Design, improve, and evaluate reusable agent skills with high-quality SKILL.md files, precise trigger descriptions, progressive disclosure, and testable behavior. This skill should be used when users ask to create a new skill, rewrite or review an existing skill, audit a skill collection such as `config/source/skills` for redundancy or overlap, improve skill trigger quality, organize skill references, or evaluate whether a skill should trigger and behave correctly.
SkillScore68Maintained
Automatic
◆AI Engineer pack
Last verified 8/23/2026
What it changes
Passed 14 of 21 test cases with the skill, and 10 of 21 without it.
Without skill45%
With skill68%
Checks it passed that the model alone missed
The instructions specify running npm run build:skill-manifest.
The proposed frontmatter rewrite includes an explicit version field.
The review flags external raw markdown fetch URLs as security risks.
and 4 more in the full report
5 fixed10 passed either way7 still failing0 broke
Pass-rate lift
+23 pp
Tokens
+48%
Agent turns
0%
Response time
-22%
Model gemini-3.6-flashMeasured 8/23/2026v315 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 4
Prompt
After updating skill metadata in `plugin/cloudbase`, which build command must be executed to finalize the skill package?
What was checked, without and with the skill
Checked
Without skill
With skill
The instructions specify running npm run build:skill-manifest.
Missed
Passed
case-15 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md98 lines8 files
Skill Authoring
Create and refine reusable agent skills with better trigger quality, cleaner structure, stronger behavioral guidance, and more reliable evaluation.
When to use this skill
Use this skill when you need to:
Create a new SKILL.md
Improve an existing skill's name or description
Review whether a skill is too broad, too narrow, or poorly structured
Audit a local skill collection such as config/source/skills for redundancy, trigger overlap, or weak boundaries
Split a large skill into SKILL.md plus references/, assets/, or scripts/
Design evaluation prompts and review whether a skill triggers and behaves correctly
Repo-managed CloudBase skill review
When the task targets config/source/skills, apply these guardrails in addition to the normal skill-authoring workflow:
This section is the repo-managed CloudBase skill review baseline for this repository.
Keep frontmatter complete and normalized, including version
Keep examples inside the skill's declared platform and scope
Keep shared operational rules in one canonical source instead of copying large blocks across neighboring skills
If the skill claims a rule is mandatory, show that rule in at least one example
When giving a recommended default, also explain the tradeoff behind it
Do not add agent-directed remote skill-fetch URLs (for example cnb.cool/.../git/raw/... skill bodies or (standalone fallback: ...) raw links). Marketplace reviewers treat those as injection / session-hijack risk.
Prefer local relative sibling paths (../other-skill/SKILL.md). If a sibling is missing, tell the agent to ask the user to install the full CloudBase plugin or skills pack — never to HTTP-fetch remote skill markdown into context.
Human documentation URLs (docs.cloudbase.net, console pages) remain allowed when they are not skill-body fetch instructions.
Do not infer public CNB / OpenClaw / ClawHub paths from the source tree when writing marketplace-facing install docs; verify the actual published structure first.
Do NOT use for:
General documentation writing that is not about skills
README polish or marketing copy
Prompt tweaks that do not affect skill structure or behavior