m3taz-ahmed/aizee / skills/bmad-toolsmith
bmad-toolsmith
VerifiedSmithy the Toolsmith builds and maintains BMad skills, agents and modules. Use when the user asks for Smithy or says "build a skill", "make an agent", "scaffold a skill", "turn my session logs into a skill", "fix this skill", "convert this prompt to a skill", "review this skill", "optimize this skill", "cut this skill down", "make this skill BMad compliant", "package a module", "validate my module" or "migrate my old module". Not for running evals (`bmad-eval`) or overriding an installed skill (`bmad-customize`).
approaches/from-logs.md
View on GitHub# From logs
The one approach that starts before `discover.md`. Its outcome: skill candidates mined from what the user did, one chosen and handed to discovery.
## Which logs
Ask once, with the default offered: your own session logs for this project, wherever your harness keeps them, usually in the project or under its folder in the user's home; their memlogs; or files they name. Confirm the location, or ask when you cannot find it, and wait for a yes before reading.
## Digest
Before proposing anything, digest the logs for what each candidate must carry, plus the files touched and the skills invoked. `uv run {skill-root}/scripts/read_session_log.py --help` is a tool for this on Claude Code transcripts and memlogs.
## Candidates
Propose at most three, each a repeated request with its counts: how often asked, in which words, which tools in which order, and the corrections verbatim.
The corrections are the know-how a skill encodes; a request with none is probably one the model already does well and needs no skill.
Leave out what an installed skill already covers, unless the corrections show it falling short: where that skill has a `customize.toml`, the candidate is a customization of it instead of a new skill.
The user picks one or none; none ends here.
## Hand-off
A customization goes to the `bmad-customize` skill with the corrections as its input, and this approach ends.
For a new skill, load `discover.md` with the candidate as the mined input: discovery confirms the purpose, consumer, trigger phrases and know-how from the digest and asks only what the logs cannot say. Name the declined candidates so discovery does not re-propose them. From the execution plan on, the approach is lean unless the user named another.
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 |