Skills Library
58 reusable Claude Code skills. Click any skill for docs, eval status, and install prompt.
Looking for retired tools and foundational loops? Visit Heritage.
Development
Domain
Operations
/1password1Password admin with Etan present (add/rotate/migrate; op = Touch ID). To use a key, load ~/.config/golems/*.env.
/cmuxControl cmux panes, splits, browser/sidebar, messages. Triggers: cmux, split panes, terminal reads. NOT shell.
/cmux-agentscmux visible workers: spawn_agent, boot, deliver, harvest, close panes. NOT generic orchestration.
/golem-installSetup wizard + skill lister. Triggers: setup, wizard, set up/install golems, new machine, list/search/show skills.
Other
/agada-benchBrainLayer gold bench: agada bench, BL PR, embedder/enrichment change, weekly drift, gold build. NOT one-off search.
/agent-browserAgent web testing: attach to shared Chrome Beta over CDP. Never launch worker browsers or drive Helium.
/agent-routingInvoke before any git/gh and before starting another agent: dispatch a worker/reviewer, delegate_task, hand off; who gathers, gemini gatherer, Codex model/effort, /multitask, fan out in parallel. Pick provider/worktree. NOT for one edit or dependent steps.
/architectural-conformance-auditPre-R0 diff of implementation vs SOTA research. Triggers: before R0, architectural audit. NOT per-PR review.
/audio-dashboardBuild audio narration dashboards. Triggers: STT-after-TTS exact word-timing, real word-click-seek read-along dashboard, AfterCode workflow, Lakebed delivery.
/brain-store-fallbackFallback for failed brain_store: write memory to docs.local for replay. Triggers: null chunk, DB busy, close.
/claude-desktop-researchWrite grounded Claude Desktop/Web research prompts. Triggers: research prompt, Claude Desktop, MCP-aware.
/codex-workflowsVerified headless Codex worktree fan-out. Triggers: codex-workflows, headless Codex, Codex parallel. NOT for healthy cmux single-worker tasks.
/collab-monitorNative Monitor for addressed collab mail on Claude/cmux seats, report DONE markers and installed-version watches. Codex/T3 seats: no polling turns; completion notifications wake you; a T3 lead keeps one lead name waiter. NOT for file-integrity auditing.
/content-demo-creationCreate app/Remotion demos. Triggers: demo video, walkthrough, showcase.
/convention-auditAudit 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.
/cursor-workflowsRoute Cursor gather/recon through T3 delegate_task children. Triggers: cursor-workflow, cursor gather, fan out Cursors.
/cyberSecurity 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.
/deploy-verifyVerify deployed infra after merge/restart. Triggers: PR merged, deployed, daemon/MCP restart, live probe.
/drive-filingBrain Drive upload, archive this, post-digest archival, docs.local cleanup/rollup. NOT for Gemini Deep Research/queries.
/eas-prebuild-checkValidate Expo iOS/Android sync before first EAS build. Triggers: eas build, prebuild, credentials.
/ecosystem-healthHealth 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.
/eli5Explain 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.
/false-green-gate'done/green/fixed' needs a live probe. Triggers: completion claim, pr-loop completion, deploy/render/dashboard 'done'.
/fleet-wrapQuiet sprint close: stop monitors, send final dashboard/message. Triggers: fleet wrap, stand down.
/fleet-wrap-gateKill-gate: at fleet-wrap/stand-down assert cron-count==0. Triggers: fleet wrap, stand down, sprint close, going silent.
/frustration-captureStore genuine user corrections. Triggers: no/wrong/stop, I told you, not that, profanity/frustration.
/gemini-researchDeep research, compare options: Gemini Deep Research. NOT for Exa web search, drive-filing or report links.
/git-guardianGate git/shell: force-push, reset/restore, rebase, branch delete, clean, main commit, --no-verify, rm/find/rsync delete.
/grill-meDesign-tree interview. Triggers: grill me, interview my plan, stress-test this design. NOT for implementation or one-question-at-a-time interviews.
/heredoc-guardDeny command substitution in unquoted shell heredocs before execution.
/html-dashboardBuild static HTML dashboard pages: template, verify, tailnet publish. NOT T3 inline visuals or sprint status queries.
/human-confirm-gateMechanical confirmation for destructive Git and repository administration commands.
/install-runbook-linterLint a macOS onboarding runbook for privilege-correctness. Triggers: install runbook, fresh-Mac onboarding, brew cask runbook, admin/Standard user split, happy-camper onboarding.
/m1-window-gateGuard M1 dispatch and client seats during maintenance.
/model-pin-gatePreToolUse guard: unpinned Fable-seat spawns and sub-apex Fable targets block. Triggers: model pin, Fable seat, spawn.
/orcMulti-agent sprint coordination, ecosystem status, catch me up, fact propagation. NOT single-worker spawning.
/plan-councilPlan 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.
/qa-verdict-gateKill-gate: QA PASS/FAIL/INCONCLUSIVE + qa-report.md. Triggers: QA verdict, QA done/complete, pre-merge QA, false-FAIL.
/qa-videoVideo QA, debrief/review, gems/insights: QA recording, local video, YouTube. NOT still-image QA alone.
/repogolemrepoGolem launchers: {repo}Claude/Codex, flags -s/-c/-w/--worker, regenerate launchers. NOT generic agent spawning.
/research-lifecycleResearch corpus: stale context, R-number, research docs link (Google Docs/Deep Research report URL). NOT drive-filing.
/reviewer-order-gatePreToolUse guard: reviewer spawns denied until the implementer is done. Triggers: reviewer order, reviewer spawn.
/session-handoffWrite handoff, spawn successor, answer grill, verify orientation. Triggers: hand off, phase change. NOT on context%.
/skill-creatorCreate/edit/audit/eval golem skills. Triggers: create skill, skill eval, live eval, JSONL mining.
/stitch-designUse Google Stitch for design-to-code prototypes/tokens, then implement. Triggers: Stitch, screen prototypes.
/t3-visualsShow/visualize/chart/diagram/compare/status board in T3 with compact interactive HTML. Not standalone dashboards.
/tmp-blockGuard 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.
/unslopCut 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.
/weaveOrchestrator convergence: mine JSONLs, cite findings, route actions. Triggers: weave, run weave.
/whats-newDiff Claude/Codex/Cursor/Wispr/agy changelogs vs local setup. Triggers: whats new, changelog, version bump.
/yashPush dependency bugs upstream. Triggers: dependency bug, workaround, monkey-patch, fork/fix. NOT app bugs.
Quality
/large-planInvoke before any git/gh and before starting another agent (delegate_task, new thread, sub-agent): make a plan, plan next steps, lead kickoff, feature batch, multi-PR; dispatch a worker, send a brief, fan out.
/never-fabricateEvidence 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.