Claude Skills by indigoai-us

Accept HQ membership invites from a magic link or raw token.

Capture qualifying architecture decisions as ADRs in the right HQ or repo location.

Surface architectural friction and propose deepening opportunities — turn shallow modules into deep ones for better testability and AI-navigability. Output: ranked candidate list with deletion-test outcome, leverage/locality scoring, file refs. Never edits code directly; presents candidates and walks the user through grilling-style design decisions for picked candidates. Use when the codebase is hard to change, when /diagnose hands off "no good test seam," or when planning a refactor wave.

Generate dark ASCII banner graphics for HQ and social launch assets.

Compare approaches, surface unknowns, and draft a recommendation before PRD work.

Summarize estimate accuracy from the assistant time log.

Save a lightweight session checkpoint.

Clean up an HQ git worktree — merge a detached worktree branch back into local main in the primary HQ tree, then remove the worktree and delete the branch. Use when HQ work happened in a separate worktree (e.g. .claude/worktrees/<name> on claude/*, or workspace/worktrees/<name> on codex/*) and needs to land and be cleaned up — including right after /handoff when HQ itself is running from a separate worktree. HQ is local-only; this workflow never pushes to a remote.

Audit and clean HQ structures, indexes, and stale content.

Shared vocabulary and discipline for designing deep modules (a lot of behaviour behind a small interface, at a clean seam). Use when designing module boundaries or interfaces, or when another skill needs the deep-module vocabulary. Triggers on "deep module", "interface design", "design it twice".

Commit every dirty file in the current repo, only when on main.

Put the session into orchestrator mode — every task is assigned to a long-lived HQ worker from a capped session pool and run as a detached workflow-runner lane on a user-chosen engine (Codex, Grok, or Claude), so the parent session stays free to accept and route new messages. Use when the user says "/conduct", "run everything in the background", "keep the session free", "orchestrate through workers", or names an engine for delegated work.

Add Codex support to older Claude-first HQ roots without breaking Claude setup.

Create or capture a shared company skill in HQ with a durable identity and FILE_ACL governance. Use when asked to create or add a team/company skill, or to turn a repeatable workflow into an HQ skill. Do not use for personal or local-only Codex skills.

Resolve pending user decisions one at a time.

Deep project planning — research subagents (codebase / HQ / repo) + 3-tier 15-question interview (Strategic / Architecture / Quality) with smart-skip and pushback. Use for large or strategically important PRDs. For lightweight planning, use /plan instead. Adversarial spec review is delegated to /review-plan after generation.

Hand a project to a named person or fleet agent with exact grant receipts, a published dossier, local ownership updates, and a pickup DM. Track recipient access separately through their acknowledgment.

Deploy or share generated HQ artifacts through hq-deploy.

Mark a company as HQ Pro cloud-backed and sync its team setup.

Disciplined diagnosis loop for hard bugs, performance regressions, and intermittent failures. Build a deterministic feedback loop FIRST, then reproduce → hypothesise (3-5 ranked) → instrument (one variable at a time, tagged probes) → fix at the correct seam → cleanup + post-mortem. Use when the dominant problem is "I cannot reliably reproduce or measure this." For bugs that reproduce reliably with unknown root cause, use /investigate instead.

Pull a repo into HQ at latest main, fan out parallel exploration, and synthesize structured knowledge + (gated) policies under the owning company. Use when the user says "discover this repo", "ingest <repo>", "pull <repo> into HQ", or asks to learn a codebase HQ doesn't yet know.

Bind this session to one HQ DM channel — post structured status updates there and listen for replies (feedback, requests) that steer the work.

Send or read HQ Sync direct messages — inbox, 1:1 threads, channel history; also prompts, details, or scheduled notes to teammates.

Post-ship documentation sync — updates README, CLAUDE.md, architecture docs, and INDEX files to match what actually shipped. Use after merging a PR, completing a project, or deploying a release. Triggers on "update docs", "sync documentation", "docs are stale", "document what shipped".

Actively build and sharpen a project's domain model — challenge fuzzy or overloaded terms against a glossary, stress-test with edge cases, and maintain CONTEXT.md as the source of truth for a ubiquitous language. Use when the user wants to pin down domain terminology, resolve a naming conflict, define a ubiquitous language, or when another skill needs to produce or sharpen the domain model. Triggers on "what should we call this", "domain model", "ubiquitous language", "define these terms", "u...

Execute a single PRD story through coordinated worker phases (Ralph pattern). Each worker handles its domain, passes context to the next, with back-pressure (tests/lint/typecheck) keeping code on rails.

Mark a pending time estimate complete with actual duration.

Audit HQ content for stale, duplicate, or inaccurate information.

View and manage company OKRs and key results.

Preserve session state for a follow-up agent with handoff files and commits.

Score an HQ setup across hooks, context, gates, persistence, search, security, and cost.

Diagnose and fix a vault file you cannot find or open — never existed, not synced (fetch and pin it), or no access (ask the owner with a one-click grant DM).

Submit HQ bug reports or feature requests with session context.

Check that HQ is working and fix what can be fixed safely — updates HQ, starts the app if it's closed, backs up work that hasn't saved, turns safety checks back on. Reports anything left in plain language.

Inspect or change HQ vault ACLs, grants, and shared prefixes.

Triage and repair HQ session errors such as hook crashes, sync conflicts, or MCP failures.

Connect, govern, and use company apps (Linear, Notion, …) from any HQ session via `hq integrations` — browse the catalog, connect an app, set who may use it and whether its changes need approval, call its tools, and handle the approval gate. Use when the user asks an agent to look something up or act in an external app, or to add, share, or disconnect one.

Sign into HQ Cognito, preferring status, refresh, then browser login.

Sign out of HQ Cognito and clear local tokens.

Use HQ CLI secrets safely through env injection or one-off exec.

Share HQ vault paths through single-use links or direct ACL grants.

Run a full bidirectional sync for cloud-backed HQ companies.

Show current HQ Cognito identity and session expiry.

Revise human-facing prose to remove AI tells and match the intended voice.

Capture a lightweight project idea on the board.

Deprecated alias for /import-context — bootstrap HQ from your prior AI footprint (Claude Code, Codex, Grok, claude.ai history plus on-disk artifacts).

Bootstrap HQ from your prior AI footprint — Claude Code, Codex, Grok, and claude.ai conversation history plus on-disk artifacts (skills, hooks, policies, repos, plans). Proposes companies, knowledge, policies, and projects for guided import.

Iron Law debugging — systematic root cause investigation before any fixes. Scope lock, pattern classification, hypothesis testing with 3-strike rule, structured DEBUG REPORT. Use when debugging, fixing bugs, or tracing unexpected behavior. Triggers on "debug this", "fix this bug", "why is this broken", "root cause analysis".

Deprecated alias for /schedule — Outpost recurring agent jobs. Prefer /schedule.

Write structured session journal entries for durable working memory.