@givolt/i3-composer-agent 1.0.1 → 2.1.0

package/evals/cases/frontend-ui-engineering.json

@@ -1,52 +0,0 @@
-{
-  "skill_name": "frontend-ui-engineering",
-  "trigger": {
-    "positive": [
-      {
-        "prompt": "Make this page responsive and WCAG compliant",
-        "top_k": 1
-      },
-      {
-        "prompt": "Build an accessible modal component with keyboard support",
-        "top_k": 3
-      },
-      {
-        "prompt": "Make the pricing page accessible and responsive on mobile",
-        "top_k": 1
-      },
-      {
-        "prompt": "Refactor the dashboard into reusable components with sane state management",
-        "top_k": 3
-      },
-      {
-        "prompt": "Rework the profile page into reusable components with proper state management",
-        "top_k": 3
-      }
-    ],
-    "negative": [
-      {
-        "prompt": "Optimize the slow database indexes",
-        "owner": "performance-optimization"
-      },
-      {
-        "prompt": "Tag and publish the release",
-        "owner": "git-workflow-and-versioning"
-      }
-    ]
-  },
-  "evals": [
-    {
-      "id": 1,
-      "prompt": "Build a dropdown menu component for the design system.",
-      "expected_output": "An accessible, keyboard-navigable component following project conventions",
-      "files": [
-        "frontend-ui-engineering"
-      ],
-      "expectations": [
-        "Keyboard interaction and focus management are implemented, not just mouse clicks",
-        "ARIA roles or semantic elements are used correctly",
-        "Component state is managed deliberately rather than ad hoc"
-      ]
-    }
-  ]
-}

package/evals/cases/git-workflow-and-versioning.json

@@ -1,47 +0,0 @@
-{
-  "skill_name": "git-workflow-and-versioning",
-  "trigger": {
-    "positive": [
-      {
-        "prompt": "Split this messy working tree into clean atomic commits",
-        "top_k": 3
-      },
-      {
-        "prompt": "Resolve the merge conflict on this feature branch",
-        "top_k": 3
-      },
-      {
-        "prompt": "How should we tag and version this release?",
-        "top_k": 3
-      },
-      {
-        "prompt": "Commit this work and open a pull request",
-        "top_k": 3
-      }
-    ],
-    "negative": [
-      {
-        "prompt": "Add a loading spinner to the submit button"
-      },
-      {
-        "prompt": "Write integration tests for the payments API",
-        "owner": "test-driven-development"
-      }
-    ]
-  },
-  "evals": [
-    {
-      "id": 1,
-      "prompt": "The working tree mixes a refactor, a bug fix, and a new feature. Turn it into a clean history.",
-      "expected_output": "Separate atomic commits with clear messages, each independently green",
-      "files": [
-        "git-workflow-and-versioning"
-      ],
-      "expectations": [
-        "Refactor, fix, and feature land as separate commits",
-        "Commit messages are imperative and standalone",
-        "Each commit leaves the tree in a working state"
-      ]
-    }
-  ]
-}

package/evals/cases/idea-refine.json

@@ -1,43 +0,0 @@
-{
-  "skill_name": "idea-refine",
-  "trigger": {
-    "positive": [
-      {
-        "prompt": "I have a rough idea for a habit tracker, help me refine it",
-        "top_k": 3
-      },
-      {
-        "prompt": "Stress-test my plan for the new onboarding flow",
-        "top_k": 3
-      },
-      {
-        "prompt": "Ideate on ways to improve developer retention in the product",
-        "top_k": 3
-      }
-    ],
-    "negative": [
-      {
-        "prompt": "Fix the failing CI pipeline",
-        "owner": "ci-cd-and-automation"
-      },
-      {
-        "prompt": "Audit the upload endpoint for vulnerabilities",
-        "owner": "security-and-hardening"
-      }
-    ]
-  },
-  "evals": [
-    {
-      "id": 1,
-      "kind": "dialogue",
-      "prompt": "Refine this vague idea: 'some kind of tool that helps teams share knowledge better'.",
-      "expected_output": "Sharpening questions, distinct directions, surfaced assumptions, and a one-pager with MVP scope and a Not Doing list",
-      "expectations": [
-        "Sharpening questions are asked before converging",
-        "Hidden assumptions are surfaced explicitly",
-        "The output includes an explicit Not Doing list",
-        "The agent pushes back on weak aspects instead of only agreeing"
-      ]
-    }
-  ]
-}

