asset-validation
Skill1 starsChanged 4 days agoApache-2.0View on GitHub
审查可复用技能、插件、规则和 Agent；需要行为验证时运行真实 CLI 验收。不用于普通应用测试。
1 other project uses a version of this.
Adopted by
Most recently taken up by
- alex-voloshin-dev/ai-skillstheir own version, first seen May 17, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- alex-voloshin-dev/ai-skills★ 2same 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 repository13 other files it gives its agents.
- agent-conductSkill
- awesome-presentationSkill
- browser-harnessSkill
- changelog-writingSkill
- debian-testvmSkill
- feature-deliverySkill
- herdrSkill
- persistent-ssh-opsSkill
- provision-xray-hy2-nodeSkill
- public-acceptanceSkill
- repo-knowledge-graphSkill
- tddSkill
- trigger-build-workflowSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Behavioral acceptance / real CLI evaluation: use acceptance.md for isolation, task design, observation, and cleanup.
- Distinctive: line 14
Use Codex for real CLI acceptance by default.
- Distinctive: line 20
Keep edits and generated evidence within the authorized asset and task paths.
- Distinctive: line 21
Keep credentials and settings contents out of output.
- Very specific: line 25
When the existing workflow needs or the user requests a standalone acceptance report, default to REPORT.html and read the HTML report …
≈ “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
Asset Validation
Choose the requested outcome
- Review / audit: inspect the asset and relevant references, report concrete findings, and run proportionate static checks. Use review-and-fix.md. Do not launch ACC or modify the asset unless the request includes those actions.
- Fix / iterate: implement the requested corrections and verify affected behavior. A documentation edit does not automatically require full acceptance.
- Behavioral acceptance / real CLI evaluation: use acceptance.md for isolation, task design, observation, and cleanup. A static review cannot establish a behavioral PASS.
Use Codex for real CLI acceptance by default. Use Claude Code only when the user explicitly selects it; an unavailable Codex must not silently trigger a Claude fallback.
Infer the route from the requested deliverable and existing authorization. Ask only when a missing choice changes scope, cost, or permitted side effects. An already specified asset, purpose, or CLI needs no reconfirmation. If an asset is named without a requested operation, start with a brief read-only assessment.
Shared boundaries
- Keep edits and generated evidence within the authorized asset and task paths. Do not write memory, host configuration, or global installation state unless requested.
- Keep credentials and settings contents out of output; report paths and redacted evidence.
- Preserve unrelated changes. Use task-private scratch directories and clean only resources created by this task.
- Distinguish inspection, format checks, script execution, and observed Agent behavior in the result. Do not manufacture a PASS from work performed on behalf of the asset-under-test.
- Continue authorized fixes and relevant verification to completion; a new approval is needed only when the next action exceeds that authorization.
- When the existing workflow needs or the user requests a standalone acceptance report, default to
REPORT.htmland read the HTML report standard. Preserve existing JSON contracts; ordinary static review does not require an extra report.
References
Load only the route needed for the current task:
- Review and focused fixes: static findings and canonical skill validation.
- Behavioral acceptance: real CLI execution, evidence, and cleanup.
- Asset identification: ambiguous asset types or acceptance registration.
The CLI is scripts/acc.ts, relative to this skill directory. Its Bun runtime, DB, and round mechanics belong to the behavioral acceptance route; ordinary review does not need them.
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.