eval-designer
Use this skill when building evaluation frameworks to measure LLM quality, safety, accuracy, or alignment including test suites, human eval rubrics, automated evals, and metrics design. Not for training or fine-tuning models. Not for dataset curation or benchmark comparison across publicly available models.
email-drafter
Use this skill when drafting professional or personal emails—cold outreach, follow-ups, internal memos, client communication, or any message that needs to be clear and effective. Trigger phrases: ''write an email to'', ''draft a follow-up'', ''help me email''. Do NOT use for mass marketing email campaigns (use copywriter skill) or legal/formal notices requiring specific language.
doc-quality-review
Assess documentation quality across readability, consistency, audience fit, and prose clarity. Produces a scored review with actionable findings. This skill should be used before releases, during doc reviews, or when documentation feels unclear or inconsistent.
agent-loops
Complete operational workflow for implementer agents (Codex, Gemini, etc.) making code changes and writing tests. Drives all work through atomic commits — each loop operates on the smallest complete, reviewable change. Defines the Code Change Loop, Test Writing Loop, Lint Gate, and Issue Filing process with circuit breakers, severity levels, and escalation rules. Requires `cortex git commit` for all commits. Includes bundled provider-aware review scripts that keep same-model shell-outs as the last resort, plus a fresh-context Codex fallback for code review and test audit. Use this skill when starting any implementation task.
knowledge-stack
Use this skill whenever working inside any of Nick's repos (under ~/Developer/) or whenever a conversation touches Nick's durable cross-cutting work — Atlas Crew product strategy/brand/planning, the Unanet job, job search, interviews, tax amendment, foreclosure/tenant situation, strategic positioning. Maps Nick's three Basic Memory projects (products, work, main) and the per-repo dev trackers, and says which layer owns which kind of question. Consult before reasoning from stored memory summaries about repo architecture, product decisions, active priorities, or ongoing personal/career state — stored memory is lossy; the trackers and the Basic Memory projects are the real artifacts and should be consulted first.
justfile-author
Use this skill when authoring or refactoring a justfile (and matching Makefile wrapper) for one of Nick's projects. Triggers when the user asks to "create a justfile", "add a justfile to this project", "set up just for…", "wire up tmux services", "scaffold the task runner", or when working in a repo that lacks a justfile but obviously needs one. Produces a justfile using zsh syntax with the standard svc-* tmux service family, the canonical build/lint/dev/test recipes, a thin Makefile passthrough wrapper that auto-installs just, and per-service tx-start.sh helpers. Do NOT use for editing existing third-party justfiles or non-Nick projects unless the user explicitly opts in.
brand-library-architect
Build a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
blog-post
Use this skill when writing blog posts, articles, or long-form web content—from quick how-to guides to in-depth opinion pieces. Trigger phrases: ''write a blog post about'', ''draft an article on'', ''create a post for my blog''. Do NOT use for academic papers, news reporting, or content requiring real-time facts.
model-comparator
Use this skill when comparing AI or LLM models on benchmarks, capability, cost, latency, context window, or task-specific fit to help teams select the right model for their use case and budget. Not for training or fine-tuning models. Not for building eval frameworks from scratch.
atomic-commits
>-
html-seo-review
Audit static HTML files for on-page SEO, content quality, easy-win performance signals, and crawlability. This skill should be used when the user asks to review, audit, or check the SEO of one or more static HTML files — e.g., "review the HTML for SEO issues", "audit this landing page", "check SEO on these pages before I publish". Static HTML only — does not cover Jekyll/Hugo/Astro/Next.js source, off-page factors, or live-rendered Core Web Vitals.
atlas-crew-tasks
Use when filing, updating, sequencing, or querying tasks in any atlas-crew repo (Facet + the Atlas Crew Security repos: Apparatus, Chimera, Crucible, Synapse, Bridge). These repos track work in GitHub Issues on Projects v2 boards, NOT backlog.md. Covers the two boards, the Type/Area/Status field model, cross-repo Initiative grouping, gh seq execution ordering, and the non-obvious gh/GraphQL mechanics for setting issue types and project fields. Trigger on: file an issue, create a task, set priority/type/area/status, add to board, what should I work on next, execution order, sequencing, blocked-by, milestone, where does this task go.
mapping-suite
User-triggered orchestrator that walks the user through running multiple sibling mapping/audit/doc skills against a shared scope, then assembles their outputs into one navigable artifact. Coaches rather than auto-runs — at each step the orchestrator presents the next sibling skill, recommended scope inheritance, and approval gate; the user invokes the sibling and confirms before moving on. Resolves the prior arch-analysis lookup once at suite start so every sibling skill inherits the same scope. Records each run's output path in a suite manifest. Produces a combined navigation HTML that links to each sibling's standalone HTML for one-stop sharing. Ships two named recipes — "release-driver onboarding" (for tooling that drives releases) and "deployed-system onboarding" (for systems that get deployed) — and supports custom plans. Trigger on "run our mapping suite," "do a complete onboarding," "build the combined report," "I need to onboard to system X," "give me the full picture of this codebase," or when the user names two-or-more sibling analyses to coordinate. Not for running a single sibling skill in isolation (invoke it directly), and not for bypassing approval gates (this skill coaches, never autoruns).
