m3taz-ahmed/aizee / skills/bmad-deep-recon
bmad-deep-recon
VerifiedDecision-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/technical.md
View on GitHub# Technical Research Pack
Serves: adopt a technology area, design an integration approach, ground an architecture in current practice, assess feasibility before committing a roadmap.
**Dimensions (priority order — prune to the decision):**
1. Landscape & maturity — dominant approaches, what's consolidating vs churning, what the current generation newly makes possible
2. Integration & interoperability — protocols, formats, auth patterns, where integrations actually hurt
3. Architecture patterns in practice — which named patterns dominate at what scale, and what the failures teach
4. Implementation reality — learning curve, tooling, operational burden, what teams say 6–12 months in
5. Ecosystem health — contributor/release vitality, backing durability, the five-year regret risk
**Craft (the non-obvious):** read the retrospective threads, not the launch threads; favor accounts with production numbers over advocacy; before citing a pain point, check whether it was since fixed — an old complaint against a current version is a false claim; read repository metrics over time, never snapshots; issue trackers reveal the gap between docs and reality.
**Freshness:** versions & compatibility ≤ 1 mo · ecosystem signals ≤ 6 mo · landscape ≤ 12 mo (AI-adjacent ≤ 3 mo) · patterns ≤ 2 yr.
**Two-source classes:** version/compatibility claims; performance or scale numbers a recommendation rests on; claims that a technology or pattern failed — one post-mortem is an anecdote.
**Feeds (bmm):** architecture spine (candidate paradigms, operational constraints) · brief (feasibility) · roadmap risk and estimates.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |