Reference for writing a Workflow tool script (script API and gotchas, agent() options, pipeline() vs parallel(), verification and convergence patterns, resume, worked example). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.

Turn a fuzzy intention into a /goal objective the Goal verifier can actually judge - one outcome, numbered binary "Done when" checks that leave evidence in the transcript, guardrails, a budget, and a block protocol. Use when the user wants to set or define a goal, asks whether a goal is good enough, or says "keep going until X". Usage - /goal-draft <what you want done>, or /goal-draft <existing goal> to tighten it. This skill only writes the objective; it never starts the work.

Control local desktop applications through Computer Use for tasks that require reading or operating app UI. Prefer purpose-built connectors, APIs, or CLIs when available.

Review a GitLab merge request for a Factory work item using brokered source-control tools

Re-review a GitLab merge request after new commits and reconcile the previous review

Re-review a pull request after a push — reconcile the previous review against the new commits, look for new defects the push introduced, then a fresh pass over the whole PR, and finish with a verdict on the PR

Mark a GitHub issue as done and update its status labels

Find worthwhile FastMCP issues to work on in a backlog or release window, verify promising candidates, and present concrete picks with existing PR links.

Assess a FastMCP pull request for justified behavior, compatibility, and correctness, then follow CI and review feedback to a revision-specific verdict. Use for draft or ready PRs and self-review before publication.

Review an incoming external issue (and any gated-closed PR behind it) and decide whether to assign the contributor or decline. Use when the maintainer says "look at this issue", "review issue

Cut a FastMCP release end to end. Use when the maintainer says "cut a release", "prep a patch", "ship 4.x.y", or asks what a release would contain. Covers the notes preview, the title pun, the docs changelog PR that must land before the tag, the tag itself, the publish fan-out, and verifying gofastmcp.com actually deployed.

Carry a selected FastMCP bug from reproduction through a scoped fix, compatibility review, validation, and a monitored pull request.

Where new brain files go. Decision protocol for filing brain pages by primary subject, not by format or source. Reference for all brain-writing skills.

Compress an agent's routing file (RESOLVER.md or AGENTS.md) by converting granular skill-per-row tables into functional-area dispatchers. Each area lists sub-skills in a "(dispatcher for: ...)" clause. The LLM reads one area entry and routes to the correct sub-skill. Proven via held-out A/B eval: dispatcher pattern outperforms naive pipe-table compression.

Deduplicate and synthesize raw concept stubs into a tiered intellectual map (T1 Canon to T4 Riff), tracing idea evolution across sources over time. Transforms thousands of raw concept pages into a curated intellectual fingerprint. Includes a reversible curation cull pass (Phase 5) with hard keep/delete/merge verdicts, substance gates, grounding labels, cluster budgets, and merge-with-backlinks salience promotion.

Compile daily briefing with meeting context, active deals, and citation tracking

Feed and whole-publication ingestion: turn an entire blog, newsletter, or RSS/Atom archive into brain source pages. Covers feed discovery, pagination walking, normalization to a common article shape, canonical-URL dedup, idempotent re-runs, 429 pacing, and empty-husk repair. This is the PUBLICATION-scope skill — a single article URL routes to idea-ingest instead. Per-article enrichment hands off to the brain-ingest-gate skill; public posts only (gated content is skipped, never worked around).

Gate on identity questions to the user. Before any "who is X?" (or role / relationship question) reaches the user, exhaust the brain's lookup chain: think → search + page read → mounted sources → timeline/graph → web. If escalation survives the chain, ask WITH a hypothesis, never a bare unknown. Also owns the no-placeholders-at-ingest rule: pages created during bulk ingestion get their relationship/role resolved immediately.

Open the GBrain owner dashboard, manage MCP clients and permissions, or connect a native OAuth harness. Distinguishes owner administration from ordinary MCP access.

Detect which gbrain engine is in use (PGLite vs Postgres), prefer Postgres for agent-harness installs, install/provision Postgres (Supabase discovery via SUPABASE_ACCESS_TOKEN, local Postgres, opt-in Docker), and move an existing PGLite brain with the guarded engine migration. Detection is one engine-free command; the install ladder is one flag.