship this issue end to end', 'supervise the sdlc'.
analyze
Strategic business analysis tool for decisions, ideas, plans, and tradeoffs of any kind. Delivers a structured assessment with recommendation and first action. MANDATORY TRIGGERS: 'analyze this', 'run an analysis', 'strategic analysis', 'do a full analysis', 'business analysis'. STRONG TRIGGERS: 'should we X or Y', 'evaluate this', 'assess this', 'what's the strategic read', 'deep dive on this', 'pressure test this idea', 'give me your full take'. Do NOT trigger on simple factual questions, quick lookups, or casual requests without meaningful stakes.
reclassify
Use when reclassifying a plan's type (bug/feature/chore) during the Planning phase. Triggered when the initial classification was wrong or the scope changed. Only works before plan is approved (status must be Planning).
checking-system-logs
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. Always filter by project name.
do-docs
Use when cascading documentation updates after code changes. Finds every document referencing the changed area and makes targeted surgical updates. Triggered by 'update docs', 'sync the docs', or any request about documentation updates.
frontend-design
Use when creating distinctive, production-grade frontend interfaces with high design quality. Triggered by requests to build web components, pages, artifacts, posters, or applications. Generates creative, polished code that avoids generic AI aesthetics.
pencil-design
Use when designing or iterating on .pen files via the Pencil MCP server (or the headless `pencil` npm CLI). Captures cross-project gotchas — save semantics for new files, schema pitfalls that aren't in the schema text, and the MCP-vs-CLI file-existence distinction. Triggered by '.pen file', 'pencil mcp', 'mcp__pencil__*', 'pencil cli', 'design system pen'. NOT triggered by ordinary frontend / CSS design work — that belongs in `frontend-design` or `do-design-system`.
ebook-ingest
Use this skill when the user wants to find, download, and prepare an ebook for AI agent ingestion (RAG, fine-tuning, or long-context reference). Triggers include: requests to acquire a digital copy of a book the user owns in print, building a personal book corpus for an AI agent, converting EPUB/PDF/MOBI to clean Markdown for LLM consumption, or chunking books for vector stores. Handles search across multiple sources (Gutenberg, Standard Ebooks, Anna's Archive, LibGen, Z-Library, archive.org), format conversion via calibre/pandoc, OCR for scanned PDFs, cleanup, metadata, and chunking. Do NOT use for academic papers (use Sci-Hub/unpaywall), bulk public-domain scraping (hit Gutenberg's API directly), or DRM'd commercial ebooks the user has not purchased.
officecli
Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.
do-merge
Use when merging a pull request that has cleared the SDLC pipeline. Runs the deterministic verify-then-merge gate — confirms the PR is OPEN, mergeable, CI-green, REVIEW-approved, and links its tracking issue — then authorizes and squash-merges. Triggered by 'merge this PR', 'do-merge', or automatically by /sdlc at the MERGE stage.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.