Skip to content

m3taz-ahmed/aizee / skills/bmad-deep-recon

bmad-deep-recon

Verified

Decision-grade research on a topic or this repository. Use when the user says "deep recon", "research this", "draft a research prompt", "process this research report", "market research", "domain research", "technical research", "competitor research", "what users say about X", "literature review", "help me choose between", "research the codebase", "research how X works here" or "why is X built this way". Not for a quick code question answered in chat.

types/domain.md

View on GitHub
# Domain Research Pack

Serves: commit to building in an industry, talk credibly with domain experts, scope a product for a regulated field, brief a team entering unfamiliar territory.

**Dimensions (priority order — prune to the decision):**

1. Industry structure & value chain — how value flows, who captures margin where
2. Key players & gatekeepers — incumbents, platforms, whose APIs/standards/marketplaces you build with or against
3. Rules of the game — laws, licenses, de-facto standards, what compliance costs a new entrant
4. Language & mental models — the vocabulary and implicit workflows practitioners think in; **build the glossary — it's why domain research exists**
5. Technology adoption — the current technical baseline and where the industry sits on the adoption curve

**Craft (the non-obvious):** annual-report industry sections are free structured teardowns; conference keynotes reveal who actually matters; go to regulator sites directly for any load-bearing claim — and read enforcement actions to learn what's actually punished versus merely written; job postings name the real tools and skills; pending regulatory changes matter as much as current text.

**Freshness:** structure ≤ 3 yr · player landscape ≤ 18 mo · regulatory status: verify current on every load-bearing claim, whatever its date · tech adoption ≤ 18 mo, AI-adoption claims ≤ 6 mo.

**Two-source classes:** regulatory and compliance assertions; quantitative industry figures a recommendation rests on; claims about a gatekeeper's policy.

**Feeds (bmm):** brief (context, feasibility) · PRD (constraints, domain vocabulary) · architecture (integration landscape, compliance requirements).
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