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`).
evals/triggers.json
View on GitHub[
{
"query": "make me a skill that turns a meeting transcript into decisions and action items",
"should_trigger": true
},
{
"query": "I keep asking you to run the same release checklist every time. can you turn that into a skill so I stop repeating myself",
"should_trigger": true
},
{
"query": "build an agent called Scout who reviews PRs with a grumpy senior-engineer persona and can also write release notes",
"should_trigger": true
},
{
"query": "scaffold a new skill folder for me, I'll write the prompt myself",
"should_trigger": true
},
{
"query": "my changelog skill never triggers when I ask for release notes, fix the description",
"should_trigger": true
},
{
"query": "review skills/decision-record and tell me what is bloated in it",
"should_trigger": true
},
{
"query": "package these three skills into a module we can install from our repo",
"should_trigger": true
},
{
"query": "we have an old module with a module.yaml and a setup skill, migrate it to the new bmod format",
"should_trigger": true
},
{
"query": "convert my Cursor rule for commit messages into a skill",
"should_trigger": true
},
{
"query": "hey smithy, I want a persona that remembers our conversations between sessions",
"should_trigger": true
},
{
"query": "I found this code-review skill on GitHub and copied it into .claude/skills/code-review. Can you make this skill BMad compliant and optimize it?",
"should_trigger": true
},
{
"query": "a teammate shared their standup-notes skill with me but it's like 4000 tokens of rambling, cut this skill down to what actually matters",
"should_trigger": true
},
{
"query": "grabbed a pdf-summary skill off some marketplace, optimize this skill before I start using it on our project",
"should_trigger": true
},
{
"query": "optimize this SQL query, it takes 12 seconds on the orders table and I think it's the join",
"should_trigger": false
},
{
"query": "run the evals for skills/decision-record and show me the benchmark",
"should_trigger": false
},
{
"query": "implement the login story from the ticket tree",
"should_trigger": false
},
{
"query": "what should I do next with bmad on this project?",
"should_trigger": false
},
{
"query": "write a python script that parses this CSV and sums the totals column",
"should_trigger": false
},
{
"query": "install the pdf skill from the anthropic marketplace",
"should_trigger": false
},
{
"query": "help me brainstorm names for my product",
"should_trigger": false
},
{
"query": "which skills do I have installed right now?",
"should_trigger": false
},
{
"query": "add a rule to tools/validate_skills.py that rejects descriptions without Use when",
"should_trigger": false
},
{
"query": "what is a bmod and how does bmad setup find one?",
"should_trigger": false
},
{
"query": "create a ticket for the new export feature",
"should_trigger": false
},
{
"query": "override the dev agent's communication style for this project only",
"should_trigger": false
},
{
"query": "customize the prd skill so it writes into docs/ instead of the default folder",
"should_trigger": false
}
]
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 |