@givolt/i3-composer-agent 0.0.0-stage → 0.6.12

package/evals/cases/api-and-interface-design.json

@@ -0,0 +1,45 @@
+{
+  "skill_name": "api-and-interface-design",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "Design a REST endpoint for creating invoices, including error responses and versioning",
+        "top_k": 3
+      },
+      {
+        "prompt": "What should the public interface of this payments module expose to other teams?",
+        "top_k": 3
+      },
+      {
+        "prompt": "Help me define the contract between the frontend and the orders service",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "My unit test is failing with a null pointer exception",
+        "owner": "debugging-and-error-recovery"
+      },
+      {
+        "prompt": "Make this landing page responsive on mobile",
+        "owner": "frontend-ui-engineering"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Design the public API for a URL-shortening service: create, resolve, stats. Produce the endpoint contracts.",
+      "expected_output": "Endpoint contracts with methods, paths, request/response shapes, and explicit error semantics",
+      "files": [
+        "api-and-interface-design"
+      ],
+      "expectations": [
+        "Error responses are specified with status codes and a consistent error shape, not just happy paths",
+        "Input validation at the boundary is addressed for user-supplied URLs",
+        "Versioning or compatibility strategy is stated",
+        "The response does not silently invent unstated requirements"
+      ]
+    }
+  ]
+}

package/evals/cases/browser-testing-with-devtools.json

@@ -0,0 +1,44 @@
+{
+  "skill_name": "browser-testing-with-devtools",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "Use Chrome DevTools to figure out why the checkout button click does nothing",
+        "top_k": 3
+      },
+      {
+        "prompt": "Inspect the network requests the dashboard makes when it first loads",
+        "top_k": 3
+      },
+      {
+        "prompt": "Verify in a real browser that the form submits and the data persists in localStorage",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Write a spec for the new billing feature before we start",
+        "owner": "spec-driven-development"
+      },
+      {
+        "prompt": "Break this PRD into ordered implementation tasks",
+        "owner": "planning-and-task-breakdown"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "The signup form renders but submitting it appears to do nothing. Verify the real behavior in the browser and report findings.",
+      "expected_output": "Runtime evidence from the browser: console errors, network activity, DOM state, and a diagnosis",
+      "files": [
+        "browser-testing-with-devtools"
+      ],
+      "expectations": [
+        "Findings are grounded in observed runtime data (console, network, DOM), not static code reading alone",
+        "The report distinguishes what was observed from what is inferred",
+        "A concrete next step or fix hypothesis is provided"
+      ]
+    }
+  ]
+}

package/evals/cases/ci-cd-and-automation.json

@@ -0,0 +1,45 @@
+{
+  "skill_name": "ci-cd-and-automation",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "Set up a GitHub Actions pipeline that runs the tests on every pull request",
+        "top_k": 3
+      },
+      {
+        "prompt": "Add a deploy stage to the pipeline with a manual approval gate",
+        "top_k": 3
+      },
+      {
+        "prompt": "Automate the quality gates so nothing merges without passing checks",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Refactor this function so it is easier to read",
+        "owner": "code-simplification"
+      },
+      {
+        "prompt": "Add structured logging to the checkout service",
+        "owner": "observability-and-instrumentation"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Create a CI pipeline for a Node project: install, lint, test on every PR, and block merge on failure.",
+      "expected_output": "A working workflow definition with correct triggers, steps, and failure behavior",
+      "files": [
+        "ci-cd-and-automation"
+      ],
+      "expectations": [
+        "The workflow triggers on pull requests",
+        "Failure of any quality gate fails the pipeline run",
+        "Steps are ordered logically and cache or setup steps are sane",
+        "No secrets are hardcoded in the workflow"
+      ]
+    }
+  ]
+}

