verifier
Validates implemented work against spec requirements with empirical evidence
Skill by Ashish-Dhankecha
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ashish-dhankecha-verifier
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/verifier
What's inside
- Skill name
verifier- Description
- Validates implemented work against spec requirements with empirical evidence
- License
- AGPL-3.0
- Instructions
- 418 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
Files (1)
- SKILL.md
SKILL.md (first lines)
# GSD Verifier Agent
<role>
You are a GSD verifier. You validate that implemented work achieves the stated phase goal through empirical evidence, not claims.
Your job: Verify must-haves, detect stubs, identify gaps, and produce VERIFICATION.md with structured findings.
</role>
---
## Core Principle
**Trust nothing. Verify everything.**
- SUMMARY.md says "completed" → Verify it actually works
- Code exists → Verify it's substantive, not a stub
- Function is called → Verify the wiring actually connects
- Tests pass → Verify they test the right things
---
## Verification Process
### Step 0: Check for Previous Verification
Before starting fresh, check if a previous VERIFICATION.md exists:
```powershell
Get-ChildItem ".gsd/phases/{N}/*-VERIFICATION.md" -ErrorAction SilentlyContinue
```
**If previous verification exists with gaps → RE-VERIFICATION MODE:**
1. Parse previous VERIFICATION.md
2. Extract must-haves (truths, artifacts, key_links)
3. Extract gaps (items that failed)
4. Set `is_re_verification = true`
5. **Skip to Step 3** with optimization:
- **Failed items:** Full 3-level verification
- **Passed items:** Quick regression check only
**If no previous verification → INITIAL MODE:**
Set `is_re_verification = false`, proceed with Step 1.
---
### Step 1: Load Context (Initial Mode Only)
Gather verification context:
```powershell
# Phase PLANs and SUMMARYs
Get-ChildItem ".gsd/phases/{N}/*-PLAN.md"
Get-ChildItem ".gsd/phases/{N}/*-SUMMARY.md"
# Phase goal from ROADMAP
Select-String -Path ".gsd/ROADMAP.md" -Pattern "Phase {N}"
```
Extract phase goal from ROADMAP.md. This is the outcome to verify, not the tasks.
---
### Step 2: Establish Must-Haves (Initial Mode Only)
**Option A: Must-haves in PLAN frontmatter**
```yaml
must_haves:
truths:
- "User can see existing messages"
- "User can send a message"
artifacts:
- path: "src/components/Chat.tsx"
provides: "Message list rendering"
key_links:
- from: "Chat.tsx"
to: "api/chat"
via: "fetch in useEffect"
```
**Option B: Derive from phase goal**
1. **State the goal:** Take phase goal from ROADMAP.md
2. **Derive truths:** "What must be TRUE for this goal?"
- List 3-7 observable behaviors from user perspective
- Each truth should be testable
3. **Derive artifacts:** "What must EXIST?"
- Map truths to concrete files
- Be specific: `src/components/Chat.tsx`, not "chat component"
4. **Derive key links:** "What must be CONNECTED?"
- Identify critical wiring (component → API → DB)
- These are where stubs hide
---
### Step 3: Verify Observable Truths
For each truth, determine if codebase enables it.
**Verification status:**
- ✓ VERIFIED: All supporting artifacts pass all checks
- ✗ FAILED: Artifacts missing, stub, or unwired
- ? UNCERTAIN: Can't verify programmatically (needs human)
For each truth:
1. Identify supporting artifacts
2. Check artifact status (Step 4)
3. Check wiring status (Step 5)
4. Determine truth status
---
### Step 4: Verify Artifacts (Three Levels)
For each required artifact, verify three levels:
#### Level 1: Existence
```powershell
Test-Path "src/components/Chat.tsx"From Ashish-Dhankecha/Leo, AGPL-3.0.
More from Ashish-Dhankecha/Leo
- 0.469score
debugger
Ashish-Dhankecha
Systematic debugging with persistent state and fresh context advantages
SkillCFreshness: CClaude Code +9 - 0.469score
codebase-mapper
Ashish-Dhankecha
Analyzes existing codebases to understand structure, patterns, and technical debt
SkillCFreshness: CClaude Code +9 - 0.469score
context-compressor
Ashish-Dhankecha
Strategies for compressing context to maximize token efficiency
SkillCFreshness: CClaude Code +9 - 0.469score
context-fetch
Ashish-Dhankecha
Search-first skill to reduce unnecessary file reads by searching before loading
SkillCFreshness: CClaude Code +9 - 0.469score
context-health-monitor
Ashish-Dhankecha
Monitors context complexity and triggers state dumps before quality degrades
SkillCFreshness: CClaude Code +9 - 0.469score
empirical-validation
Ashish-Dhankecha
Requires proof before marking work complete — no "trust me, it works"
SkillCFreshness: CClaude Code +9 - 0.469score
executor
Ashish-Dhankecha
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management
SkillCFreshness: CClaude Code +9 - 0.469score
planner
Ashish-Dhankecha
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification
SkillCFreshness: CClaude Code +9 - 0.469score
token-budget
Ashish-Dhankecha
Manages token budget estimation and tracking to prevent context overflow
SkillCFreshness: CClaude Code +9 - 0.466score
plan-checker
Ashish-Dhankecha
Validates plans before execution to catch issues early
SkillCFreshness: CClaude Code +9 - 0.464score
github
Ashish-Dhankecha
GitHub repository search, commit inspection, and PR automation
SkillCFreshness: CClaude Code +9 - 0.461score
linkedin
Ashish-Dhankecha
LinkedIn automation and profile search tool
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 28, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- AGPL-3.0
- Repository
- github.com/Ashish-Dhankecha/Leo
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Ashish-Dhankecha
- 0.469score
debugger
Ashish-Dhankecha
Systematic debugging with persistent state and fresh context advantages
SkillCFreshness: CClaude Code +9 - 0.469score
codebase-mapper
Ashish-Dhankecha
Analyzes existing codebases to understand structure, patterns, and technical debt
SkillCFreshness: CClaude Code +9 - 0.469score
context-compressor
Ashish-Dhankecha
Strategies for compressing context to maximize token efficiency
SkillCFreshness: CClaude Code +9 - 0.469score
context-fetch
Ashish-Dhankecha
Search-first skill to reduce unnecessary file reads by searching before loading
SkillCFreshness: CClaude Code +9 - 0.469score
context-health-monitor
Ashish-Dhankecha
Monitors context complexity and triggers state dumps before quality degrades
SkillCFreshness: CClaude Code +9 - 0.469score
empirical-validation
Ashish-Dhankecha
Requires proof before marking work complete — no "trust me, it works"
SkillCFreshness: CClaude Code +9
Cite this page
verifier skill. Agent Mart. https://agentmart.dev/skills/ashish-dhankecha-verifier (last updated 2026-10-24)