sdd-verify
Skill0 starsChanged 29 days agoApache-2.0View on GitHub
Use when every task in tasks.md is checked, or before calling a feature done, merging or releasing it. Traces every requirement to its tasks and to evidence produced now, and writes verify.md - flagging anything uncovered instead of passing it.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- svg153/skillstheir own version, first seen Nov 1, 2026
- PedroMosquera/squadaitheir own version, first seen Oct 13, 2026
- pchemguy/Skill-SDD-Managertheir own version, first seen Oct 6, 2026
- callingcard1973/claude-skillstheir own version, first seen Apr 17, 2026
- Maicololiveras/praxisgenai-agent-orchestratortheir own version, first seen Mar 16, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- PedroMosquera/squadai★ 10same name
- Maicololiveras/praxisgenai-agent-orchestrator★ 1same name
- svg153/skills★ 1same name
- callingcard1973/claude-skills★ 0same name
- pchemguy/Skill-SDD-Manager★ 0same name
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 repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- sdd-constitutionSkill
- sdd-implementSkill
- sdd-planSkill
- sddSkill
- sdd-specifySkill
- sdd-tasksSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
2
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 13
Before anything else, read these if they exist.
- Very specific: line 24
Write every artifact in language.
- Very specific: line 29
Run verify_command. If it is empty, use the test command in <specs_dir>/constitution.md.
- Distinctive: line 48
PASS: only if the suite passed, every non-removed requirement is ✅, and no task is unticked.
- Very specific: line 54
Write verify.md from the template.
“Common” is measured: kept by at least 6 in 10 of the 5 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
SDD — Verify
Verification answers one question with evidence: does the system do what the spec says?
Its output, verify.md, is the record a reviewer reads before accepting the feature.
Step 0 — Load project settings
Before anything else, read these if they exist. Missing files are normal; use the defaults.
.sdd/config.yamlin the project, else~/.sdd/config.yaml. Defaults:specs_dir: specs,language: en,ids: {requirement: REQ, task: T},gates: [specify, plan, tasks],verify_command: "",phases: [constitution, specify, plan, tasks, implement, verify].- Template:
.sdd/templates/verify.md, else~/.sdd/templates/verify.md, elsetemplates/verify.mdnext to this file. - Extra rules:
.sdd/rules/all.mdand.sdd/rules/verify.md(project, then global). They add to this skill; when they conflict with it, they win.
Write every artifact in language. Use the configured ID prefixes everywhere this skill
says REQ or T.
Step 1 — Run the suite
Run verify_command. If it is empty, use the test command in
<specs_dir>/constitution.md; if there is none, ask the user. Keep the last 20 lines of
the real output and the exit status. Do not summarize from memory or from an earlier run.
Step 2 — Trace every requirement
For each requirement in spec.md (skip ~~removed~~ ones):
- Tasks — which tasks in
tasks.mdcite it. - Evidence — produced in this run: the test that exercises its acceptance criteria and its result, or a manual check you perform now with what you observed. "The code handles it" is not evidence.
- Status — ✅ covered (evidence passes) · ⚠️ partial (some acceptance criteria not exercised) · ❌ uncovered (no task, or no evidence, or evidence fails).
Also collect: tasks that cite no requirement (scope creep), and unticked tasks.
Step 3 — Verdict
PASS only if the suite passed, every non-removed requirement is ✅, and no task is unticked. Anything else is FAIL. Never mark ✅ without evidence produced in this run, and never round ⚠️ up to ✅.
Step 4 — Write verify.md
Write verify.md from the template. On FAIL, fill "Next actions" with where to go back
to: a missing requirement → sdd-specify; a requirement with no task → sdd-tasks; a
failing check → sdd-implement.
Show the user the verdict and the traceability table.
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.