Skip to content

Guild-Agents/guild / src/templates/skills/build-feature

build-feature

Verified

Full pipeline: evaluation -> spec -> implementation -> review -> QA

FileKindSize
SKILL.mdskill md16.9 KB
evals/evals.jsonconfig1.8 KB
evals/triggers.jsonconfig801 B

evals/evals.json

View on GitHub
{
  "skill": "build-feature",
  "evals": [
    {
      "id": "bf-has-core-phases",
      "description": "Plan contains evaluate, design, implement phases",
      "expectations": [
        { "text": "Has evaluate step", "assertion": "step-exists:evaluate" },
        { "text": "Has design step", "assertion": "step-exists:design" },
        { "text": "Has implement step", "assertion": "step-exists:implement" }
      ]
    },
    {
      "id": "bf-has-quality-phases",
      "description": "Plan contains review, QA, and completion phases",
      "expectations": [
        { "text": "Has review step", "assertion": "step-exists:review" },
        { "text": "Has QA phase", "assertion": "step-exists:qa-phase" },
        { "text": "Has completion step", "assertion": "step-exists:completion" }
      ]
    },
    {
      "id": "bf-advisor-uses-reasoning",
      "description": "Advisor (evaluate) uses reasoning tier",
      "expectations": [
        { "text": "Evaluate uses reasoning tier", "assertion": "step-model-tier:evaluate:reasoning" }
      ]
    },
    {
      "id": "bf-developer-uses-execution",
      "description": "Developer (implement) uses execution tier",
      "expectations": [
        { "text": "Implement uses execution tier", "assertion": "step-model-tier:implement:execution" }
      ]
    },
    {
      "id": "bf-gates-exist",
      "description": "Quality gates exist at pre-review and final",
      "expectations": [
        { "text": "Pre-review gate exists", "assertion": "gate-exists:gate-pre-review" },
        { "text": "Final gate exists", "assertion": "gate-exists:gate-final" }
      ]
    },
    {
      "id": "bf-minimum-steps",
      "description": "Plan has at least 8 steps",
      "expectations": [
        { "text": "At least 8 steps", "assertion": "step-count:8" }
      ]
    }
  ]
}
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall