verify
Skill14 starsChanged 37 days agoMITView on GitHub
Ensure code quality with systematic 6-phase verification loop. Use after feature completion, before PR creation, after refactoring, or for periodic quality checks. Keywords: verify, verification, check, validate, quality, build, lint, test, security, pr-ready.
- Reads credentials
188 other projects use a version of this.
Adopted by
Most recently taken up by
- Doist/todoist-aitheir own version, first seen Nov 9, 2026
- udecode/better-convextheir own version, first seen Nov 9, 2026
- pytorch/heliontheir own version, first seen Nov 8, 2026
- amir20/dozzletheir own version, first seen Nov 8, 2026
- Doist/todoist-clitheir own version, first seen Nov 8, 2026
- codewithmukesh/dotnet-claude-kittheir own version, first seen Nov 8, 2026
Used with
Projects with it also use instinct-export, instinct-import and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
TheKREATORSSkillinstinct-export
Export instincts from project/global scope to a file
Also in 3 projects that use this
TheKREATORSSkillinstinct-import
Import instincts from file or URL into project/global scope
Also in 3 projects that use this
AviadPSkillrisk-assess
Assess the risk and blast radius of a proposed code change before implementing it. Evaluates CI impact, framework-wide vs localized scope, rollback path, and identifies blindspots. Use when user says "what's the risk", "is this safe", "assess the impact", "risk assess", "blast radius", or before applying framework-wide or CI-affecting changes. Do NOT use for code quality review (use code-quality) or plan validation (use design-validator).
Also in 3 projects that use this
AaravChadhaSkillsecure
Security review with a confidence gate - a finding exists only with a concrete exploit scenario and a high/medium/low confidence rating; everything else goes to a worth-hardening list, never inflated. Sweeps five surfaces: auth gates, secrets hygiene, injection and unsafe sinks, unsafe deserialization/crypto/transport, and LLM tool-use trust boundaries. Reports only, never fixes. Use when the user asks for a security review or to check vulnerabilities, secrets, or auth.
Also in 3 projects that use this
ArvorCoSkillspecify
Create feature specification from natural language description. Use when starting a new feature or creating a spec. Triggers on: create spec, specify feature, new feature spec.
Also in 10 projects that use this
Jurel89Skillai-slop-cleaner
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
Also in 4 projects that use this
- +1 more from TheKREATORS
Other versions188 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 188
- react/react★ 252ksame name
- facebook/react★ 252ksame name
- garrytan/gstack★ 141ksame name
- oven-sh/bun★ 97ksame name
- anthropics/financial-services★ 41ksame name
- anthropics/financial-services-plugins★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- anthropics/claude-quickstarts★ 19ksame name
- NVIDIA-NeMo/Speech★ 19ksame name
178 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository44 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adaptSkill
- animateSkill
- auditSkill
- bolderSkill
- brainstormSkill
- build-fixSkill
- business-panelSkill
- checkpointSkill
- clarifySkill
- colorizeSkill
- composition-patternsSkill
- confidence-checkSkill
- config-doctorSkill
- critiqueSkill
- delightSkill
- design-auditSkill
- devils-advocateSkill
- distillSkill
- eval-harnessSkill
- feature-plannerSkill
- fix-prSkill
- frontend-designSkill
- gap-analysisSkill
- grill-with-docsSkill
- hardenSkill
- impeccableSkill
- layoutSkill
- learnSkill
- optimizeSkill
- overdriveSkill
- polishSkill
- pytest-runnerSkill
- python-best-practicesSkill
- quieterSkill
- react-best-practicesSkill
- sc-helpSkill
- security-auditSkill
- shapeSkill
- tddSkill
- typesetSkill
- ui-ux-pro-maxSkill
- uv-packageSkill
- web-design-guidelinesSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 167 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Ensure quality through systematic 6-phase verification after code changes and confirm PR-ready state.
