本文へ移動
cccskills
無料GitHub で公開

ln-643-api-contract-auditor

Checks layer leakage in method signatures, missing DTOs, entity leakage to API, inconsistent error contracts. Returns findings with penalty-based scoring.

インストール方法を見る

含まれるファイル(2)

  • SKILL.md7.3 KB
  • references/detection_patterns.md6.2 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Paths: File paths (shared/, references/, ../ln-*) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.

API Contract Auditor (L3 Worker)

Specialized worker auditing API contracts, method signatures at service boundaries, and DTO usage patterns.

Purpose & Scope

  • Worker in ln-640 coordinator pipeline - invoked by ln-640-pattern-evolution-auditor
  • Audit API contracts at architecture level (service boundaries, layer separation)
  • Check layer leakage, DTO patterns, error contract consistency
  • Return structured analysis with 4 scores (compliance, completeness, quality, implementation)

Out of Scope (owned by ln-623-code-principles-auditor):

  • Code duplication (same DTO shape repeated, same mapping logic, same validation)
  • Report only ARCHITECTURE BOUNDARY findings (wrong layer, missing contract)

Input (from ln-640 coordinator)

- pattern: "API Contracts"     # Pattern name
- locations: string[]          # Service/API directories
- adr_reference: string        # Path to related ADR
- bestPractices: object        # Best practices from MCP Ref/Context7
- output_dir: string           # e.g., "docs/project/.audit/ln-640/{YYYY-MM-DD}"

# Domain-aware (optional, from coordinator)
- domain_mode: "global" | "domain-aware"   # Default: "global"
- current_domain: string                   # e.g., "users", "billing" (only if domain-aware)
- scan_path: string                        # e.g., "src/users/" (only if domain-aware)

Workflow

Phase 0: Load References

MANDATORY READ: Load shared/references/two_layer_detection.md for detection methodology. Load references/detection_patterns.md — language-specific Grep patterns for all 5 rules.

Phase 1: Discover Service Boundaries

scan_root = scan_path IF domain_mode == "domain-aware" ELSE codebase_root

1. Find API layer: Glob("**/api/**/*.py", "**/routes/**/*.ts", "**/controllers/**/*.ts", root=scan_root)
2. Find service layer: Glob("**/services/**/*.py", "**/services/**/*.ts", root=scan_root)
3. Find domain layer: Glob("**/domain/**/*.py", "**/models/**/*.py", root=scan_root)
4. Map: which services are called by which API endpoints

Phase 2: Analyze Contracts (5 Rules)

MANDATORY READ: Use detection_patterns.md for language-specific Grep patterns per rule.

#RuleSeverityWhat to Check
1Layer LeakageHIGH/MEDIUMService/domain accepts HTTP types (Request, parsed_body, headers)
2Missing DTOMEDIUM/LOW4+ params repeated in 2+ methods without grouping DTO
3Entity LeakageHIGH/MEDIUMORM entity returned from API without response DTO. Downgrade when: internal API with no external consumers → LOW
4Error ContractsMEDIUM/LOWMixed error patterns (raise + return None) in same service
5Redundant OverloadsLOW/MEDIUMMethod pairs with _with_/_and_ suffix differing by 1-2 params
6Architectural HonestyHIGH/MEDIUMRead-named function (get_/find_/check_/validate_/is_/has_) body contains write side-effects. Exclusions per shared/references/ai_ready_architecture.md

Scope boundary: SKIP DUPLICATION findings (owned by ln-623), REPORT only ARCHITECTURE BOUNDARY findings.

Phase 3: Calculate 4 Scores

Compliance Score (0-100):

CriterionPoints
No layer leakage (HTTP types in service)+35
Consistent error handling pattern+25
Follows project naming conventions+10
No hidden side-effects in read-named functions+10
No entity leakage to API+20

Completeness Score (0-100):

CriterionPoints
All service methods have typed params+30
All service methods have typed returns+30
DTOs defined for complex data+20
Error types documented/typed+20

Quality Score (0-100):

CriterionPoints
No boolean flag params in service methods+15
No opaque return types hiding write actions+10
No methods with >5 params without DTO+25
Consistent naming across module+25
No redundant overloads+25

Implementation Score (0-100):

CriterionPoints
DTOs/schemas exist and are used+30
Type annotations present+25
Validation at boundaries (Pydantic, Zod)+25
API response DTOs separate from domain+20

Phase 3.5: Calculate Score

MANDATORY READ: Load shared/references/audit_worker_core_contract.md and shared/references/audit_scoring.md.

Primary score uses penalty formula (same as all workers):

penalty = (critical × 2.0) + (high × 1.0) + (medium × 0.5) + (low × 0.2)
score = max(0, 10 - penalty)

Diagnostic sub-scores (0-100 each) are calculated separately and reported in AUDIT-META for diagnostic purposes only.

Phase 4: Write Report

MANDATORY READ: Load shared/references/audit_worker_core_contract.md and shared/templates/audit_worker_report_template.md.

# Build markdown report in memory with:
# - AUDIT-META (extended: score [penalty-based] + diagnostic score_compliance/completeness/quality/implementation)
# - Checks table (layer_leakage, missing_dto, entity_leakage, error_contracts, redundant_overloads)
# - Findings table (issues sorted by severity)
# - DATA-EXTENDED: issues array with principle + domain fields (for cross-domain aggregation)

IF domain_mode == "domain-aware":
  Write to {output_dir}/643-api-contract-{current_domain}.md
ELSE:
  Write to {output_dir}/643-api-contract.md

Phase 5: Return Summary

Report written: docs/project/.audit/ln-640/{YYYY-MM-DD}/643-api-contract-users.md
Score: 6.75/10 (C:65 K:70 Q:55 I:80) | Issues: 4 (H:2 M:1 L:1)

Critical Rules

MANDATORY READ: Load shared/references/audit_worker_core_contract.md.

