From automated-assessment
Use when working with ANY project compliance assessment, quality enhancement, or test suite improvement. MUST be triggered BEFORE manual quality work begins (e.g., to enhance tests, improve coverage, increase mutation score, or strengthen test suite). Also use for: running quality audits against checkpoint-enabled skills, verifying release readiness, mechanical checks, or LLM-assisted code reviews.
How this skill is triggered — by the user, by Claude, or both
Slash command
/automated-assessment:automated-assessmentThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Systematic compliance assessment against checkpoint-enabled skills.
assets/llm-rubric-dependency-compatibility.mdassets/llm-rubric-repo-health.mdassets/skill-template/checkpoints.yamlevals/evals.jsonreferences/calibration.mdreferences/checkpoint-coverage-requirements.mdreferences/checkpoint-workflow.mdreferences/checkpoints-schema.mdreferences/dependency-compatibility.mdreferences/learning-derived-checkpoints.mdreferences/migration-guide.mdreferences/verification-patterns.mdscripts/run-checkpoints.shSystematic compliance assessment against checkpoint-enabled skills.
/assess # All matching skills
/assess skill-repo typo3-testing # Specific skills only
/assess --force # Ignore preconditions
/assess --mechanical-only # Scripted checks only
/assess --autofix # Fix issues automatically
/assess --review # Categorize failures
/assess --autoimprove # Fix + propose improvements
/assess dependency-compatibility # Dependency compat checks
/assess --pre-push # Pre-push validation gate
/assess --check-coverage # Verify checkpoint coverage
| Option | Effect |
|---|---|
<skill-names> | Run checkpoints for named skills only (also accepts domain names like dependency-compatibility) |
--force | Skip precondition checks |
--mechanical-only | Skip LLM reviews |
--autofix | Fix failures via responsible skill, re-verify |
--review | Categorize failures, suggest skill improvements |
--autoimprove | Fix + propose checkpoint changes; add --create-issues to file issues |
--json | Raw JSON output |
--pre-push | Run pre-push gate (PHPStan, tests, PHP-CS-Fixer, Rector) |
--check-coverage | Verify adequate checkpoint coverage |
CRITICAL: Run /assess BEFORE manual quality work (enhance tests, improve coverage, strengthen suite, upgrade PHPStan, etc.). Assessment generates a structured gap analysis, preventing wasted iterative discovery.
/assess with relevant skills--autofix for automated resolution)/assess to verifyMechanical: file_exists, file_not_exists, contains, not_contains, regex, json_path, gh_api, command. LLM: llm_review (grouped by domain). See references/checkpoints-schema.md.
repo-health security code-quality documentation git-workflow docker ddev upgrade dependency-compatibility pre-push
--autofix invokes responsible skill for failures, re-verifies. Statuses: auto-fixed, needs-review, unfixable. --review/--autoimprove create feedback loops.
Only installed tools (vendor/bin/*) are checked. Missing tools pass. IDs: PP-01 (PHPStan), PP-02 (PHPUnit), PP-03 (PHP-CS-Fixer), PP-04 (Rector).
error = blocks release, warning = recommendation, info = optional.
references/checkpoints-schema.md -- Checkpoint YAML schema and typesreferences/checkpoint-coverage-requirements.md -- Required coverage categories per skillreferences/checkpoint-workflow.md -- Full assessment workflow with autofix loopreferences/calibration.md -- Calibration debt, audit cadence, anchor at generation time, ratchet anti-patternreferences/dependency-compatibility.md -- Multi-major-version assessment triggerreferences/migration-guide.md -- Adding checkpoints to existing skillsreferences/verification-patterns.md -- Verification patterns and result schemasCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub netresearch/claude-code-marketplace --plugin automated-assessment