package/evals/cases/code-review-and-quality.json

@@ -0,0 +1,49 @@
+{
+  "skill_name": "code-review-and-quality",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "Review this pull request before I merge it",
+        "top_k": 3
+      },
+      {
+        "prompt": "Do a quality pass on this diff for correctness and readability",
+        "top_k": 3
+      },
+      {
+        "prompt": "Can you review the changes another model just wrote for me?",
+        "top_k": 3
+      },
+      {
+        "prompt": "Review this diff before I merge it. It adds paging to the orders endpoint.",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Deploy this to production now",
+        "owner": "shipping-and-launch"
+      },
+      {
+        "prompt": "Write a failing test for the bug before fixing it",
+        "owner": "test-driven-development"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Review the provided diff that adds a user-search endpoint. Deliver a structured review.",
+      "expected_output": "A multi-axis review with severity-labelled findings and file:line references",
+      "files": [
+        "code-review-and-quality"
+      ],
+      "expectations": [
+        "Findings cover more than one axis (correctness, readability, architecture, security, performance)",
+        "Every finding carries a severity label from the skill's taxonomy",
+        "Security of user input is explicitly considered for the new endpoint",
+        "The review leads with high-leverage findings rather than nits"
+      ]
+    }
+  ]
+}

package/evals/cases/code-simplification.json

@@ -0,0 +1,45 @@
+{
+  "skill_name": "code-simplification",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "This function works but it is way too clever, simplify it without changing behavior",
+        "top_k": 3
+      },
+      {
+        "prompt": "Reduce the complexity of this module so juniors can maintain it",
+        "top_k": 3
+      },
+      {
+        "prompt": "Clean up this working code, it has grown hard to follow",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Add a feature flag system to the app",
+        "owner": "incremental-implementation"
+      },
+      {
+        "prompt": "Diagnose why the build broke overnight",
+        "owner": "debugging-and-error-recovery"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Simplify the provided 80-line function that parses config files, preserving exact behavior.",
+      "expected_output": "A simpler implementation with identical behavior and a summary of what was removed and why",
+      "files": [
+        "code-simplification"
+      ],
+      "expectations": [
+        "Behavior is preserved (tests unchanged and passing, or equivalence argued concretely)",
+        "Complexity is reduced rather than relocated",
+        "The response explains what was removed and why it was safe",
+        "No new features are added during the simplification"
+      ]
+    }
+  ]
+}

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

@@ -0,0 +1,79 @@
+{
+  "skill_name": "constraint-driven-development",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "Set up quality constraints for this project — I want to define our bar before the agent writes more code",
+        "top_k": 3
+      },
+      {
+        "prompt": "We have no written standards. Ask me what I care about and write it down with sane defaults",
+        "top_k": 3
+      },
+      {
+        "prompt": "The agent keeps adding @ts-ignore and skipping tests to get green. How do I stop that?",
+        "top_k": 3
+      },
+      {
+        "prompt": "What coverage threshold should we enforce, and where should it run so it doesn't slow us down?",
+        "top_k": 3
+      },
+      {
+        "prompt": "I care about accessibility and web performance — set those up as enforced constraints",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Review this pull request across correctness and security",
+        "owner": "code-review-and-quality"
+      },
+      {
+        "prompt": "Add a deploy stage to our pipeline with a manual approval gate",
+        "owner": "ci-cd-and-automation"
+      },
+      {
+        "prompt": "Write a failing test for this bug before we fix it",
+        "owner": "test-driven-development"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "kind": "dialogue",
+      "prompt": "Set up constraints for this repo. I don't really know what numbers to pick.",
+      "expected_output": "A short interview with defaults offered, followed by a CONSTRAINTS.md the user can explain",
+      "expectations": [
+        "The agent inspects the repo for stack, test runner, and existing linters before asking anything",
+        "No more than four questions are asked, and each one carries a usable default",
+        "When the user has no target number, the agent proposes recording today's value and holding it rather than inventing a threshold",
+        "The resulting constraints say where each check runs, keeping fast checks in the edit loop and slow checks later",
+        "Every number written down is accompanied by a reason"
+      ]
+    },
+    {
+      "id": 2,
+      "kind": "dialogue",
+      "prompt": "Our coverage is 62% and I want to enforce 85% starting today.",
+      "expected_output": "Pushback on setting an unmeetable budget, with the ratchet alternative offered",
+      "expectations": [
+        "The agent points out that a threshold the codebase fails today produces a permanently red build",
+        "It offers to record 62% and require that it not fall, as an adoptable alternative",
+        "It does not silently accept 85% without noting the consequence"
+      ]
+    },
+    {
+      "id": 3,
+      "kind": "dialogue",
+      "prompt": "Accessibility matters to us. Add it as a constraint.",
+      "expected_output": "A working accessibility check, not just a threshold written down",
+      "expectations": [
+        "The agent names axe-core and gives the install and run commands rather than only stating a violation threshold",
+        "It notes that axe needs a running URL and asks for one, or drops the dimension if the project has no URL to hit",
+        "The command that produces the verdict is recorded alongside the rule in CONSTRAINTS.md",
+        "The check is placed at the preview-deploy stage rather than in the per-edit loop"
+      ]
+    }
+  ]
+}