  • Architecture-level only: Focus on service boundaries, not internal implementation
  • Read before score: Never score without reading actual service code
  • Scope boundary: SKIP duplication findings (owned by ln-623)
  • Detection patterns: Use language-specific Grep from detection_patterns.md
  • Domain-aware: When domain_mode="domain-aware", scan only scan_path, tag findings with domain

Definition of Done

MANDATORY READ: Load shared/references/audit_worker_core_contract.md.

  • Service boundaries discovered (API, service, domain layers)
  • Method signatures extracted and analyzed
  • All 5 rules checked using detection_patterns.md
  • Scope boundary applied (no duplication with ln-623)
  • 4 scores calculated with justification
  • Issues identified with severity, location, suggestion, effort
  • If domain-aware: findings tagged with domain field
  • Report written to {output_dir}/643-api-contract[-{domain}].md (atomic single Write call)
  • Summary returned to coordinator

Reference Files

  • Detection patterns: references/detection_patterns.md
  • Scoring rules: ../ln-640-pattern-evolution-auditor/references/scoring_rules.md
  • Pattern library: ../ln-640-pattern-evolution-auditor/references/pattern_library.md

Version: 2.0.0 Last Updated: 2026-02-08

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA standards. Use this skill to generate semantic ARIA for Web and accessibility traits for Web and Native platforms (iOS/Android).

日本語の概要は準備中です。原文の説明を表示しています。

tensology/decisionsai172026年10月13日 更新

Whole site or product — a full web accessibility (a11y) audit against WCAG 2.2, following the WCAG-EM methodology. Defines scope, samples representative pages and flows, runs the automated tier (`accessibility-scan`) and the hands-on manual tier (`accessibility-inspect`), and produces one conformance report. Grades each finding by severity and evidence basis, and states per-criterion conformance as pass, fail, or undetermined (needs a human). Use it for 'audit my site for accessibility', 'is this product accessible', 'a11y audit', 'WCAG or Section 508 conformance report', or any multi-page assessment. Assesses; does not fix (use `accessibility-fix`) or diff (use `accessibility-diff`). For a single page use `accessibility-scan`; for hands-on keyboard and screen-reader checks use `accessibility-inspect`.

日本語の概要は準備中です。原文の説明を表示しています。

tensology/decisionsai172026年10月13日 更新

Regression check — diff a live page's web accessibility (a11y) violations against a baseline. By default it compares your uncommitted changes (stash-based); pass `--branch [<name>]` to compare against a branch. Reports the new WCAG violations introduced, the ones fixed, and the count of pre-existing ones. Use it for 'did my change break accessibility', 'what a11y issues did this PR add', or as a CI gate. For a full scan of one page use `accessibility-scan`; for a whole site use `accessibility-audit`.

日本語の概要は準備中です。原文の説明を表示しています。

tensology/decisionsai172026年10月13日 更新

Remediation only — repair web accessibility (a11y) violations against WCAG 2.2 with a baseline, edit, and verify loop. Takes a target (URL, files, directory) or a findings worklist from `accessibility-scan`/`accessibility-inspect`/`accessibility-audit`, applies mechanical fixes as given, leaves TODOs for visual or contextual judgment, and verifies by re-running the baseline check. It only fixes. To find issues use `accessibility-scan` (one page, automated), `accessibility-inspect` (one page, manual), or `accessibility-audit` (whole site, WCAG-EM); to check for regressions use `accessibility-diff`. Use it for 'fix the a11y issues in X', 'make this accessible', 'add missing alt text and labels', 'apply these accessibility fixes', 'remediate these violations'.

日本語の概要は準備中です。原文の説明を表示しています。

tensology/decisionsai172026年10月13日 更新

One page, hands-on manual tier — drive a live page through the web accessibility (a11y) checks a rule engine can't decide: keyboard operation and focus order, screen-reader names, roles and states from the accessibility tree, reflow and zoom, reduced motion, form errors, and target size. Grades each finding by evidence basis (verified / confirm-with-a-human / human-required) and severity, and closes every criterion in a ledger: verified, flagged, not exercised, or N/A. Locates and assesses; does not fix (use `accessibility-fix`). Use it for keyboard testing, focus-order checks, screen-reader or a11y-tree review, reflow and zoom at 200%, or 'is this operable, not just lint-clean'. The automated tier is `accessibility-scan`; `accessibility-audit` runs both across a sampled site.

日本語の概要は準備中です。原文の説明を表示しています。

tensology/decisionsai172026年10月13日 更新

One page, automated tier — run the web accessibility (a11y) rule engine against a live page and locate every violation it can detect mechanically. Pass a URL, a config target name (e.g. `accesslint:accessibility-scan dev`), or nothing to use the default target from `accesslint.config.json`. Ensures a debuggable Chrome, runs the @accesslint/core engine over CDP, and returns a worklist of live-DOM WCAG 2.2 violations, each grounded to its DOM selector and source `file:line`. Locates; doesn't edit. Use it for 'is this page accessible', 'check a11y on this URL', 'find contrast and alt-text issues', or to verify a UI change. For hands-on keyboard and screen-reader checks use `accessibility-inspect`; for a whole site or product use `accessibility-audit`; to diff against uncommitted changes or a branch use `accessibility-diff`.

日本語の概要は準備中です。原文の説明を表示しています。

tensology/decisionsai172026年10月13日 更新

tensology のスキルをすべて見る

このスキルの問題を報告する