Skills Library

Review changes and handle CodeRabbit/Greptile/Bugbot/GitHub feedback. Triggers: review, comments, security.

Full PR loop plus the agent-identity signature on GitHub writes. Triggers: create PR, finish work, post PR comment, sign a comment, golem-id, Co-Authored-By trailer.

Life admin for health, habits, jobs, clients, contracts, and scheduling. Triggers: daily plan, wearable data, outreach.

Figma-to-code pixel verification loop. Triggers: Figma designs, pixel perfect, design verification.

Manage 1Password op secrets/env. Triggers: API keys, .env, op auth.

Control cmux panes, splits, browser/sidebar, messages. Triggers: cmux, split panes, terminal reads. NOT shell.

Spawn AI workers in cmux via MCP/repoGolem. Triggers: visible workers, terminal agents, orchestration, audits.

Setup wizard + skill lister. Triggers: setup, wizard, set up/install golems, new machine, list/search/show skills.

BrainLayer retrieval benchmark: recall@K, MRR, p@5, placebo. Triggers: agada bench, BL PR, embedder swap.

Agent web testing: attach to shared Chrome Beta over CDP. Never launch worker browsers or drive Helium.

Route work to Cursor/Gemini/Codex/Claude; pick the fan-out engine. Triggers: delegate, who gathers, gemini gatherer, worker assignment, routing, Codex model/effort, subagents, /multitask, parallel agents, fan out, in parallel, batch classify/audit. NOT for one edit or dependent steps.

Pre-R0 diff of implementation vs SOTA research. Triggers: before R0, architectural audit. NOT per-PR review.

Build audio narration dashboards. Triggers: STT-after-TTS exact word-timing, real word-click-seek read-along dashboard, AfterCode workflow, publish-to-tailnet delivery.

Fallback for failed brain_store: write memory to docs.local for replay. Triggers: null chunk, DB busy, close.

Write grounded Claude Desktop/Web research prompts. Triggers: research prompt, Claude Desktop, MCP-aware.

Verified headless Codex worktree fan-out. Triggers: codex-workflows, headless Codex, Codex parallel. NOT for healthy cmux single-worker tasks.

Use native Monitor for addressed collab mail, report DONE markers and installed-version watches; use the packaged detached fallback on Codex seats. NOT for file-integrity auditing.

Create app/Remotion demos. Triggers: demo video, walkthrough, showcase.

Audit code for duplicated ownership, uncoordinated implementations, multiple writers, split lifecycle controls, live-copy drift, or missing single sources of truth. NOT for generic lint, style, security, or architectural research audits.

Run Cursor-workflow gather/recon via AutoCursor primitives. Triggers: cursor-workflow, autocursor gather, cursor gather.

Security audit for MCP, TS, Swift, shell, launchd plists. Triggers: security, vulnerability, hardening, traversal, injection, shell hardening, bash security, launchd plist, LaunchAgents, plist secret, raw API key in plist, secrets hygiene, op:// reference.

Verify deployed infra after merge/restart. Triggers: PR merged, deployed, daemon/MCP restart, live probe.

Brain Drive filing, archival, and the docs.local lifecycle. Triggers: Drive/Brain Drive upload, archive this, post-digest archival, docs.local cleanup, docs.local artifacts, rollup, folders, prompts/results, audits, plans, transcripts, dashboards. NOT for Gemini Drive/web research.

Validate Expo iOS/Android sync before first EAS build. Triggers: eas build, prebuild, credentials.

Health checks for MCP, BrainLayer, skills, friction, and AI context hygiene vs ~/.golems/config.yaml. Triggers: health check, whats broken, MCP/BL status, context check/bloat, MCP/skill/hook hygiene.

Explain a new topic fast to a smart adult. Triggers: /eli5 [topic], eli5 this, break this down for me, I know nothing about X catch me up.

'done/green/fixed' needs a live probe. Triggers: completion claim, pr-loop completion, deploy/render/dashboard 'done'.

Quiet sprint close: stop monitors, send final dashboard/message. Triggers: fleet wrap, stand down.