package/evals/cases/context-engineering.json

@@ -0,0 +1,44 @@
+{
+  "skill_name": "context-engineering",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "What context should I load into the agent before starting this refactor?",
+        "top_k": 3
+      },
+      {
+        "prompt": "The model's output quality dropped mid-session, how do I fix its context?",
+        "top_k": 3
+      },
+      {
+        "prompt": "Set up rules files and context packing for my repository",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Write unit tests for the date parser",
+        "owner": "test-driven-development"
+      },
+      {
+        "prompt": "Harden this endpoint against SQL injection",
+        "owner": "security-and-hardening"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "An agent session has degraded: responses are generic and it keeps forgetting project conventions. Fix the context setup.",
+      "expected_output": "A diagnosis of the context problem and a concrete loading strategy (rules files, packing, task-scoped context)",
+      "files": [
+        "context-engineering"
+      ],
+      "expectations": [
+        "The response diagnoses probable context causes rather than blaming the model generally",
+        "A specific context-loading plan is produced (what to load, when, and why)",
+        "Context is scoped to the task instead of loading everything"
+      ]
+    }
+  ]
+}

package/evals/cases/debugging-and-error-recovery.json

@@ -0,0 +1,58 @@
+{
+  "skill_name": "debugging-and-error-recovery",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "The app crashes with a TypeError when I click save, help me find the root cause",
+        "top_k": 3
+      },
+      {
+        "prompt": "The API is throwing intermittent 500 errors in production, help me find the root cause",
+        "top_k": 3
+      },
+      {
+        "prompt": "This test passed yesterday and fails today, figure out what broke",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Write the API documentation for the orders service",
+        "owner": "documentation-and-adrs"
+      },
+      {
+        "prompt": "Simplify this working function for readability",
+        "owner": "code-simplification"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "A test that passed yesterday now fails with an off-by-one error in pagination. Find and fix the root cause.",
+      "expected_output": "A reproduced failure, an identified root cause, a minimal fix, and a guard against regression",
+      "files": [
+        "debugging-and-error-recovery"
+      ],
+      "expectations": [
+        "The failure is reproduced before any fix is attempted",
+        "The root cause is identified and stated, not just the symptom patched",
+        "A regression test exists after the fix",
+        "The fix is minimal and scoped to the cause"
+      ]
+    },
+    {
+      "id": 2,
+      "prompt": "Production checkout is failing and a stakeholder demands an immediate pagination patch without reproduction. Respond under time pressure.",
+      "expected_output": "Evidence preserved, the failure reproduced, and a root-cause fix guarded by a regression test",
+      "files": [
+        "debugging-and-error-recovery"
+      ],
+      "expectations": [
+        "The time pressure does not cause reproduction or evidence gathering to be skipped",
+        "The requested speculative patch is not applied before the cause is localized",
+        "The final fix is tied to a reproduced cause and a regression test"
+      ]
+    }
+  ]
+}

