Skip to content

m3taz-ahmed/aizee / skills/bmad-facilitate

bmad-facilitate

Verified

Coaches the user through writing, updating or validating a document. Use when invoked by skill name only

references/guidance-planning.md

View on GitHub
# Planning guidance

For plans, requirements and cases for a decision. These rules add to the skill's; the template's own comments win over them.

## Stakes

Read the stakes as one of: hobby or personal use, internal, pitch or investor, publication, public launch, regulated or contracted.

- At hobby stakes, one line fills a section. Skip reconciliation unless the user wants it, and run the rubric walker or no reviewer, with no fresh reader and without naming them first.
- Below regulated or contracted stakes, default and tag. At them, ask instead, and invent no regulation, citation or threshold. An obligation the user did not name, from you or a reviewer, is an open question; headless, so is anything you would have asked.
- Only at launch, regulated or contracted stakes may a review fix make the document longer.

## Assumptions in the body

Mark each unconfirmed inference where it lands as `[ASSUMPTION: ...]`, the only tag, a requirement you or a review fix added included. A proposal the user accepts goes in untagged. A tag stays until the user accepts that item. At the memlog audit, check each logged assumption still open is tagged where it lands. At polish, on a headless run or once a yes to a group has left tags standing, first move every remaining tag out of the body into the template's section for assumptions or a closing `## Assumptions`, one line each naming the id or section it affects, so the body reads clean and the guesses sit in one place.

## Ids and requirements

Give stable ids to anything others will cite. Where the document carries requirements or scope, make each requirement testable and each edge explicit; coaching a requirements document stops when the remaining questions reach edge cases and trade-offs. Names, owners and dates in the body come from the user, never the environment.

## The level below

A document over its template's length pushes detail down to the level below or splits. A review finding that would grow the agreed scope, or add detail the level below should decide, is no fix here: send it to that level or the open questions unless the user asks for it by name. Defer each open item with an owner and a revisit condition.
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: 472kUpdated 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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated 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: 322kUpdated Claude CodeCodexVerifiedInstall