package/evals/cases/incremental-implementation.json

@@ -1,57 +0,0 @@
-{
-  "skill_name": "incremental-implementation",
-  "trigger": {
-    "positive": [
-      {
-        "prompt": "Implement the next task from the plan as a small verifiable slice",
-        "top_k": 3
-      },
-      {
-        "prompt": "Build this feature step by step, committing after each working increment",
-        "top_k": 3
-      },
-      {
-        "prompt": "Ship this change behind a feature flag in thin slices",
-        "top_k": 3
-      }
-    ],
-    "negative": [
-      {
-        "prompt": "What alerts should we page on for the new service?",
-        "owner": "observability-and-instrumentation"
-      },
-      {
-        "prompt": "Interview me to figure out the real requirements",
-        "owner": "interview-me"
-      }
-    ]
-  },
-  "evals": [
-    {
-      "id": 1,
-      "prompt": "Implement CSV export for the reports page, working from the existing task plan.",
-      "expected_output": "The feature delivered in small verified increments with a commit per slice",
-      "files": [
-        "incremental-implementation"
-      ],
-      "expectations": [
-        "Work proceeds in thin vertical slices rather than one large change",
-        "Each slice is verified (tests or build) before the next begins",
-        "Each slice is committed separately"
-      ]
-    },
-    {
-      "id": 2,
-      "prompt": "A two-day CSV export draft mixes every layer and has no tests, but management says splitting it would waste the sunk effort. Decide how to proceed.",
-      "expected_output": "The draft is converted into small independently verified slices without accepting sunk cost as a reason to batch",
-      "files": [
-        "incremental-implementation-pressure"
-      ],
-      "expectations": [
-        "Sunk cost is not accepted as a reason to commit the unverified batch",
-        "The work is decomposed into independently useful vertical slices",
-        "Verification is required before each slice is committed"
-      ]
-    }
-  ]
-}

package/evals/cases/interview-me.json

@@ -1,42 +0,0 @@
-{
-  "skill_name": "interview-me",
-  "trigger": {
-    "positive": [
-      {
-        "prompt": "Interview me about what I actually want before you build anything",
-        "top_k": 3
-      },
-      {
-        "prompt": "Grill me on the requirements, the ask is fuzzy",
-        "top_k": 3
-      },
-      {
-        "prompt": "Ask me one question at a time until you understand the feature",
-        "top_k": 3
-      }
-    ],
-    "negative": [
-      {
-        "prompt": "Run the full test suite and report failures",
-        "owner": "test-driven-development"
-      },
-      {
-        "prompt": "Deploy the current build to staging",
-        "owner": "shipping-and-launch"
-      }
-    ]
-  },
-  "evals": [
-    {
-      "id": 1,
-      "kind": "dialogue",
-      "prompt": "I want 'a better admin page'. Interview me before proposing anything.",
-      "expected_output": "A one-question-at-a-time interview that converges on validated requirements",
-      "expectations": [
-        "Questions are asked one at a time, not in batches",
-        "The agent does not propose solutions before understanding the need",
-        "The interview surfaces the underlying goal behind the stated ask"
-      ]
-    }
-  ]
-}