Kill-gate: at fleet-wrap/stand-down assert cron-count==0. Triggers: fleet wrap, stand down, sprint close, going silent.

Store genuine user corrections. Triggers: no/wrong/stop, I told you, not that, profanity/frustration.

NotebookLM/Gemini research: sources, Deep Research, queries, artifacts. Triggers: Gemini, synthesis.

Safety gate for destructive git/main commits. Triggers: force-push, reset, branch delete, clean, main commit.

Design-tree interview. Triggers: grill me, interview my plan, stress-test this design. NOT for implementation or one-question-at-a-time interviews.

Create static HTML dashboards from template. Triggers: dashboard, status, digest, compare, what changed.

Mechanical confirmation for destructive Git and repository administration commands.

Lint a macOS onboarding runbook for privilege-correctness. Triggers: install runbook, fresh-Mac onboarding, brew cask runbook, admin/Standard user split, happy-camper onboarding.

PreToolUse guard: unpinned Fable-seat spawns and sub-apex Fable targets block. Triggers: model pin, Fable seat, spawn.

Orchestrate multi-agent sprints/cmux/ecosystem work. Triggers: sprint, spawn, status, catch me up, delegate.

Plan councils, anonymized candidate ranking, bulk judge fleets, assumption checks. Triggers: council, review my plan, score the plan, judge the plan, validate plan, check assumptions, cross-family judges, lift round, exact-head review, conditional GO, MUST_FIX, peer ranking, anonymized review, adversarial verification, score multiple candidates, judge fleet, bulk judge, R3 verdicts, kg-judge, RT gate, evidence_degraded. NOT for one-off PR/code review.

Kill-gate: QA PASS/FAIL/INCONCLUSIVE + qa-report.md. Triggers: QA verdict, QA done/complete, pre-merge QA, false-FAIL.

Video QA/extraction for screen, local video, YouTube. Triggers: narrated QA, bugs, QA checklist, video gems.

Launch repoGolem agents in any repo. Triggers: spawn agent, launcher, brainlayerClaude, flags -s/-c/-w/--worker.

Refresh local research context and the Drive grounding corpus. Triggers: stale context, R-number.

PreToolUse guard: reviewer spawns denied until the implementer is done. Triggers: reviewer order, reviewer spawn.

Write handoff, spawn successor, answer grill, verify orientation. Triggers: hand off, context high.

Create/edit/audit/eval golem skills. Triggers: create skill, skill eval, live eval, JSONL mining.

Use Google Stitch for design-to-code prototypes/tokens, then implement. Triggers: Stitch, screen prototypes.

TDD edit-limit hook (advisory). Triggers: tdd guard, test-first hook, untested edits, snapshot/golden carve-out.

Guard denying durable writes to /tmp, /private/tmp, /var/folders, $TMPDIR; enforces <repo>/.worktrees/<name>. Triggers: tmp guard, TMP-BLOCK deny, WORKTREE-CONVENTION deny, bypass ledger. NOT for storage policy.

Cut AI tells while keeping every receipt, number, path, and hedge intact. Triggers: unslop, cut the slop, wall of text, too verbose, rambly, make this readable. NOT for delivery cadence (see i-have-adhd), channel choice, or artifact length governance.

Orchestrator convergence: mine JSONLs, cite findings, route actions. Triggers: weave, run weave.

Compare Claude/Codex/Cursor/Wispr changelogs to local setup. Triggers: whats new, changelog, updates.

Push dependency bugs upstream. Triggers: dependency bug, workaround, monkey-patch, fork/fix. NOT app bugs.

Scaffold multi-phase plans with async agents. Triggers: large feature, multi-PR refactor, parallel cmux.

Evidence gate + surface sweep: read, run and verify before claims; account for every surface a change touches. Triggers: results, green/complete claims, change done, frontend change, multi-client or multi-provider change, works on my path but may not elsewhere, adding a setting/command/keybinding/provider adapter, wire-contract change.

Audit unfamiliar repos: architecture, features, config gaps. Triggers: unfamiliar repo audit. NOT catchup.