- Distinctive: line 22
After feature implementation completion
- Very specific: line 23
Before PR creation (--pre-pr)
- Distinctive: line 52
Purpose: Verify type safety
- Distinctive: line 115
Purpose: Check security vulnerabilities and sensitive information exposure
- Very specific: line 248
After function/component completion → /verify quick
- Very specific: line 249
After 15 minutes elapsed → /verify
“Common” is measured: kept by at least 6 in 10 of the 167 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.
Files
Dynamic Context
Current working state:
!git status --short 2>/dev/null
Recent changes:
!git diff --stat 2>/dev/null | tail -5
Verification Loop Skill
Purpose
Ensure quality through systematic 6-phase verification after code changes and confirm PR-ready state.
Core Principle: Build failure → Immediate stop → Fix issue → Re-verify
Activation Triggers
- After feature implementation completion
- Before PR creation (
--pre-pr) - After refactoring work
- Periodic quality checks (15-min intervals or major component completion)
- User explicit request:
/verify,verify,check
6-Phase Verification Pipeline
Phase 1: Build Verification 🔨
Purpose: Confirm project compilation/build success
# JavaScript/TypeScript
npm run build || pnpm build || yarn build
# Python
python -m py_compile src/**/*.py
# Go
go build ./...
# Rust
cargo buildOn Failure: 🚨 Immediate stop - Build error resolution is top priority
Phase 2: Type Checking 📝
Purpose: Verify type safety
# TypeScript
npx tsc --noEmit
# Python (with type hints)
pyright src/ || mypy src/
# Flow
npx flow checkOutput: Type error count and locations
Phase 3: Linting 🔍
Purpose: Detect code style and potential issues
# JavaScript/TypeScript
npm run lint || npx eslint src/
# Python
ruff check src/ || flake8 src/
# Go
golangci-lint run
# Rust
cargo clippyOutput: Lint violation count and severity
Phase 4: Testing 🧪
Purpose: Confirm test passing and coverage
# JavaScript/TypeScript
npm test -- --coverage
# Python
pytest --cov=src --cov-report=term-missing
# Go
go test -cover ./...
# Rust
cargo testCriteria:
- ✅ All tests pass
- ✅ Coverage ≥ 80% (business logic)
- ⚠️ Coverage < 80% → Show warning
Phase 5: Security Scanning 🛡️
Purpose: Check security vulnerabilities and sensitive information exposure
5.1 Secrets Detection:
# Check .env, credentials, API keys
grep -r "PRIVATE_KEY\|SECRET\|PASSWORD\|API_KEY" src/ --include="*.ts" --include="*.js" --include="*.py"5.2 Debug Statement Detection:
# Check console.log, print, debugger
grep -rn "console\.log\|console\.debug\|debugger" src/ --include="*.ts" --include="*.tsx" --include="*.js"
grep -rn "print(" src/ --include="*.py" | grep -v "# noqa"5.3 Dependency Vulnerabilities (optional):
npm audit --audit-level=high
pip-auditOutput: List of discovered security issues
Phase 6: Diff Review 📋
Purpose: Final review of changes
git diff --stat
git diff HEAD~1 --name-onlyReview Items:
- No unintended file changes
- No missing error handling
- Edge case handling confirmed
- Unnecessary console.log/print removed
- No hardcoded values
Verification Modes
Quick Mode (/verify quick)
Fast verification - Execute Build + Type Check only
Phase 1: Build ✅
Phase 2: Types ✅
⏱️ Complete: ~30 secondsFull Mode (/verify or /verify full)
Complete 6-phase verification
Phase 1: Build ✅
Phase 2: Types ✅
Phase 3: Lint ✅
Phase 4: Tests ✅ (Coverage: 85%)
Phase 5: Security ✅
Phase 6: Diff ✅
⏱️ Complete: ~2-5 minutesPre-PR Mode (/verify pre-pr)
