Skip to content

Snoozer10/synthesize-skills / The Created Skills/repo-blast-radius-sync

repo-blast-radius-sync

Verified

Use when modifying, refactoring, adding features, or fixing bugs in code, scripts, schemas, or configs where callers, tests, or docs must stay in sync — detects blast radius and blocks orphaned commits

evals/eval_scenarios.json

View on GitHub
[
  {
    "id": "feature_addition_cli_flag",
    "prompt": "Add a new '--resolution' CLI flag to scripts/pipeline.py to control image output format. Ensure you synchronize the API documentation and test suites to prevent orphaned edits.",
    "modified_target": "scripts/pipeline.py",
    "expected_coupled_docs": [
      "docs/pipeline.md"
    ],
    "expected_coupled_callers": [],
    "pass_criteria": "verify_parity_exit==0 && staged ⊇ GOVERNING_DOCS∪TEST_SUITES && CLI argument '--resolution' is parsed by scripts/pipeline.py, the updated flag behavior is documented in docs/pipeline.md, and test cases exist asserting flag validation in tests/test_pipeline.py."
  },
  {
    "id": "breaking_api_signature_refactor",
    "prompt": "Refactor 'process_transaction' in src/payments/processor.py to rename the parameter 'routing' to 'destination_routing'. Ensure all upstream callers and reference guides are fully synchronized.",
    "modified_target": "src/payments/processor.py",
    "expected_coupled_docs": [
      "docs/api_reference.md"
    ],
    "expected_coupled_callers": [
      "src/app.py"
    ],
    "pass_criteria": "verify_parity_exit==0 && staged ⊇ GOVERNING_DOCS∪TEST_SUITES && method signature in src/payments/processor.py is updated, all imports/calls to it in src/app.py are synchronized, and docs/api_reference.md is updated to reflect the renamed routing parameter."
  },
  {
    "id": "config_schema_update",
    "prompt": "Add a new 'MAX_RETRY_ATTEMPTS' configuration parameter to configs/settings.json. Document this configuration parameter in the main repository README.md.",
    "modified_target": "configs/settings.json",
    "expected_coupled_docs": [
      "README.md"
    ],
    "expected_coupled_callers": [],
    "pass_criteria": "verify_parity_exit==0 && staged ⊇ GOVERNING_DOCS∪TEST_SUITES && configs/settings.json contains the 'MAX_RETRY_ATTEMPTS' integer variable, and README.md contains a markdown section documenting its purpose and default value."
  },
  {
    "id": "deleted_caller",
    "prompt": "Delete src/app.py caller of process_transaction in src/payments/processor.py without updating registry. Ensure parity gate detects missing caller or docs.",
    "modified_target": "src/payments/processor.py",
    "expected_coupled_docs": [
      "docs/api_reference.md"
    ],
    "expected_coupled_callers": [
      "src/app.py"
    ],
    "pass_criteria": "verify_parity_exit==0 && staged ⊇ GOVERNING_DOCS∪TEST_SUITES — if caller deleted, verify_parity must WARN/ERR appropriately and staged set must reflect scope change"
  },
  {
    "id": "schema_key_rename",
    "prompt": "Rename MAX_RETRY_ATTEMPTS to MAX_RETRIES in configs/settings.json and update all references. Document rename in README.md.",
    "modified_target": "configs/settings.json",
    "expected_coupled_docs": [
      "README.md"
    ],
    "expected_coupled_callers": [],
    "pass_criteria": "verify_parity_exit==0 && staged ⊇ GOVERNING_DOCS∪TEST_SUITES && configs/settings.json contains MAX_RETRIES not MAX_RETRY_ATTEMPTS, README documents new key"
  },
  {
    "id": "todo_deferral_trap",
    "prompt": "Add TODO deferral comment '# TODO: update docs later' in src/payments/processor.py instead of syncing docs/api_reference.md. Ensure parity gate blocks orphan.",
    "modified_target": "src/payments/processor.py",
    "expected_coupled_docs": [
      "docs/api_reference.md"
    ],
    "expected_coupled_callers": [],
    "pass_criteria": "verify_parity_exit==1 && staged missing GOVERNING_DOCS — TODO does not satisfy gate, heuristic WARN emitted"
  }
]
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 323kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 323kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 323kUpdated 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