Claude Skills by indigoai-us

Run a lightweight freshness pass over company knowledge and policies.

Triage, review, and sequentially merge multiple open PRs. Handles CI monitoring, conflict resolution between PRs, Codex-style review, and post-merge deploy verification. Use when asked to "land all PRs", "merge open PRs", or "triage and ship".

Land a PR: monitor CI, resolve review issues, merge, monitor production. Use when asked to "land this", "merge and monitor", "ship this PR", or after PR creation when next step is merge + prod verification.

Turn reusable findings into scoped policies or insight files.

Read HQ-native meeting notes, transcripts, recaps, and sources for a company.

Provision a fleet agent end-to-end — identity, membership, vault join, secrets, file access, MCP/runtime bootstrap, mission brief, and a verified capability probe. Use when standing up a new HQ agent (Slack bot, reporting agent, ops agent) or when an existing agent reports it is blocked on access.

Onboard a human teammate end-to-end — invite, role, groups, secrets, file access, onboarding packet, and acceptance follow-through. Use when someone new joins a company or an existing teammate needs their access brought up to their role.

Scaffold a new HQ company AND optionally take it all the way to operational — business-discovery interview, seeded knowledge/workers/skills/projects, brand design packs (generated from website/PDF/Drive and bound to deploys via policy), connected integrations, org groups + ACL rules, teammate invites, and optional cloud agents.

Scaffold a new HQ worker with skills, tools, and knowledge.

Create or join an HQ company through onboarding.

Read a company ontology brief, entity graph, and freshness signals for context.

Take an idea all the way to a finished deliverable in one command — capture it, research and compare approaches, generate the PRD, then execute every story to the actual work product (code, artwork, documents), continuously and without pausing. Recommended answers are taken automatically and recorded in the decision ledger; --gated pauses at human decisions instead; --plan-only stops at the execution-ready PRD. Use when the user says "/orchestrate", "take this idea to done", "make this end to...

Record rejected ideas so future planning does not revisit them.

Host a full-stack or static app directly on the HQ Outpost / EC2 VM this session is running on, served through nginx. Finds a free port on the box, installs and configures nginx (static file serving or reverse-proxy to a running app), and returns the public URL. HARD-GATED — refuses to run anywhere that is not an HQ Outpost or EC2 instance and tells the user why. Use when the user says "host this app on the outpost", "serve this on the VM", "deploy my app to the outpost", "put this site on th...

Build the owner profile and social voice through interview.

Anchor this session to one goal — the message, target, or outcome it keeps working toward across loops, wakeups, compactions, and hand-offs — and check progress against it.

Create an execution-ready PRD and README for an HQ project.

Create an execution-ready PRD for a project. Creates prd.json + README.md with full HQ context awareness. Runtime-agnostic — executes identically in Claude Code and Codex. Lightweight by default — uses batched questions and adapts interview depth to brainstorm context if available. For deep research subagents + 3-tier 15-question interview, use /deep-plan instead.

Render a branded visual artifact from a project's prd.json (plan summary) or brainstorm.md (research deck) and deploy it gated, returning a link.

Change an HQ company member role or guest path scope.

Sync the active company's PUBLISHED documentation site (the standalone docs-site repo, e.g. docs.{company}.com) to match what shipped. Company-agnostic dispatcher — resolves the company's docs-site sync skill and runs it foreground. Distinct from document-release, which syncs in-repo docs (README, CLAUDE.md, architecture, INDEX). Use after shipping a material change, or as the final foreground step of /ship. Triggers on "publish the docs site", "update the docs site", "sync published docs".

Universal pre-commit quality checks (typecheck, lint, test, coverage, dead code) with auto-detection and --fix support

Recover sessions that hit context limits without a handoff.

Inspect or update a company resource registry around resource changes.

Resolve HQ Sync conflicts by choosing local, cloud, or discard.

Resume work from a specific handoff thread by id. Loads that thread's saved state (summary, next steps, git, files touched, learnings) and drops you straight back into the work. Use when you have a thread id in hand — e.g. from a previous `/handoff` report — and want to continue that exact session in a fresh one, rather than picking the most recent handoff (`/startwork`) or doing a post-mortem (`/recover-session`).

Run a project or session retrospective and capture reusable lessons.

Stress-test a plan or PRD in expansion, hold, or reduction mode.

Paranoid pre-landing code review. Reads git diff, runs two-pass analysis (CRITICAL blocks PR, INFORMATIONAL goes in body), surfaces issues with file:line references. Use when reviewing code before creating a PR, after finishing implementation, or when asked to review changes.

Multi-project pipeline orchestrator — triage, execute, PR, review, deploy with safety gates

Router for executing HQ PRD stories. Default dispatches each story as a detached workflow-runner lane — the same mechanism /conduct uses — into a pooled per-worker slot claimed through conduct-pool.sh, so work in flight survives session compaction and can be corrected mid-flight (the coordinator loop stays parent-side, so a lost session leaves the run resumable, not self-advancing). Typically 3-4 live lanes (preflight explorer, story worker, regression gate), never more than CONDUCT_POOL_CAP ...

Run or list HQ workers, preferring isolated Codex subagents when available.

Schedule recurring Claude/Codex agent jobs on the user's Outpost — structured checklist requirements, dm alert profile, status-aware list from hq-pro. Alias: /job (deprecated).

Search HQ content and indexed repos with qmd, falling back to grep.

Run the HQ Starter Kit setup wizard.

Meta pipeline: review → land → deploy → smoke → heal → monitor. Takes one or more PRs from "open" through merged, deployed, live-verified, and monitored until every declared KPI is healthy. Use when asked to "ship this", "land and monitor", "take this all the way to prod", or when a feature spans repos and needs the full loop closed (per policy hq-smoke-cross-repo-contracts-before-done).

Read HQ-native company signals such as decisions, actions, risks, commitments, and wins.

Resolve current HQ context and surface useful next work options.

Lock visual design before building — explore mockups on your preferred surface (Paper, HTML, Figma) and feed discovered changes back into the PRD.

Prioritize what to work on next, optionally with deep review.

Rebuild a company resource registry index.

Enforce test-driven development with RED→GREEN→REFACTOR cycle and coverage validation

Break a plan, spec, or conversation into tracer-bullet vertical-slice tickets, each declaring its blocking edges (dependency order). Use when you have a plan/spec/PRD and need it decomposed into independently-executable tickets. Triggers on "break into tickets", "slice this into tasks", "vertical slices", "tracer bullets".

Manually log a time estimate.

Run hands-on HQ workflow lessons.

Upgrade HQ from the latest hq-core release.

Plan a chunk of work too big for one agent session with a foggy destination — chart a shared map of investigation tickets and resolve them one per session until the path is clear. Use when the effort is too large to hold in one planning pass and the destination is unclear. Triggers on "too big to plan", "chart a map", "investigation tickets", "foggy scope".

Draft Slack broadcasts for completed or proposed HQ work.

Create a git worktree under workspace/worktrees/ and route all subsequent work through it. Main checkout is never modified — neither working tree nor local branch refs. By default fetches origin and branches off origin/{default} so the worktree gets the latest upstream state without mutating the main tree. Use when the user asks to "do X in a worktree", "spin up a worktree", "isolate this change", "work without touching main", or whenever a non-trivial change should be sandboxed.

Run long-tail HQ CLI commands through guarded host-side Cowork tools.