outfitter-dev

Patterns for @outfitter/daemon including lifecycle management, IPC communication, health checks, and PID files. Use when building background services, daemons, or when "daemon", "IPC", "health check", "background service", or "@outfitter/daemon" are mentioned.

Creates handlers, CLI commands, MCP tools, and daemon services following Outfitter Dev Kit conventions. Use when adding new components to a project, scaffolding code, or when "create handler", "new command", "add tool", or "daemon service" are mentioned.

Deep patterns for @outfitter/mcp including tool registration, Zod schemas, resources, and server configuration. Use when building MCP servers, registering tools, defining resources, or when "MCP server", "MCP tool", "registerTool", or "@outfitter/mcp" are…

Generates patterns, templates, and guides for @outfitter/* packages. Covers transport-agnostic handler systems, Result types, error taxonomy, and package APIs. Use when working with @outfitter/*, Result types, Handler contract, error taxonomy, or when Result,…

Verify Outfitter compliance in a codebase. Scans for anti-patterns (throws, console, hardcoded paths) and produces a severity-ranked compliance report. Use for pre-commit checks, code review, or migration validation.

Submit feedback to the Outfitter team via GitHub issues. Use after discovering bugs, missing features, unclear docs, or improvement opportunities in @outfitter/* packages.

Start with Outfitter — scaffold new projects or adopt patterns in existing codebases. Detects context, scans for adoption candidates, and orchestrates phased conversion.

Troubleshoots Outfitter Dev Kit issues including Result handling, MCP problems, CLI output, exit codes, and logging. Use when debugging stack-specific issues, unexpected errors, wrong output modes, or when "debug Result", "MCP not working", "wrong exit code",…

This skill should be used when the user asks to "complete a branch", "merge to main", "finish my feature", "ship this branch", "integrate to main", "create a PR from GitButler", or when `--complete-branch` flag is mentioned. Guides completion of GitButler…

This skill should be used when coordinating multiple AI agents working concurrently, handling agent handoffs, transferring commits between agents, or when "multi-agent", "concurrent agents", "parallel agents", "agent collaboration", or "parallel execution"…

This skill should be used when creating stacks, dependent branches, or when "stack", "stacked branches", "anchor", "--anchor", "but branch new -a", "create dependent branch", or "break feature into PRs" are mentioned with GitButler. Covers anchor-based…

This skill should be used when the user asks to "create a virtual branch", "assign file to branch", "work on multiple features simultaneously", "organize commits after coding", "use but commands", or mentions GitButler, virtual branches, parallel development…

This skill should be used when checking project status, starting sessions, reviewing activity, or when "sitrep", "status report", or "what's changed" are mentioned.

Design stack-based systems using @outfitter/* packages. Use when planning new projects, choosing packages, designing handler architecture, or when "architecture", "design", "structure", "plan handlers", or "error taxonomy" are mentioned.

Creates GitHub issues for problems discovered while using @outfitter/* packages. Use when finding bugs, missing features, unclear documentation, or improvement opportunities.

Reference for Outfitter Stack patterns including Result types, Handler contract, Error taxonomy, and @outfitter/* package conventions. Use when learning the stack, looking up patterns, understanding packages, or when "Result", "Handler", "error taxonomy",…

Route a Trails question to native Clark and/or Lewis subagents and synthesize their distinct judgments. Use when the user asks the Trails crew, asks Clark or Lewis, requests an architectural or execution second opinion, wants both co-architects to review a…

Embody Clark, Trails' co-architect and architectural conscience. Use when the current agent should be Clark inline for framework architecture, doctrine, vocabulary, ADRs, tenet alignment, long-horizon coherence, pathfinding, assessment, calibration, debriefs,…

Embody Lewis, Trails' co-architect and execution conscience. Use when the current agent should be Lewis inline to turn doctrine into landed work, shape goals and Graphite stacks, coordinate agents, run evidence and review loops, settle releases, debrief…

The working-on-Trails doctrine digest — what governs the framework, the decision tools for framework work, and where truth lives. Use at the start of any session that changes Trails itself (framework code, docs, vocabulary, governance), when orienting a new…

Authoritative architectural ruling on a specific Trails framework question — naming choices, vocabulary compliance, pattern fitness, scope decisions. Consults the constitutional hierarchy, decides, and logs. Use when a definitive call is needed or when 'let…

Big-picture architectural planning and exploration for the Trails framework. Socratic, principle-anchored exploration of features, ADRs, tenets, and horizon planning. Use when planning new capabilities, drafting or revising ADRs, exploring architectural…

Autonomous codebase health scan for vocabulary drift, naming convention violations, structural anti-patterns, documentation staleness, and test health. Produces prioritized findings as Linear issues. Use for health checks, scheduled scans, or after heavy…

Run a Trails Regrade migration loop with dry-run discovery, occurrence judgment, safe apply, verification, ledger capture, and per-cycle resume.

Use the skillset compiler to build, check, inspect, and import source skills or plugins.

Side-by-side draft case owned by SET-555.

Helps maintain the repository.

Prove canonical plugin package placement.

Proofreads written material.

Kitchen-sink skill exercising shared resources and custom resource mappings.

Develops changes with focused tests.

Confirms the Cursor plugin skill projection.

