fitness
Run quality fitness checks using configured thresholds and gates. Scores code against project standards.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Run quality fitness checks using configured thresholds and gates. Scores code against project standards.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Manage project board — issues, sprints, status tracking, acceptance verification, and release management. Supports GitHub Projects, Jira, and YouTrack via pluggable providers.
Manage project board — issues, sprints, status tracking, acceptance verification, and release management. Supports GitHub Projects, Jira, and YouTrack via pluggable providers.
Happy path smoke testing — navigates all configured endpoints, checks HTTP status and server logs for errors, and optionally auto-creates GitHub issues for failures. Config-driven via CC_SMOKE_TEST_* variables.
Manage GitHub Project board — issues, sprints, status tracking, acceptance verification, and release management. White-labeled template for any project.
Check for and apply cognitive-core framework updates. Compares installed agents, skills, and hooks against the framework source, shows available updates, and safely applies them.
Check for and apply cognitive-core framework updates. Compares installed agents, skills, and hooks against the framework source, shows available updates, and safely applies them.
| name | fitness |
| description | Run quality fitness checks using configured thresholds and gates. Scores code against project standards. |
| user-invocable | true |
| disable-model-invocation | true |
| allowed-tools | Bash, Read, Grep, Glob |
| catalog_description | Quality fitness checks with configurable thresholds and gates. |
Evaluates code quality against configurable fitness functions and gates. Reads
thresholds from cognitive-core.conf (CC_FITNESS_* variables).
$ARGUMENTS -- target file/dir, optional --gate=lint|commit|test|merge|deployFrom cognitive-core.conf:
CC_FITNESS_LINT -- lint gate threshold (default: 60)CC_FITNESS_COMMIT -- commit gate threshold (default: 80)CC_FITNESS_TEST -- test gate threshold (default: 85)CC_FITNESS_MERGE -- merge gate threshold (default: 90)CC_FITNESS_DEPLOY -- deploy gate threshold (default: 95)CC_LINT_COMMAND -- lint commandCC_TEST_COMMAND -- test runner| Function | Check | Source |
|---|---|---|
lint-pass | Configured lint command passes | CC_LINT_COMMAND |
format-pass | Configured format check passes | CC_FORMAT_COMMAND |
naming | File and symbol naming conventions | CLAUDE.md |
error-handling | Proper error handling patterns | CLAUDE.md |
| Function | Check | Source |
|---|---|---|
layer-deps | Layer dependencies follow pattern | CC_ARCHITECTURE |
domain-purity | Domain layer has no infrastructure | Code analysis |
no-anti-patterns | Blocked patterns from CLAUDE.md absent | CLAUDE.md |
| Function | Check | Source |
|---|---|---|
test-exists | New modules have corresponding tests | CC_TEST_PATTERN |
test-passes | Test suite passes | CC_TEST_COMMAND |
| Function | Check | Source |
|---|---|---|
no-secrets | No hardcoded credentials | Grep patterns |
parameterized-queries | No raw SQL/query injection | Code analysis |
input-validation | Public interfaces validate input | Code analysis |
| Gate | Trigger | Threshold | On Fail |
|---|---|---|---|
lint | Before staging | CC_FITNESS_LINT% | Block |
commit | Pre-commit | CC_FITNESS_COMMIT% | Reject |
test | Pre-merge | CC_FITNESS_TEST% | Block merge |
merge | Pull request | CC_FITNESS_MERGE% | Block merge |
deploy | Pre-deploy | CC_FITNESS_DEPLOY% | Abort |
FITNESS EVALUATION
==================
Target: [path]
Gate: [gate name]
CATEGORY SCORES
---------------
Code Standards: [0.00-1.00]
Architecture: [0.00-1.00]
Tests: [0.00-1.00]
Security: [0.00-1.00]
--------------------------
OVERALL: [0.00-1.00]
GATE THRESHOLD: [N]% ([gate] gate)
STATUS: [FIT - PASSED | UNFIT - BLOCKED]
REQUIRED FIXES:
1. [fix description]
/pre-commit -- Quick lint pass/code-review -- Detailed reviewCLAUDE.md -- Project standards