Skip to content
cccskills
FreePublished on GitHub

integration-checker

Verify cross-component wiring and data flow.

The English summary is being prepared. Showing the original description.

See how to install

Files included (2)

  • SKILL.md4.2 KB
  • references/wiring-checks.md5.6 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Integration checker

Check that components are connected and receive real data. A function can pass unit tests yet never be called; an endpoint can exist without being registered.

This skill reads and reports. Return fixes to the active implementation task or feature-lifecycle; do not create another approval round when fixes are already authorized.

Reference loading

Load references/wiring-checks.md for language detection, export exclusions, wiring states, data-flow failures, contract patterns, and the requirements map.

Phase 0: PRIME

Read repository instructions. In a feature pipeline, use .feature/state/implement/ to scope changed and added files. Otherwise use the requested path or diff; a requested full audit covers all source files. If the implementation artifact is missing, use the diff and state the gap.

Detect every language in scope. Reuse existing integration evidence for unchanged connections; trace affected producers and consumers beyond the diff where needed.

Gate: Scope and languages are known.

Phase 1: EXPORT/IMPORT MAP

Inventory public symbols using language-aware searches:

  • Go: exported package functions, types, constants, variables, and methods.
  • Python: module definitions, __all__, and __init__.py re-exports.
  • TypeScript/JavaScript: named/default exports and barrel re-exports.

Exclude dependencies, generated files, build output, fixtures, and repository metadata. Apply the reference's exceptions for public library APIs, plugin contracts, framework entrypoints, and other legitimate external consumers before calling a symbol orphaned.

For each symbol, record file, name, kind, and line. Find imports and actual usage; an import alone does not establish wiring. Classify as ORPHANED, IMPORTED_NOT_USED, or WIRED using the reference. Report failures first; show successful connections only in verbose mode.

Gate: Every in-scope symbol has a status or an explicit unresolved limitation.

Phase 2: DATA FLOW AND CONTRACT CHECK

Trace WIRED connections for real inputs and compatible contracts. Check hardcoded empty data, placeholders, dead parameters, mock remnants, shape/type mismatches, and event/message names using the reference.

Static inspection establishes structure and likely compatibility, not runtime correctness. Use existing runtime evidence where available; distinguish observed failures from uncertain dynamic-language matches. Low-confidence contract findings warn rather than fail.

Gate: Data-flow and contract findings include locations, evidence, and confidence.

Phase 3: REPORT

Report component counts, wiring failures, data-flow issues, contract mismatches, and concrete fixes. In pipeline mode, use .feature/state/plan/ to map each requirement from entrypoint to implementation as WIRED, PARTIAL, or UNWIRED.

Compute integration score as 100 * WIRED / (WIRED + IMPORTED_NOT_USED + ORPHANED); report N/A when the denominator is zero.

VerdictConditionNext action
PASSNo wiring, flow, or contract issuesContinue validation
WARNUnused imports or low-confidence contract findings onlyResolve or explain warnings
FAILOrphaned components, data-flow defects, or high-confidence contract mismatchesReturn concrete fixes to implementation

State incomplete coverage separately; missing source or unresolved scope cannot establish a PASS. Include circular imports as integration findings. For a large monorepo, narrow to affected connections unless the user requested a full audit; split a full audit into bounded scopes without silently omitting files.

Gate: Findings, limitations, and next actions are clear. After fixes, recheck affected connections rather than repeating unchanged analysis.

References

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Manage multiple Claude Code accounts: add, list, check, launch, and install shell aliases for 10+ isolated CLAUDE_CONFIG_DIR profiles.

The English summary is being prepared. Showing the original description.

notque/vexjoy-agent442Updated Oct 17, 2026

Improve architecture across modules by deepening interfaces.

The English summary is being prepared. Showing the original description.

notque/vexjoy-agent442Updated Oct 17, 2026

Assessment: read-only inspection, codebase overview, value analysis, health checks, ADR consultation, decision analysis, multi-perspective critique.

The English summary is being prepared. Showing the original description.

notque/vexjoy-agent442Updated Oct 17, 2026

Background memory consolidation — overnight review, merge, and injection payload for memory files.

The English summary is being prepared. Showing the original description.

notque/vexjoy-agent442Updated Oct 17, 2026

Jev-driven browser automation: Jev picks operations, programs execute, a text model writes field values only when Jev cannot pick one from the goal.

The English summary is being prepared. Showing the original description.

notque/vexjoy-agent442Updated Oct 17, 2026

Write, compose, integrate, and improve programs that call Jev, TypeSafe's System One judgment model.

The English summary is being prepared. Showing the original description.

notque/vexjoy-agent442Updated Oct 17, 2026

See all skills by notque

Report a problem with this skill