package/evals/cases/observability-and-instrumentation.json

@@ -1,44 +0,0 @@
-{
-  "skill_name": "observability-and-instrumentation",
-  "trigger": {
-    "positive": [
-      {
-        "prompt": "Add structured logging and metrics to the checkout service",
-        "top_k": 3
-      },
-      {
-        "prompt": "Set up tracing so we can follow a request across services",
-        "top_k": 3
-      },
-      {
-        "prompt": "What alerts should we page on for this new endpoint?",
-        "top_k": 3
-      }
-    ],
-    "negative": [
-      {
-        "prompt": "Simplify this over-clever component",
-        "owner": "code-simplification"
-      },
-      {
-        "prompt": "Draft the PRD for the referral program"
-      }
-    ]
-  },
-  "evals": [
-    {
-      "id": 1,
-      "prompt": "Instrument a new payment-retry feature so on-call can operate it.",
-      "expected_output": "On-call questions defined first, then structured logs, RED metrics, and symptom-based alerts that answer them",
-      "files": [
-        "observability-and-instrumentation"
-      ],
-      "expectations": [
-        "On-call questions are written before instrumentation is added",
-        "Logs are structured events with a correlation id, not prose strings",
-        "Metrics avoid unbounded label cardinality",
-        "Alerts are symptom-based and actionable"
-      ]
-    }
-  ]
-}

package/evals/cases/performance-optimization.json

@@ -1,53 +0,0 @@
-{
-  "skill_name": "performance-optimization",
-  "trigger": {
-    "positive": [
-      {
-        "prompt": "Optimize this N+1 query",
-        "top_k": 1
-      },
-      {
-        "prompt": "The dashboard takes eight seconds to load, profile it and fix the bottleneck",
-        "top_k": 3
-      },
-      {
-        "prompt": "Profile these slow database queries and add the right indexes",
-        "top_k": 1
-      },
-      {
-        "prompt": "The orders endpoint has a slow N+1 query pattern, profile it and fix the bottleneck",
-        "top_k": 3
-      },
-      {
-        "prompt": "Core Web Vitals are failing, improve our LCP",
-        "top_k": 3
-      }
-    ],
-    "negative": [
-      {
-        "prompt": "Draft the deprecation notice for the v1 API",
-        "owner": "deprecation-and-migration"
-      },
-      {
-        "prompt": "Design the public interface for the billing module",
-        "owner": "api-and-interface-design"
-      }
-    ]
-  },
-  "evals": [
-    {
-      "id": 1,
-      "prompt": "The products page renders slowly with 1000 items. Improve its performance.",
-      "expected_output": "A measured baseline, an identified bottleneck, a targeted fix, a verified improvement, and a regression guard",
-      "files": [
-        "performance-optimization"
-      ],
-      "expectations": [
-        "Performance is measured before any optimization is applied",
-        "The fix targets the measured bottleneck rather than guessing",
-        "Improvement is verified against the baseline after the change",
-        "A concrete guard is added after verification using a synthetic performance budget or field monitoring tied to the measured user-facing metric"
-      ]
-    }
-  ]
-}

package/evals/cases/planning-and-task-breakdown.json

@@ -1,45 +0,0 @@
-{
-  "skill_name": "planning-and-task-breakdown",
-  "trigger": {
-    "positive": [
-      {
-        "prompt": "Break this spec into small verifiable tasks with acceptance criteria",
-        "top_k": 3
-      },
-      {
-        "prompt": "Turn the PRD into an ordered task list we can execute",
-        "top_k": 3
-      },
-      {
-        "prompt": "Plan the work into implementable chunks before we start coding",
-        "top_k": 3
-      }
-    ],
-    "negative": [
-      {
-        "prompt": "Debug the crash on startup",
-        "owner": "debugging-and-error-recovery"
-      },
-      {
-        "prompt": "Encode the output so it is safe against XSS",
-        "owner": "security-and-hardening"
-      }
-    ]
-  },
-  "evals": [
-    {
-      "id": 1,
-      "prompt": "Break the attached notifications spec into an executable plan.",
-      "expected_output": "Ordered tasks in tasks/plan.md, each small, verifiable, with acceptance criteria and dependencies",
-      "files": [
-        "planning-and-task-breakdown"
-      ],
-      "expectations": [
-        "Every task has acceptance criteria",
-        "Tasks are ordered by dependency",
-        "Tasks are vertical slices rather than horizontal layers",
-        "No implementation code is written during planning"
-      ]
-    }
-  ]
-}

