danielfortizv/sdd-comparative-study/tessl-spec-verification
Claude Code and agent skill by danielfortizv/sdd-comparative-study
- community
Checking that the SKILL.md file is still in the repository.
Verify that implementation and tests remain synchronized with specs after code changes. Use when code has been generated or modified from specs, after implementation is complete, or when reviewing a PR that touches spec-covered code. Reports mismatched targets, broken test links, and undocumented behavioral changes. Common triggers: "verify the spec", "check spec alignment", "are specs up to date", or after completing implementation work.
Install
npx vskill@latest install danielfortizv/sdd-comparative-study/tessl-spec-verificationSKILL.md
Spec Verification
Ensure code and tests still reflect the documented requirements. Detect and fix drift between specs, implementation, and tests.
When to use
- After implementation is complete (before marking work as done)
- When reviewing PRs that touch spec-covered code
- When
work-reviewflags potential spec drift - Periodically as a maintenance check
Steps
- Find all specs. Locate
.spec.mdfiles in the project'sspecs/directory:
``bash find specs/ -name "*.spec.md" 2>/dev/null ``
- Validate structural integrity. For each spec, check that links resolve:
- Verify each
targets:path exists (expand globs, confirm matches) - Verify each
[@test]link points to an existing test file - Confirm frontmatter has
name,description, and at least one target
``bash # Use the bundled validation scripts: ./scripts/validate-specs.sh specs/ ./scripts/check-spec-links.sh specs/ `` If either script reports failures, record them as broken-link findings.
- Run linked tests. Execute the test files referenced by
[@test]links:
``bash # Extract test paths from specs and run them grep -rh '\[@test\]' specs/*.spec.md | sed 's/.*\[@test\] *//' | sed 's/$//' ``` If tests fail, diagnose the failure. Determine whether the test, the code, or the spec is wrong before proceeding.
- Spot-check targets for drift. Read the files listed in
targets:and compare against spec requirements:
- For each requirement in the spec, confirm the target file implements it
- Look for logic in target files that contradicts the spec (edge cases, error handling, data contracts)
- Look for new behavior in target files not mentioned in any spec
- Check for drift signals:
- Behavioral changes in code not mentioned in the spec
- Newly added tests without matching requirements (or vice versa)
- Deleted or renamed files that still appear in
targets:or[@test]links - New code paths in target files that aren't covered by any requirement
- Fix drift. When drift is detected:
- If code changed behavior: update the spec first, then re-verify
- If spec is stale: update the spec to match current implementation
- If links are broken: update paths in frontmatter and
[@test]links - After fixes, re-run steps 2-3 to confirm everything resolves
Output
A verification report:
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingCalculadora/Etapa 1/Tessl/.agents/skills/tessl__spec-verification/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/danielfortizv/sdd-comparative-study/tessl-spec-verification)