edercnj/x-lib-verify-group

Global Output Policy

• Language: English ONLY.
• Tone: Technical, Direct, and Concise.
• Efficiency: Remove all conversational fillers and greetings to save tokens.

Skill: Group Verifier (Library)

Purpose

Runs between each parallelism group (G1-G7) during Phase 2 of the feature lifecycle. Compiles the code, classifies any errors, decides whether to retry or escalate, and extracts created file contents for the next group's dependency inputs.

When Called

| Caller Skill | Phase | Context | |-------------|-------|---------| | x-implement-story | Phase 2 | After each group completes, BEFORE starting the next group | | x-implement-task | Implementation | Inline build gate between layer groups |

Inputs

| Input | Type | Description | |-------|------|-------------| | Group ID | G1\|G2\|G3\|G4\|G5\|G6\|G7 | The parallelism group to verify | | Task outputs | File list | Files created/modified by tasks in the completed group |

Procedure

Step 1 — Compile

{{COMPILE_COMMAND}}

Capture: exit code + stderr output.

For G7 (Tests group), use the full build command instead:

{{BUILD_COMMAND}}

Step 2 — Analyze

• If exit code = 0 -> Go to STEP 5 (success)
• If exit code != 0 -> Parse error output, go to STEP 3

Step 3 — Classify Errors

Classify errors based on the {{LANGUAGE}} compiler/interpreter output. The patterns below are common across languages — adapt to the specific error messages produced by your toolchain:

| Error Category | Classification | Meaning | | ----------------------------------------------------- | ------------------ | --------------------------------- | | Missing type/symbol from a PREVIOUS group | MISSING_DEPENDENCY | Previous group regression | | Missing type/symbol from the CURRENT group | TASK_ERROR | Current task produced bad code | | Type mismatch / incompatible types | TASK_ERROR | Wrong types in current task | | Missing package/module from previous group | MISSING_DEPENDENCY | Previous group incomplete | | Missing external dependency | BUILD_ERROR | Missing dependency in build file | | Interface/contract mismatch | TASK_ERROR | Implementation doesn't match port | | Unhandled error/exception | TASK_ERROR | Missing error handling | | Any other error | UNKNOWN | Needs investigation |

Step 4 — Decide

| Classification | Attempt | Action | | ------------------ | ------- | ------------------------------------------------- | | TASK_ERROR | 1st | RETRY same tier, add error message to prompt | | TASK_ERROR | 2nd | RETRY same tier, add both errors to prompt | | TASK_ERROR | 3rd | ESCALATE to next tier (Junior->Mid, Mid->Senior) | | MISSING_DEPENDENCY | any | HALT pipeline, flag previous group regression | | BUILD_ERROR | any | HALT pipeline, report missing dependency | | UNKNOWN | 1st | ESCALATE immediately to next tier | | UNKNOWN | 2nd | HALT pipeline, flag for manual intervention |

Escalation path: Junior -> Mid -> Senior -> Manual intervention

When retrying a task:

1. Re-read the output from the failed attempt
2. Add to the retry prompt: ## COMPILATION ERROR\n{error message}\n## FIX INSTRUCTIONS\nThe previous attempt produced this error. Fix it.
3. Re-launch with the same tier (or escalated tier)

Step 5 — Extract Outputs

For each task in the completed group:

1. Read all files listed in task.files_created
2. Read all files listed in task.files_modified
3. Store content for use as dependency inputs in subsequent groups

Step 6 — Commit

After successful compilation:

git add {all files from this group}
git commit -m "{group commit message}"

Group commit messages follow Conventional Commits format (see rules/06-git-conventions.md for scopes):

feat({scope}): add {group description} for STORY-ID

Derive the {scope} from the architecture layer being committed. The scopes table in rules/06-git-conventions.md defines the valid scopes for your project. Example pattern:

• G1: feat(domain): add foundation models and migration for STORY-ID
• G2: feat(domain): add ports, DTOs, and engine for STORY-ID
• G3-G5: Use the scope matching the adapter layer (e.g., persistence, api, config)
• G6: feat(observability): add tracing and metrics for STORY-ID
• G7: test: add tests for STORY-ID

Step 7 — Report

Group G{N} verified: {PASS|FAIL}
  Tasks: {N} completed, {N} retried, {N} escalated
  Files: {N} created, {N} modified
  Warnings: {N}
  {If escalation: "ESCALATION: T{X} from {tier} -> {next_tier} (reason: {error})"}

---

G7 Extended Verification

G7 uses {{BUILD_COMMAND}} instead of {{COMPILE_COMMAND}}:

Additional checks:

1. Parse test results from build reports
2. Count: tests, failures, errors, skipped
3. Parse coverage report
4. Verify: line coverage >= 95%, branch coverage >= 90%

If tests fail:

• Classify failing tests by the task that created them
• Retry the test task with the failure message
• If test depends on production code from another task, check production code first

Error Handling

| Scenario | Action | |----------|--------| | Compilation fails with TASK_ERROR (1st attempt) | Retry same tier with error message in prompt | | Compilation fails with TASK_ERROR (2nd attempt) | Retry same tier with both errors in prompt | | Compilation fails with TASK_ERROR (3rd attempt) | Escalate to next tier (Junior -> Mid -> Senior) | | MISSING_DEPENDENCY detected | Halt pipeline, flag previous group regression | | BUILD_ERROR (missing external dependency) | Halt pipeline, report missing dependency in build file | | UNKNOWN error (1st attempt) | Escalate immediately to next tier | | UNKNOWN error (2nd attempt) | Halt pipeline, flag for manual intervention | | Senior-tier escalation exhausted | Halt pipeline, flag for manual intervention |

Integration Notes

| Skill | Relationship | Context | |-------|-------------|---------| | x-implement-story | called-by | Invoked during Phase 2 after each group | | x-implement-task | called-by | Build gate between layer groups during implementation |

• Uses {{COMPILE_COMMAND}} for G1-G6, {{BUILD_COMMAND}} for G7
• Produces atomic commits per group (rollback points)