rnwolfe

Run the full forge pipeline end-to-end within this Claude Code session, processing multiple issues autonomously until a stop condition is met

Interactive project bootstrapping — generates CLAUDE.md, VISION.md, CI workflow, forge.toml, and configures GitHub

Poll a PR's CI checks until all pass, any fail, or timeout — then report the result

Pick the next backlog/ready issue, claim it, and prepare a branch — without implementing it

Perform a final review check on a PR and merge it if clean, or report what's blocking

Process all open review comments on a PR: fix addressable issues, reply in-thread, create follow-up issues for deferred items

Pick an issue from the backlog, implement it in a fresh worktree, and open a PR

Generate feature and enhancement ideas through codebase exploration and interactive discussion

Audit codebase for architectural drift, pattern violations, complexity creep, dead code, and test gaps from continuous autonomous development

Audit documentation for accuracy and completeness — checks command refs, landing page, feature pages, and developer docs against the actual codebase

Pick an issue from the backlog, implement it in a fresh worktree, and open a PR

Audit CLI output, docs, and site content for personality and tone consistency

Strategic product ownership — roadmap health checks, spec authoring, and vision-coherence enforcement for mine

Cut a release: analyze unreleased work, propose semver bump, draft CHANGELOG, tag, and push

Audit the autodev pipeline health, recent PR quality, and identify improvement opportunities

Turn a rough idea into a fully structured GitHub issue matching the gold-standard template

Scaffold and maintain a self-hosted Astro Starlight documentation site in the current repository, and wire the repo's agent file (CLAUDE.md / AGENTS.md / etc.) to keep docs fresh alongside commits and releases. Use when the user wants to "add docs", "set up a docs site", "scaffold Starlight", "create a documentation site", "add llms.txt", make docs AI-readable, or establish a docs-as-code workflow. Inspects the repo first (package manager, monorepo layout, existing docs, CI, agent files), decides non-bloating placement, applies design tokens, sets up easy LAN/self-host serving, and adds a docs freshness directive to the agent file. Builds the docs *shell* (site, tokens, llms.txt, CI, freshness wiring) with stub pages; pair it with the `harvest-docs` skill to populate the pages with comprehensive, code-accurate content.

Give a long-running, self-hosted tool its own lifecycle CLI — a single `<tool>` binary with install / upgrade / doctor / status / logs / restart / uninstall (and optional prune) subcommands, a managed service unit (systemd user unit on Linux, launchd plist on macOS), channel-based self-upgrade (stable = highest release tag, nightly/dev = branch tip), and a `/health`-probe that verifies the running version before an upgrade is called done. Use when the operator says "give this tool an install/upgrade CLI", "add self-upgrade", "channel-based upgrade command", "make it self-managing", "a factory-style CLI for this service", "born with the maintenance surface", or is about to hand-port a service-management CLI from another project. It implants the operational lifecycle surface; pair it with a release/versioning flow (tags + changelog) for the other half.

Operating mode for long-running autonomous sessions where the user is unavailable (overnight, traveling, AFK for hours) and cannot answer clarifying questions. Shifts Claude from "ask when unsure" to "decide, document, and keep moving" while preserving hard guardrails on irrecoverable actions. Use this skill ONLY when the user explicitly invokes it — phrases like "run overnight", "I'm going to bed, keep working on X", "autonomous run", "no need to check in until morning", "/overnight", or any direct request to operate without check-ins. Do NOT trigger on normal long tasks where the user is still at the keyboard. The user has explicitly accepted the cost of any recoverable mistakes; in exchange, expect Claude to ground decisions rigorously, log them auditably, and produce a morning report so the work is reviewable.

Cut a release for a Bun/Vite/tRPC-style project — propose a semver bump from conventional commits, write a Keep-a-Changelog entry, bump version(s) in lockstep, annotated-tag, and hand the push to the operator. Also the canonical reference for wiring the runtime "what's new" loop (changelog parser → API → version-gated modal) and a channel-based upgrade CLI into a new project. Use when asked to "cut a release", "tag a version", "bump the version", "update the changelog", "do a release", or to add release-notes / what's-new / self-upgrade machinery to an app.