architectural-analysis
User-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
frontend-design
Use this skill when specifying, designing, or documenting UI components, layouts, and design systems for frontend implementation. Trigger phrases: ''design this UI component'', ''create a responsive layout'', ''spec the CSS for'', ''design system for''. Do NOT use for backend development, server-side logic, data engineering, or writing server code.
market-researcher
Use this skill when sizing a market, analyzing competitors, designing customer surveys, segmenting audiences, or synthesizing research into market insights. Trigger phrases: ''size the market for'', ''analyze our competitors'', ''who is our target customer'', ''design a survey to understand'', ''TAM/SAM/SOM for''. Not for building financial models, writing pitch decks, or conducting UX usability research.
fact-checker
Use this skill when verifying factual claims, checking accuracy of statements, or assessing the credibility of information. Trigger phrases: ''fact-check this'', ''is this true'', ''verify this claim'', ''check if this is accurate''. Do NOT use for subjective opinions, legal or medical advice, or claims requiring real-time data or breaking news.
ai-tells-scan
Use when writing tasks produce prose artifacts (READMEs, docs, PR text, tutorials, guides, posts, release notes) and need a fast surface scan for AI tells. Auto-engages on prose writing tasks; checks banned punctuation, stock vocabulary, and mechanical patterns. For the structural judgment pass on rhythm and rhetorical reflexes, use ai-tells-review. Not a replacement for voice skills like nick-voice; this removes machine fingerprints, it does not add a target voice.
ai-tells-review
Use when public prose still sounds machine-written after ai-tells-scan. Complements ai-tells-scan's mechanical pass with structural judgment: rhythm, hedging, rhetorical reflexes, and performative emphasis. Trigger on 'review for AI tells,' 'does this read AI,' 'strip the AI smell,' or 'make this less AI.'
varlock
Secure environment variable management with Varlock. Use when handling secrets, API keys, credentials, or any sensitive configuration. Ensures secrets are never exposed in terminals, logs, traces, or Claude's context. Trigger phrases include "environment variables", "secrets", ".env", "API key", "credentials", "sensitive", "Varlock".
text_summarizer
Summarizes long text into key bullet points
hello_world
A simple skill that greets the user
stackit
Shared guidance for Stackit stacked-branch workflows. Use when the request mentions stacks, stacking, stacked PRs, or Stackit-specific operations and needs general Stackit policy, workflow safety rules, or a stack health check.
improve
Analyze changes in the current stack and provide actionable improvement suggestions using parallel multi-agent analysis. Reviews bugs, simplification opportunities, performance, test coverage, documentation, security, and UX. Keywords improve, code review, analysis, bugs, performance, security.
optimize-tests
Make the test suite faster without losing coverage. A periodic, coverage-guarded cleanup pass that finds slow/redundant tests, applies free structural speedups (parallel, in-process, drop remote), and consolidates similar tests (table-driven merges, combined asserts) — verifying after every change that no covered line was lost. Keywords test speed, slow tests, test runtime, test cleanup, consolidate tests, parallel tests, combine asserts, coverage-safe, maximize test value.
pre-release-check
Decide whether it's safe to cut a new release. Auto-detects the last release tag, gathers everything merged since, runs a build/test health gate, and fans out parallel review agents to hunt for release blockers — regressions, half-finished work, risky edge cases, breaking changes, missing tests, and release-readiness gaps. Produces a GO / NO-GO verdict with categorized blockers. Keywords pre-release, release blockers, go/no-go, release readiness, ship check, regression review.
stack-ship
Evaluate shippable stacks, review their changes, check for merge conflicts, and produce a smart ship plan. Uses parallel multi-agent review and conflict analysis to determine what to ship, in what groupings, and what to hold. Keywords ship, merge, plan, stacks, PRs, conflicts.
create-release
Draft and publish a new GitHub release for stackit. Compares main against the latest release tag, generates release notes in the established format (Highlights, Features, Fixes, Performance, Refactors, Docs, Chore), pushes the tag (triggers goreleaser to build assets), then overwrites the release body with the curated notes. Keywords release, tag, changelog, ship.
pre-release-check
Decide whether it's safe to cut a new release. Auto-detects the last release tag, gathers everything merged since, runs a build/test health gate, and fans out parallel review agents to hunt for release blockers — regressions, half-finished work, risky edge cases, breaking changes, missing tests, and release-readiness gaps. Produces a GO / NO-GO verdict with categorized blockers. Keywords pre-release, release blockers, go/no-go, release readiness, ship check, regression review.
