Skip to content

HigorAlves/orc / codex/orc/content/skills/map

Ask which orc command, skill, or flow fits your situation — the router over everything orc ships.

The orc map

Which orc thing do I reach for? Answer from this map — recommend ONE entry point (➡️), name the runner-up only when the choice is genuinely close.

Before stating what a command or skill does, or recommending one of its steps be skipped, read its file: the summaries here are for orientation only.

The main flow (idea → shipped)

Step-by-step, human at every gate:

$orc-prd → $orc-trd → $orc-plan → $orc-start → implement → $orc-qa → $orc-ship → $orc-ci → $orc-address → $orc-cleanup

Most work enters mid-flow — a settled spec starts at $orc-plan; a settled plan starts at $orc-start. The one-shot alternative: $orc-flow runs the whole pipeline (plan → implement → QA → ship → address → cleanup) with an interactive gate per phase. Prefer $orc-flow when you want to hand over a well-described feature; prefer the step commands when you want to steer. $orc-explain is the optional step after QA: a narrated walkthrough of what was built and proven.

On-ramps (how work arrives)

SituationEntry point
Report in (ticket, Sentry, paste): is it real?$orc-triage
Confirmed bug, failing test, weird behavior$orc-debug (root cause before fix)
Production is on fire RIGHT NOW$orc-incident → later $orc-postmortem
CI red on an open PR$orc-ci
Someone's PR needs review$orc-code-review
Reviewers commented on YOUR PR$orc-address
PRD/spec/brief landed$orc-plan (dispatches analysis as needed)
"Where's the rot?" / refactor appetite$orc-plan, refactor framing (orc-refactor-architect)
Chunk of work too big for one session$orc-wayfinder
Issue backlog needs herding$orc-triage
Feature needs a Jira Epic→Story→Task build-out$orc-jira-breakdown
Dependencies stale or vulnerable$orc-deps
Need a narrated video of what shipped$orc-explain (after $orc-qa)
Cut a release (user project)$orc-release
New package/service/app shell$orc-scaffold
Interrupted mid-anything$orc-resume ($orc-status lists what's live)
A build just finished (or went sideways)$orc-retro — improve the environment, not the code
Agents keep relearning the same conventions$orc-context — write the binding project-context.md

Sharpening (before committing to build)

  • orc-grill-me / $orc-plan --grill — relentless decision-by-decision interview (engine: orc-grilling)
  • orc-grill-with-docs — same, but records ADRs + glossary as you go
  • orc-prototype — throwaway code to answer a design question
  • orc-research — primary-source investigation captured into the repo
  • orc-to-questionnaire — decision belongs to someone else? Package it for them
  • Docs: $orc-prd $orc-trd $orc-rfc $orc-adr (settled decisions → orc-adr-writing)

Vocabulary underneath (model-invoked, loaded when relevant)

orc-tdd · orc-systematic-debugging · orc-verification-before-completion · orc-codebase-design · orc-domain-modeling · orc-review-contract · orc-pr-size-budget · orc-callouts · orc-gates · orc-writing-for-agents — preloaded by commands and agents; invoke directly only outside them.

Phase boundaries (continue here or clear?)

Finished a phase (plan approved, slice green, QA passed)?
├─ Next phase needs the full working context (implement after plan)? → continue in-session
├─ Next phase judges the work (review, QA)? → fresh eyes win — new session or $orc-fan-out
├─ Handing to another tool/person/machine? → orc-handoff
└─ Done for the day? → checkpoint is already in .orc/ — $orc-resume picks it up

Utilities

  • $orc-stack-pr — branch blew the size budget? Split into a chained PR stack ($orc-ship's gate invokes it)
  • $orc-evidence — publish the QA evidence packet to the ticket
  • $orc-jira — Jira work items from the terminal (orc-jira-cli underneath)
  • $orc-fan-out — N independent tasks, parallel dispatch, no shared state

Setup (once per repo)

$orc-setup — tracker choice + triage labels + domain doc layout. $orc-env — containerized dev environment. orc doctor (CLI) — dependency health.

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 469kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall