agentleFS
Sign inStart free
FaisalAlqarniFaisalAlqarni/sp-ecc/skills/verification-loop/SKILL.md

verification-loop

Skill9 starsChanged 9 months agoMITView on GitHub

Use when verifying implementation correctness - provides a systematic loop for checking tests, lint, build, and runtime behavior

We split this skill into the rules it gives an agent

6 rules. 5 are common, 0 are distinctive, and 1 is very specific to this project.

  • 5

    Common

    Most of the 73 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Common:

    After completing a feature or significant code change

    line 13
  2. Common:

    Before creating a PR

    line 14
  3. Common:

    When you want to ensure quality gates pass

    line 15
  4. Common:

    If build fails, STOP and fix before continuing.

    line 28
  5. Common:

    After running all phases, produce a verification report:

    line 89
  6. Very specific:

    When invoked from sp-ecc:subagent-driven-development, follow this retry protocol:

    line 124

“Common” is measured: kept by at least 6 in 10 of the 73 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Verification Loop Skill

A comprehensive verification system for Claude Code sessions.

When to Use

Invoke this skill:

  • After completing a feature or significant code change
  • Before creating a PR
  • When you want to ensure quality gates pass
  • After refactoring

Verification Phases

Phase 1: Build Verification

# Check if project builds
npm run build 2>&1 | tail -20
# OR
pnpm build 2>&1 | tail -20

If build fails, STOP and fix before continuing.

Phase 2: Type Check

# TypeScript projects
npx tsc --noEmit 2>&1 | head -30

# Python projects
pyright . 2>&1 | head -30

Report all type errors. Fix critical ones before continuing.

Phase 3: Lint Check

# JavaScript/TypeScript
npm run lint 2>&1 | head -30

# Python
ruff check . 2>&1 | head -30

Phase 4: Test Suite

# Run tests with coverage
npm run test -- --coverage 2>&1 | tail -50

# Check coverage threshold
# Target: 80% minimum

Report:

  • Total tests: X
  • Passed: X
  • Failed: X
  • Coverage: X%

Phase 5: Security Scan

# Check for secrets
grep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10

# Check for console.log
grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10

Phase 6: Diff Review

# Show what changed
git diff --stat
git diff HEAD~1 --name-only

Review each changed file for:

  • Unintended changes
  • Missing error handling
  • Potential edge cases

Output Format

After running all phases, produce a verification report:

VERIFICATION REPORT
==================

Build:     [PASS/FAIL]
Types:     [PASS/FAIL] (X errors)
Lint:      [PASS/FAIL] (X warnings)
Tests:     [PASS/FAIL] (X/Y passed, Z% coverage)
Security:  [PASS/FAIL] (X issues)
Diff:      [X files changed]

Overall:   [READY/NOT READY] for PR

Issues to Fix:
1. ...
2. ...

Continuous Mode

For long sessions, run verification every 15 minutes or after major changes:

Set a mental checkpoint:
- After completing each function
- After finishing a component
- Before moving to next task

Run: /verify

Retry Protocol (Pipeline Mode)

When invoked from sp-ecc:subagent-driven-development, follow this retry protocol:

IF any phase fails:
  1. Dispatch fix subagent with specific failure details
  2. Fix subagent addresses ONLY the failures (no other changes)
  3. Re-run the full verification loop
  4. If fail again: repeat (max 3 attempts total)
  5. After 3 failures: STOP and report to user:
     "Verification failed 3 times. Remaining failures:
      - [list each failure with phase and details]
      Manual intervention needed."
  6. Write failure details to pipeline-state.md

Important: Each retry re-runs ALL phases, not just the failed one. A fix for one phase may break another.

Integration with Hooks

This skill complements PostToolUse hooks but provides deeper verification. Hooks catch issues immediately; this skill provides comprehensive review.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free