Documentation for AI agents — AGENTS.md, CLAUDE.md, and agent-readable content patterns. Use when creating agent entry points, structuring .claude/ directories, or when "CLAUDE.md", "AGENTS.md", "agent documentation", "machine-readable", or "writing for…

Rigorous quality gate for documentation before merge or publish. Verifies code examples run, links resolve, APIs match implementation, and all sections are complete. Use when auditing docs, reviewing documentation PRs, or when "verify", "quality gate", "docs…

Reviews documentation for voice, style, and structure alignment with Outfitter standards. Use when reviewing docs, checking content quality, or when "review this doc", "voice check", "style review", or "is this ready?" are mentioned.

Project documentation structure and templates — READMEs, API docs, guides, and CLI references. Use when creating documentation, structuring a docs/ directory, writing READMEs, or when "documentation", "README", "API docs", "docs structure", or "guides" are…

Writing craft and style patterns for Outfitter content—sentence rhythm, metaphor usage, enthusiasm calibration, structural moves. Use when drafting blog posts, documentation, announcements, or READMEs, or when "styleguide", "writing style", "voice", or "tone"…

Bun-first development patterns for TypeScript projects. Use when auditing Node.js projects for migration opportunities, starting new projects, evaluating npm dependencies, or reducing package.json bloat. Triggers on mentions of npm, yarn, pnpm, Node.js…

Outfitter's philosophical voice and values. Covers opinionated stance, agent-first design, goal-serving content, and earned confidence. Use when writing Outfitter content, reviewing drafts, establishing tone, or when "voice", "tone", "messaging", "brand", or…

Check and configure outfitter marketplaces and plugins. Use when setting up a new project, checking plugin configuration, or when "setup outfitter", "configure plugins", or "marketplace" are mentioned.

Safely sync navigator's agent-browser fork with upstream vercel-labs/agent-browser, analyze changes, and generate integration documentation

CLI testing guidance and patterns. Loaded by /ops/test/cli command or subagents for comprehensive Navigator CLI testing.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Evaluate upstream changes using Navigator's design frameworks to decide what to adopt, skip, or adapt

MCP testing guidance and patterns. Loaded by /ops/test/mcp command or subagents for comprehensive Navigator MCP server testing.

This skill should be used when the user asks about "wm command", "waymark cli", "wm find", "wm add", "wm edit", "wm rm", "wm fmt", "wm lint", or needs to use waymark tooling. Requires `using-waymarks` skill for syntax fundamentals. Provides comprehensive CLI…

This skill should be used when the user asks about "waymark syntax", "writing waymarks", "::: sigil", "tldr waymarks", "about waymarks", searching waymarks with ripgrep, or mentions waymark grammar, signals, markers, or properties. Provides comprehensive…

Places and maintains waymarks across a codebase, focusing on TLDR coverage and accuracy. Delegates to the waymarker agent for systematic auditing and placement. Use when adding TLDRs to files, auditing waymark coverage, updating stale waymarks, or when "add…

CLI testing guidance and patterns. Loaded by /ops/test/cli command or subagents for comprehensive testing.

Complete Outfitter editorial review workflow. Use when reviewing docs, ADRs, READMEs, release notes, announcements, blog posts, agent guidance, or docs-heavy PRs for voice, style, structure, correctness, and readiness.

Outfitter documentation structure and maintenance guidance. Use when creating or reorganizing Outfitter docs, READMEs, ADRs, guides, API and CLI reference, release notes, or agent-facing documentation.

Outfitter prose craft and terminology. Use when writing or reviewing docs, ADRs, READMEs, release notes, announcements, blog posts, agent prompts, comments, PR descriptions, or issue language for rhythm, clarity, and word choice.

Outfitter writing voice and values. Use when drafting or reviewing Outfitter docs, ADRs, READMEs, release notes, announcements, blog posts, agent guidance, or PR and issue language for stance, audience, and tone.

Parallel CLI stress testing using orchestrated subagents. Spawns specialized agents to test different CLI domains simultaneously, aggregating results into structured reports. Supports discovery mode (agents analyze CLI structure) and directive mode (runbooks…

Guides GitHub PR activity workflows using the Firewatch CLI (fw) and MCP server. Use when triaging PRs, responding to review feedback, querying PR activity, or when the user mentions firewatch, PR reviews, PR comments, or review threads.

Query GitHub PR activity using the Firewatch CLI (fw). Fetch, cache, filter, and act on PR comments, reviews, commits, and CI status. Outputs JSONL for jq composition. Use when checking PR status, finding review comments, querying activity, resolving…

Teaches effective documentation search using the blz CLI tool. Use when searching documentation with blz, looking up APIs, finding code examples, retrieving citations, or when questions mention libraries, frameworks, "how to", or documentation topics. Covers…

Teaches how to discover, validate, and add llms.txt documentation sources to the blz CLI. Use when adding documentation to blz, finding llms.txt or llms-full.txt files, validating sources, refreshing content, or managing the documentation index. Covers source…

Use when operating dispatch, creating or attaching Codex lanes, sending/steering/context-injecting/stopping through dispatch, checking provider capacity, managing triggers, checking daemon status/logs, or configuring the dispatch MCP/plugin surface. Not for…

Use when sending a short, synchronous dispatch-backed direct message to an owned Dispatch lane, asking a bounded question, identifying inter-lane sender/target handles, or teaching a target lane to reply in a lightweight chat style. Long name: dispatch…

Configure Claude Code GitHub Actions workflows effectively. Covers automatic mode detection, event routing, subagent coordination, hooks for quality gates, MCP server integration, reusable workflows, performance optimization, and security best practices for…