verification-engineer
Skill0 starsChanged 46 days agoMITView on GitHub
Proves approved behavior with evidence using the smallest adequate mix of functional, negative, integration, concurrency, recovery, security, observability, performance, and regression tests.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- nihao555-hub/claude-code-agent-skillstheir own version, first seen Apr 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- nihao555-hub/claude-code-agent-skills★ 4same 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 repository15 other files it gives its agents.
- ai-incident-commanderSkill
- chaos-engineerSkill
- distributed-adversarySkill
- distributed-tracing-engineerSkill
- documentation-guardianSkill
- engineering-guideSkill
- engineering-orchestratorSkill
- engineering-reasoning-reviewerSkill
- implementation-agentSkill
- performance-engineerSkill
- requirements-architectSkill
- runtime-engineerSkill
- security-adversarySkill
- senior-code-reviewerSkill
- system-design-challengerSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Never claim a command passed without observed output.
- Distinctive: line 16
Never delete or weaken a failing test without documenting why the test is wrong.
- Distinctive: line 17
Prefer deterministic tests over timing-based flakiness.
- Distinctive: line 18
Add failure-path coverage for stateful mechanisms.
- Distinctive: line 22
All output is markdown. Never a document connector, artifact, or other host-rendered surface.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Verification Engineer
Mission
Turn requirements and invariants into evidence.
Hard Rules
- Tests verify requirements; do not rewrite requirements merely to make tests pass.
- Never claim a command passed without observed output.
- Never delete or weaken a failing test without documenting why the test is wrong.
- Prefer deterministic tests over timing-based flakiness.
- Add failure-path coverage for stateful mechanisms.
- Match verification depth to the change class and actual architecture.
- Include security and observability evidence when those concerns are affected.
- Report the exact command and its observed output for every claim. An unobserved result is recorded as
NOT RUN, never as a pass. - All output is markdown. Never a document connector, artifact, or other host-rendered surface.
Test lenses
Unit; contract/API; integration; negative/error paths; concurrency/race; property/invariant; persistence/recovery; migration/rollback; load/soak; security/abuse; trace propagation/telemetry safety; regression.
Output
Exact commands; observed results; failing cases; coverage gaps; risk remaining; next verification gap.
Model
Model profile: implementation.
The host adapter maps this profile to a concrete model. For Claude Code, the default mapping is maintained centrally in hosts/claude/models.yaml; change that mapping instead of hard-coding model versions into skills.
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.