Guild-Agents/guild / src/templates/skills/guild-specialize
guild-specialize
VerifiedEnriches CLAUDE.md by exploring the project and specializes agents to the real stack
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.6 KB |
| evals/evals.json | config | 2.1 KB |
| evals/triggers.json | config | 806 B |
evals/evals.json
View on GitHub{
"skill": "guild-specialize",
"evals": [
{
"id": "gs-has-core-steps",
"description": "Guild specialize has read, explore, enrich, specialize, confirm, commit steps",
"expectations": [
{ "text": "Has read-base step", "assertion": "step-exists:read-base" },
{ "text": "Has explore-project step", "assertion": "step-exists:explore-project" },
{ "text": "Has enrich-claude-md step", "assertion": "step-exists:enrich-claude-md" },
{ "text": "Has specialize-agents step", "assertion": "step-exists:specialize-agents" },
{ "text": "Has confirm step", "assertion": "step-exists:confirm" },
{ "text": "Has commit-enrichment step", "assertion": "step-exists:commit-enrichment" }
]
},
{
"id": "gs-enrichment-uses-reasoning",
"description": "CLAUDE.md enrichment uses reasoning tier (opus)",
"expectations": [
{ "text": "enrich-claude-md uses reasoning", "assertion": "step-model-tier:enrich-claude-md:reasoning" }
]
},
{
"id": "gs-agents-use-execution",
"description": "Agent specialization uses execution tier (sonnet)",
"expectations": [
{ "text": "specialize-agents uses execution", "assertion": "step-model-tier:specialize-agents:execution" }
]
},
{
"id": "gs-gates",
"description": "Gates at exploration and confirmation",
"expectations": [
{ "text": "explore-project has gate", "assertion": "gate-exists:explore-project" },
{ "text": "confirm has gate", "assertion": "gate-exists:confirm" }
]
},
{
"id": "gs-tech-lead-role",
"description": "Enrichment and specialization use tech-lead role",
"expectations": [
{ "text": "enrich-claude-md is tech-lead", "assertion": "step-role:enrich-claude-md:tech-lead" },
{ "text": "specialize-agents is tech-lead", "assertion": "step-role:specialize-agents:tech-lead" }
]
},
{
"id": "gs-minimum-steps",
"description": "Has at least 6 steps",
"expectations": [
{ "text": "At least 6 steps", "assertion": "step-count:6" }
]
}
]
}
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: 471k | 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 |