Strict verification before PR submission (Enhanced security)
Phase 1-6: Full verification
+ Additional security scan
+ Dependency vulnerability check
+ Commit message reviewPre-Commit Mode (/verify pre-commit)
Quick verification before commit
Phase 1: Build ✅
Phase 2: Types ✅
Phase 3: Lint ✅
Phase 5: Security (secrets only) ✅Report Format
Success Report
╔══════════════════════════════════════════════════════╗
║ 🎯 VERIFICATION REPORT ║
╠══════════════════════════════════════════════════════╣
║ Phase 1: Build ✅ OK ║
║ Phase 2: Type Check ✅ OK ║
║ Phase 3: Lint ✅ OK (0 issues) ║
║ Phase 4: Tests ✅ OK (47/47 passed, 85% cov) ║
║ Phase 5: Security ✅ OK (0 issues) ║
║ Phase 6: Diff Review ✅ OK (3 files changed) ║
╠══════════════════════════════════════════════════════╣
║ 📊 Total Issues: 0 ║
║ 🚀 PR Ready: YES ║
╚══════════════════════════════════════════════════════╝Failure Report
╔══════════════════════════════════════════════════════╗
║ 🎯 VERIFICATION REPORT ║
╠══════════════════════════════════════════════════════╣
║ Phase 1: Build ✅ OK ║
║ Phase 2: Type Check ❌ FAIL (3 errors) ║
║ → src/api/user.ts:45 - Type 'string' not assignable║
║ → src/utils/format.ts:12 - Missing return type ║
║ → src/components/Card.tsx:78 - Property missing ║
║ Phase 3: Lint ⚠️ WARN (2 warnings) ║
║ Phase 4: Tests ⏸️ SKIPPED (blocked by Phase 2)║
║ Phase 5: Security ⏸️ SKIPPED ║
║ Phase 6: Diff Review ⏸️ SKIPPED ║
╠══════════════════════════════════════════════════════╣
║ 📊 Total Issues: 5 ║
║ 🚀 PR Ready: NO ║
║ ║
║ 🔧 Suggested Fixes: ║
║ 1. Fix type errors in src/api/user.ts:45 ║
║ 2. Add return type to formatDate function ║
║ 3. Add missing 'onClick' prop to Card component ║
╚══════════════════════════════════════════════════════╝Periodic Verification Strategy
Mental Checkpoints
- After function/component completion →
/verify quick - After 15 minutes elapsed →
/verify - Major milestone completed →
/verify full
Session Integration
Start work
│
├─→ Feature implementation
│ │
│ └─→ [15min elapsed] → /verify quick
│
├─→ Component completion
│ │
│ └─→ /verify
│
├─→ Feature completion
│ │
│ └─→ /verify full
│
└─→ PR preparation
│
└─→ /verify pre-prIntegration with Other Skills
With /checkpoint
/checkpoint create "before-refactor"
... refactoring work ...
/verify full
/checkpoint verify "before-refactor" # Compare changesWith /feature-planner
Auto-execute /verify at each Phase Quality Gate
Auto-Fix Suggestions
Suggest automatic fixes on verification failure:
| Issue Type | Suggested Fix |
| Type Error | Add/modify type annotation |
| Lint Error | npm run lint -- --fix or ruff --fix |
| Missing Test | Suggest test case creation |
| console.log | Remove line or replace with logger |
| Security Issue | Suggest moving to environment variables |
Configuration
Project-specific configuration (.claude/verify.config.json):
{
"coverageThreshold": 80,
"skipPhases": [],
"customCommands": {
"build": "pnpm build",
"test": "pnpm test:ci",
"lint": "pnpm lint"
},
"securityPatterns": [
"API_KEY",
"SECRET",
"PASSWORD",
"PRIVATE_KEY"
],
"ignoreFiles": [
"**/*.test.ts",
"**/*.spec.ts",
"**/fixtures/**"
]
}Quick Reference
| Command | Description |
/verify | Full 6-phase verification |
/verify quick | Verify Build + Type only |
/verify pre-pr | Strict verification before PR |
/verify pre-commit | Quick verification before commit |
/verify --fix | Fix auto-fixable issues |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.

