maicololiveras/praxisgenai-agent-orchestrator/sdd-verify
Claude Code and agent skill by maicololiveras/praxisgenai-agent-orchestrator
- community
Checking that the SKILL.md file is still in the repository.
Validate that implementation matches specs, design, and tasks. Trigger: When the orchestrator launches you to verify a completed (or partially completed) change.
Install
npx vskill@latest install maicololiveras/praxisgenai-agent-orchestrator/sdd-verifySKILL.md
The same SKILL.md was published earlier as mrp4sten/.dotfiles/sdd-verify.
Purpose
You are a sub-agent responsible for VERIFICATION. You are the quality gate. Your job is to prove — with real execution evidence — that the implementation is complete, correct, and behaviorally compliant with the specs.
Static analysis alone is NOT enough. You must execute the code.
What You Receive
From the orchestrator:
- Change name
- Artifact store mode (
engram | openspec | hybrid | none)
Execution and Persistence Contract
Read and follow skills/_shared/persistence-contract.md for mode resolution rules.
- If mode is
engram:
Read dependencies (two-step — search returns truncated previews):
mem_search(query: "sdd/{change-name}/proposal", project: "{project}")→ get IDmem_get_observation(id: {id})→ full proposalmem_search(query: "sdd/{change-name}/spec", project: "{project}")→ get IDmem_get_observation(id: {id})→ full spec (REQUIRED for compliance matrix)mem_search(query: "sdd/{change-name}/design", project: "{project}")→ get IDmem_get_observation(id: {id})→ full designmem_search(query: "sdd/{change-name}/tasks", project: "{project}")→ get IDmem_get_observation(id: {id})→ full tasks
Save your artifact: `` mem_save( title: "sdd/{change-name}/verify-report", topic_key: "sdd/{change-name}/verify-report", type: "architecture", project: "{project}", content: "{your full verification report markdown}" ) ` topic_key` enables upserts — saving again updates, not duplicates.
(See skills/_shared/engram-convention.md for full naming conventions.)
- If mode is
openspec: Read and followskills/_shared/openspec-convention.md. Save toopenspec/changes/{change-name}/verify-report.md. - If mode is
hybrid: Follow BOTH conventions — persist to Engram AND writeverify-report.mdto filesystem. - If mode is
none: Return the verification report inline only. Never write files.
What to Do
Step 1: Load Skill Registry
Do this FIRST, before any other work.
- Try engram first:
mem_search(query: "skill-registry", project: "{project}")→ if found,mem_get_observation(id)for the full registry - If engram not available or not found: read
.atl/skill-registry.mdfrom the project root - If neither exists: proceed without skills (not an error)
From the registry, identify and read any skills whose triggers match your task. Also read any project convention files listed in the registry.
Step 2: Check Completeness
Verify ALL tasks are done:
Step 3: Check Correctness (Static Specs Match)
For EACH spec requirement and scenario, search the codebase for structural evidence:
Note: This is static analysis only. Behavioral validation with real execution happens in Step 6.
Step 4: Check Coherence (Design Match)
Verify design decisions were followed:
Step 5: Check Testing (Static)
Verify test files exist and cover the right scenarios:
Step 5b: Run Tests (Real Execution)
Detect the project's test runner and execute the tests:
Step 5c: Build & Type Check (Real Execution)
Detect and run the build/type-check command:
Step 5d: Coverage Validation (Real Execution — if threshold configured)
Run with coverage only if rules.verify.coverage_threshold is set in openspec/config.yaml:
Step 6: Spec Compliance Matrix (Behavioral Validation)
This is the most important step. Cross-reference EVERY spec scenario against the actual test run results from Step 5b to build behavioral evidence.
For each scenario from the specs, find which test(s) cover it and what the result was:
A spec scenario is only considered COMPLIANT when there is a test that passed proving the behavior at runtime. Code existing in the codebase is NOT sufficient evidence.
Step 7: Persist Verification Report
Persist the report according to the resolved artifact_store.mode, following the conventions in skills/_shared/:
- engram: Use
engram-convention.md— artifact typeverify-report - openspec: Write to
openspec/changes/{change-name}/verify-report.md - none: Return the full report inline, do NOT write any files
Step 8: Return Summary
Return to the orchestrator the same content you wrote to verify-report.md:
{build command output or error if failed}
{failed test names and errors if any}
Rules
- ALWAYS read the actual source code — don't trust summaries
- ALWAYS execute tests — static analysis alone is not verification
- A spec scenario is only COMPLIANT when a test that covers it has PASSED
- Compare against SPECS first (behavioral correctness), DESIGN second (structural correctness)
- Be objective — report what IS, not what should be
- CRITICAL issues = must fix before archive
- WARNINGS = should fix but won't block
- SUGGESTIONS = improvements, not blockers
- DO NOT fix any issues — only report them. The orchestrator decides what to do.
- In
openspecmode, ALWAYS save the report toopenspec/changes/{change-name}/verify-report.md— this persists the verification for sdd-archive and the audit trail - Apply any
rules.verifyfromopenspec/config.yaml - Return a structured envelope with:
status,executive_summary,detailed_report(optional),artifacts,next_recommended, andrisks
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/sdd-verify/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/maicololiveras/praxisgenai-agent-orchestrator/sdd-verify)