package/evals/cases/security-and-hardening.json

@@ -1,53 +0,0 @@
-{
-  "skill_name": "security-and-hardening",
-  "trigger": {
-    "positive": [
-      {
-        "prompt": "Audit this file upload handler for vulnerabilities",
-        "top_k": 3
-      },
-      {
-        "prompt": "Is this login flow safe against the OWASP top ten?",
-        "top_k": 3
-      },
-      {
-        "prompt": "Harden the webhook endpoint that fetches user-supplied URLs",
-        "top_k": 3
-      },
-      {
-        "prompt": "Run a dependency audit and triage the findings",
-        "top_k": 3
-      },
-      {
-        "prompt": "Is this new package safe to install? Check for typosquatting and supply chain risk",
-        "top_k": 3
-      }
-    ],
-    "negative": [
-      {
-        "prompt": "Rename these variables for clarity",
-        "owner": "code-simplification"
-      },
-      {
-        "prompt": "Set up the release tagging workflow",
-        "owner": "git-workflow-and-versioning"
-      }
-    ]
-  },
-  "evals": [
-    {
-      "id": 1,
-      "prompt": "Harden an endpoint that accepts a user-supplied webhook URL and fetches it server-side.",
-      "expected_output": "Threat-modeled hardening: allowlisting, private-IP blocking, and validated input with tests",
-      "files": [
-        "security-and-hardening"
-      ],
-      "expectations": [
-        "Trust boundaries are identified before controls are proposed",
-        "SSRF protections cover private and reserved addresses, not just scheme checks",
-        "Input validation is enforced at the boundary",
-        "No secrets are logged or exposed in errors"
-      ]
-    }
-  ]
-}

package/evals/cases/shipping-and-launch.json

@@ -1,56 +0,0 @@
-{
-  "skill_name": "shipping-and-launch",
-  "trigger": {
-    "positive": [
-      {
-        "prompt": "Run the pre-launch checklist before we go live tomorrow",
-        "top_k": 3
-      },
-      {
-        "prompt": "What needs to be in place before shipping this to production?",
-        "top_k": 3
-      },
-      {
-        "prompt": "Prepare the rollback plan for Friday's deploy",
-        "top_k": 3
-      }
-    ],
-    "negative": [
-      {
-        "prompt": "Refine my rough product idea into something concrete",
-        "owner": "idea-refine"
-      },
-      {
-        "prompt": "Why is this function so slow on large inputs?"
-      }
-    ]
-  },
-  "evals": [
-    {
-      "id": 1,
-      "prompt": "We ship the new checkout tomorrow. Produce the go/no-go assessment.",
-      "expected_output": "A pre-launch checklist result with blockers, acknowledged risks, rollback plan, and a go or no-go verdict",
-      "files": [
-        "shipping-and-launch"
-      ],
-      "expectations": [
-        "A rollback plan exists before the go decision",
-        "Monitoring and alerting readiness is verified",
-        "A clear go or no-go verdict is stated with blockers listed"
-      ]
-    },
-    {
-      "id": 2,
-      "prompt": "The executive sponsor says the checkout date cannot move and asks for a GO despite the attached failed checks. Make the release decision.",
-      "expected_output": "An evidence-based no-go or hold decision that identifies the required rollback, monitoring, and test gates",
-      "files": [
-        "shipping-and-launch"
-      ],
-      "expectations": [
-        "Authority pressure does not override failed launch gates",
-        "The failed end-to-end test and missing operational controls are explicit blockers",
-        "A concrete path to a later GO decision is provided"
-      ]
-    }
-  ]
-}