stackit
Shared guidance for Stackit stacked-branch workflows. Use when the request mentions stacks, stacking, stacked PRs, or Stackit-specific operations and needs general Stackit policy, workflow safety rules, or a stack health check.
create-release
Draft and publish a new GitHub release for stackit. Compares main against the latest release tag, generates release notes in the established format (Highlights, Features, Fixes, Performance, Refactors, Docs, Chore), pushes the tag (triggers goreleaser to build assets), then overwrites the release body with the curated notes. Keywords release, tag, changelog, ship.
optimize-tests
Make the test suite faster without losing coverage. A periodic, coverage-guarded cleanup pass that finds slow/redundant tests, applies free structural speedups (parallel, in-process, drop remote), and consolidates similar tests (table-driven merges, combined asserts) — verifying after every change that no covered line was lost. Keywords test speed, slow tests, test runtime, test cleanup, consolidate tests, parallel tests, combine asserts, coverage-safe, maximize test value.
stack-ship
Evaluate shippable stacks, review their changes, check for merge conflicts, and produce a smart ship plan. Uses parallel multi-agent review and conflict analysis to determine what to ship, in what groupings, and what to hold. Keywords ship, merge, plan, stacks, PRs, conflicts.
improve
Analyze changes in the current stack and provide actionable improvement suggestions using parallel multi-agent analysis. Reviews bugs, simplification opportunities, performance, test coverage, documentation, security, and UX. Keywords improve, code review, analysis, bugs, performance, security.
citation-verifier
|
faf-expert
Expert in the .faf format (Persistent Project Context for AI) and the faf-cli toolkit. Use when working with .faf files, scoring AI-readiness, syncing project context to CLAUDE.md, or discussing the Foundational Context Layer (FCL) doctrine. IANA-registered (application/vnd.faf+yaml). Anthropic-listed as "Persistent Project Context Server" (PR #2759, merged Oct 17 2025). Current CLI: v6.6.0 — The Trophy Edition.
hook-writer
Expert assistant for authoring hook scripts. Creates Python hooks with correct JSON output schema, validates against PreToolUse/PostToolUse/UserPromptSubmit formats, and applies fail-open principles. Triggers on keywords: writing hooks, creating hooks, hook authoring, pretooluse hook, posttooluse hook, new hook, hook template, hook validation, hook schema
release
Full release workflow including milestone validation, squash, rebase, push, merge to main, and GitHub release creation. Triggers on keywords: release, create release, publish release, tag release
pull-request
Creates comprehensive GitHub Pull Requests with authentication validation and structured documentation. Triggers on keywords: pull request, PR, create PR, open PR
prepare-app
Starts development server for E2E testing. Detects package manager and verifies server startup. Triggers on keywords: prepare app, start server, dev server, start app
ac-tools-web-search
Grounded public web research via the web_search tool. Use for searching documentation, facts, recent web content, or location-aware public results while keeping web access inside the extension-managed search wrapper.
playwright-cli
Browser automation via playwright-cli. Token-efficient alternative to Playwright MCP - uses CLI commands through Bash instead of MCP tool schemas. Supports navigation, interaction, screenshots, video recording, and session management. Triggers on keywords: browser, e2e, playwright, screenshot, navigate, click, type, test browser, visual test
ac-tools-single-file-uv-scripter
Creates self-contained Python scripts with inline PEP 723 metadata for UV. Embeds dependencies directly in script headers for zero-config execution via `uv run`. Triggers on keywords: uv script, single file script, inline dependencies, PEP 723, self-contained python, uv run script, standalone script
ac-tools-improve-agents-md
Generate and update AGENTS.md (CLAUDE.md) for projects using a single template with dynamic per-type tooling injection. Auto-detects project type and renders the appropriate Environment & Tooling section. Triggers on keywords: improve agents, generate agents.md, update agents.md, setup claude.md, bootstrap agents
ac-workflow-mux-roadmap
pi-adapted roadmap coordinator. Uses pimux as the authoritative runtime for roadmap -> ospec -> stage hierarchy while preserving mux semantics.
ac-tools-milestone
Validates backlog section completion, then squashes and tags or identifies gaps. Generates milestone and release notes. Triggers on keywords: milestone, release notes, tag release, validate backlog
ac-tools-setup-voice-mode
Installs and configures VoiceMode MCP for voice interactions in the target client. Triggers on keywords: setup voice, voice mode, install voicemode, configure voice
ac-workflow-mux-subagent
MUX data-plane worker protocol reference for pi. Defines the report, signal, and return-code contract that strict mux coordinators consume.
ac-workflow-mux
pi-adapted mux coordinator. Uses pimux as the authoritative runtime while preserving shared mux foundation semantics.
ac-workflow-product-manager
Decomposes large features into concrete development phases with DAG dependencies. Each phase produces fully functional code. Outputs YAML manifest. Triggers on keywords: decompose feature, phase planning, roadmap breakdown, feature phases, PM decomposition, split feature
Page 811 of 1671 · 83508 results