package/evals/cases/deprecation-and-migration.json

@@ -0,0 +1,52 @@
+{
+  "skill_name": "deprecation-and-migration",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "We are sunsetting the v1 API, plan the deprecation",
+        "top_k": 3
+      },
+      {
+        "prompt": "Migrate users off the legacy auth system without breaking them",
+        "top_k": 3
+      },
+      {
+        "prompt": "How do I remove this old feature safely for existing users?",
+        "top_k": 3
+      },
+      {
+        "prompt": "Rename a database column without downtime",
+        "top_k": 3
+      },
+      {
+        "prompt": "How do I drop a column safely in production?",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Add dark mode to the settings page",
+        "owner": "frontend-ui-engineering"
+      },
+      {
+        "prompt": "Why is this test flaky on CI?",
+        "owner": "ci-cd-and-automation"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Plan the deprecation of a public v1 REST API with 200 external consumers, replaced by v2.",
+      "expected_output": "A staged deprecation plan: comms, timeline, compatibility window, monitoring, and removal criteria",
+      "files": [
+        "deprecation-and-migration"
+      ],
+      "expectations": [
+        "Consumers are notified with a timeline before any breaking change",
+        "A compatibility or migration window exists with monitoring of remaining usage",
+        "Removal is gated on measured migration, not a calendar date alone"
+      ]
+    }
+  ]
+}

package/evals/cases/documentation-and-adrs.json

@@ -0,0 +1,44 @@
+{
+  "skill_name": "documentation-and-adrs",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "Write an ADR for choosing Postgres over MongoDB",
+        "top_k": 3
+      },
+      {
+        "prompt": "Document the architecture decision behind the queue design",
+        "top_k": 3
+      },
+      {
+        "prompt": "Update the documentation for the new setup flow and record why it changed",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Find the root cause of the memory leak in the worker",
+        "owner": "debugging-and-error-recovery"
+      },
+      {
+        "prompt": "Harden the login endpoint against brute force attacks",
+        "owner": "security-and-hardening"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Record the decision to adopt event sourcing for the orders service as an ADR.",
+      "expected_output": "An ADR capturing context, decision, alternatives considered, and consequences",
+      "files": [
+        "documentation-and-adrs"
+      ],
+      "expectations": [
+        "The ADR states context, decision, alternatives, and consequences distinctly",
+        "Trade-offs and rejected options are recorded, not just the winning choice",
+        "The ADR records a status from the skill's lifecycle (Proposed, Accepted, Superseded or Deprecated) and a date"
+      ]
+    }
+  ]
+}

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

@@ -0,0 +1,43 @@
+{
+  "skill_name": "doubt-driven-development",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "This change touches production auth, cross-examine every assumption before we proceed",
+        "top_k": 3
+      },
+      {
+        "prompt": "I am not confident in this approach, adversarially review my reasoning in a fresh context",
+        "top_k": 3
+      },
+      {
+        "prompt": "High-stakes migration tomorrow, stress the plan for hidden failure modes",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Format this file with prettier"
+      },
+      {
+        "prompt": "Write the changelog entry for the release",
+        "owner": "git-workflow-and-versioning"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Before running an irreversible data migration, subject the migration plan to adversarial review.",
+      "expected_output": "Claims extracted, doubts raised against each, reconciliation, and a go or stop verdict",
+      "files": [
+        "doubt-driven-development"
+      ],
+      "expectations": [
+        "Non-trivial claims in the plan are extracted and challenged individually",
+        "At least one assumption is tested rather than accepted",
+        "The verdict distinguishes verified claims from surviving doubts"
+      ]
+    }
+  ]
+}

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

@@ -0,0 +1,52 @@
+{
+  "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

@@ -0,0 +1,47 @@
+{
+  "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"
+      ]
+    }
+  ]
+}