Run a full strategic leverage audit on any repository and produce an executable improvement plan across four lenses — technical innovation, defensibility/moat, profitability (or open-source health metrics), and product/adoption metrics. Use this skill whenever the user points Claude at a repo and asks to "improve", "audit", "grow", "harden the moat of", "make more profitable", "make more adoptable", "find leverage in", or "level up" a project — or asks what to build next, how to position a project, how to get more stars/users/revenue, or whether a project is worth continuing. Also use it for pre-open-sourcing readiness checks and build-in-public preparation. Designed for frontier-model (Fable 5 class) deep-context analysis; do not answer these questions ad hoc when this skill is available.

Search Google Flights for fares and routes (read-only, no API key). Bootstraps the gfly binary if it isn't installed, then drives it (read-only).

Read Instagram Threads — posts, replies, mentions, search (posting is gated). Bootstraps the knit binary if it isn't installed, then drives it (read-only).

Read-only Cisco Nexus (NX-OS) state as clean JSON, with fleet fan-out. Bootstraps the nxstate binary if it isn't installed, then drives it (read-only).

Search Amazon for products, prices, and availability for an agent (read-only). Bootstraps the rivr binary if it isn't installed, then drives it (read-only).

Search the Virginia ABC catalog and live per-store stock (read-only). Bootstraps the vabc binary if it isn't installed, then drives it (read-only).

Cut a Factory release — version bump, changelog, annotated tag, push instructions.

Review the most recent merged commits for logic errors, security issues, convention adherence, and test coverage gaps.

Check project doctrine (VISION.md, CLAUDE.md, README.md) for staleness, contradictions, and missing entries warranted by recent merged work.

Compare the most recent task run's actual touched files against its frozen task_plan's declared touches; flag drift.

Score every open task in .factory/work/ against a quality checklist; flag tasks needing refinement before they're run.

Audit README and STATUS against shipped code — surface documentation drift, then apply targeted edits on approval

Cut a release: analyze unreleased work, propose semver bump, draft CHANGELOG, tag, and push

Clean up stale git state — remove merged branches (local and remote), prune remote tracking refs, remove stale worktrees, and land on a clean main. Use this whenever the repo feels messy after forge-loop sessions, before starting new work, or when asked to tidy/clean up branches or worktrees. Also triggers for: 'what local work is out of sync?', 'I have stale branches', 'clean up after merging', 'remove old worktrees'.

Guide the creation of a high-quality engram enrichment plugin — js-module or executable transport — with correct manifest, auth, scope, vocab, aliases, cursor, and tests

Run the full forge pipeline end-to-end within this Claude Code session, processing multiple issues autonomously until a stop condition is met

Run the full forge pipeline end-to-end within this Claude Code session, processing multiple issues autonomously until a stop condition is met

Process all open review comments on a PR: fix addressable issues, reply in-thread, create follow-up issues for deferred items

Interactive project bootstrapping — generates CLAUDE.md, VISION.md, CI workflow, forge.toml, and configures GitHub

Drive ufi, an agent-friendly CLI for Ubiquiti UniFi Network via the official local Integration API. Read-only by default; mutations require --allow-mutations.

Drive gfly, an agent-first, read-only CLI for searching Google Flights — itineraries, price calendar, multi-city, and IATA lookup. JSON-by-default with a stable, versioned schema.

Gather read-only state from Cisco Nexus (NX-OS) switches — show commands, interface/VLAN/route/BGP/MAC/ARP state, logging, environment. READ-ONLY by design; it cannot configure a switch. Use for "check switch state", "show interface/bgp/route on <switch>", NX-OS troubleshooting and inventory.

Search Virginia ABC products and check live store inventory from the command line.

Drive rivr, an agent-friendly CLI for Amazon Shopping search and data retrieval. Read-only; pluggable provider backend; untrusted text is fenced.