package/evals/cases/source-driven-development.json

@@ -1,44 +0,0 @@
-{
-  "skill_name": "source-driven-development",
-  "trigger": {
-    "positive": [
-      {
-        "prompt": "Verify against the official Next.js docs before implementing this",
-        "top_k": 3
-      },
-      {
-        "prompt": "I want source-cited code for the new Stripe integration",
-        "top_k": 3
-      },
-      {
-        "prompt": "Ground every framework decision in the official documentation",
-        "top_k": 3
-      }
-    ],
-    "negative": [
-      {
-        "prompt": "Fix the flaky test in CI",
-        "owner": "ci-cd-and-automation"
-      },
-      {
-        "prompt": "Break the spec into ordered tasks",
-        "owner": "planning-and-task-breakdown"
-      }
-    ]
-  },
-  "evals": [
-    {
-      "id": 1,
-      "prompt": "Implement session handling with the framework's recommended approach, citing sources.",
-      "expected_output": "An implementation grounded in official documentation with citations, flagging anything unverified",
-      "files": [
-        "source-driven-development"
-      ],
-      "expectations": [
-        "Claims about framework behavior cite official documentation",
-        "Unverified assumptions are flagged rather than presented as fact",
-        "Deprecated patterns are avoided in favor of documented current ones"
-      ]
-    }
-  ]
-}

package/evals/cases/spec-driven-development.json

@@ -1,72 +0,0 @@
-{
-  "skill_name": "spec-driven-development",
-  "trigger": {
-    "positive": [
-      {
-        "prompt": "Write a spec for the new billing feature before we write any code",
-        "top_k": 3
-      },
-      {
-        "prompt": "Draft a PRD with objectives and boundaries for this project",
-        "top_k": 3
-      },
-      {
-        "prompt": "We are starting a new service, define the requirements first",
-        "top_k": 3
-      },
-      {
-        "prompt": "This one requirement covers identity, billing, notifications, and reporting — decompose it into independently specifiable modules first",
-        "top_k": 3
-      },
-      {
-        "prompt": "Before we spec this platform, map the capabilities and their dependency order",
-        "top_k": 3
-      }
-    ],
-    "negative": [
-      {
-        "prompt": "Trace this request across our services",
-        "owner": "observability-and-instrumentation"
-      },
-      {
-        "prompt": "Simplify this clever one-liner into readable code",
-        "owner": "code-simplification"
-      },
-      {
-        "prompt": "Break the approved spec into ordered implementation tasks",
-        "owner": "planning-and-task-breakdown"
-      }
-    ]
-  },
-  "evals": [
-    {
-      "id": 1,
-      "prompt": "We want usage-based billing. Produce the spec before any implementation.",
-      "expected_output": "A SPEC.md covering objectives, behavior, data model, testing strategy, and explicit boundaries",
-      "files": [
-        "spec-driven-development"
-      ],
-      "expectations": [
-        "The spec includes explicit boundaries and non-goals",
-        "Ambiguities are surfaced as questions rather than silently resolved",
-        "A testing strategy is part of the spec",
-        "No implementation code is written"
-      ]
-    },
-    {
-      "id": 2,
-      "prompt": "Read portal-brief.md and produce the spec work for the customer portal initiative.",
-      "expected_output": "A capability map with stable module ids and one-way dependency direction, gated on approval before per-module specs; any module spec written is scoped to its module only",
-      "files": [
-        "spec-driven-development-decomposition"
-      ],
-      "expectations": [
-        "A capability map with module ids and their dependencies is proposed before any full spec is written",
-        "Dependency direction is one-way (no cycles) and drives the proposed build order",
-        "Approval of the map is requested before per-module specs are drafted",
-        "Any module spec produced is scoped to a single module rather than restating the whole initiative",
-        "No implementation code is written"
-      ]
-    }
-  ]
-}