Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add full-stack-skills/agent-skills --skill skill-official-evaluationgit clone --depth 1 https://github.com/full-stack-skills/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/full-stack-skills/agent-skills/skill-official-evaluation)<a href="https://agentmods.dev/skills/full-stack-skills/agent-skills/skill-official-evaluation"><img src="https://agentmods.dev/badge/skills/full-stack-skills/agent-skills/skill-official-evaluation.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00200 | $0.03308 |
| Opus 5 | $0.00100 | $0.01654 |
| Sonnet 5 | $0.00040 | $0.00662 |
| Haiku 4.5 | $0.00020 | $0.00331 |
Grade A, and why
skill-official-evaluation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use this skill
ALWAYS use this skill when the user asks to:
- Review a skill for compliance with the official Agent Skills specification
- Check whether a skill's frontmatter, directory structure, or naming follows the rules
- Evaluate a skill's description triggering quality against official best practices
- Audit a skill's script safety (non-interactive,
--help, secrets, structured output) - Generate an official-style evaluation report with Pass/Needs-improvement conclusions
- Verify progressive disclosure is implemented correctly
- Scan for security issues (hardcoded secrets, suspicious instructions)
- "审查技能合规" (review skill compliance), "官方规范评估" (official spec evaluation)
- "Skill 规范检查" (skill spec check), "技能安全审计" (skill security audit)
- "检查 SKILL.md 格式" (check SKILL.md format), "检查技能结构" (check skill structure)
- "生成官方评估报告" (generate official evaluation report)
- "根据官方规范评估技能" (evaluate skill against official spec)
- "这个 Skill 符合规范吗" (does this skill comply with the spec)
Trigger phrases include:
- "帮我审查这个 Skill 是否符合规范" (help me review whether this skill complies with spec)
- "检查这个技能的 SKILL.md 格式对不对" (check if this skill's SKILL.md format is correct)
- "这个技能的 frontmatter 合规吗" (is this skill's frontmatter compliant)
- "审计一下这个技能的脚本安全性" (audit this skill's script safety)
- "按照 agentskills.io 规范评估这个技能" (evaluate this skill against agentskills.io spec)
- "review this skill for official spec compliance"
- "check if my skill follows the official specification"
- "generate an official evaluation report for this skill"
- "does this skill meet the agentskills.io requirements"
When NOT to use (near-miss boundaries):
- User wants a multi-dimensional quality score with radar charts → use
skill-trace-evaluationinstead (TRACE model covers T/R/A/C/E, while official evaluation focuses on spec compliance) - User wants to learn how to design a skill (know the rules, not evaluate a specific skill) → use
skill-awesomeinstead - User wants to organize skill documentation into an index → use
skill-awesomeinstead - User asks for general code review (not related to Agent Skills) → this skill is scoped to Agent Skills ecosystem only
IMPORTANT: Official Evaluation vs TRACE Evaluation — Two Different Evaluation Models:
This skill and skill-trace-evaluation evaluate skills using different frameworks:
-
Official Evaluation (this skill): Based on the official Agent Skills specification from agentskills.io. Checks structural compliance, naming rules, frontmatter correctness, and script safety. Answers "Does this skill follow the rules?"
-
TRACE Evaluation (different skill): Based on the SkillHub TRACE quality model. Scores across Trust, Reliability, Adaptability, Convention, and Effectiveness. Produces radar charts and per-dimension scores. Answers "How good is this skill?"
When both skills could apply:
- If the user says "evaluate this skill" or "review this skill" without specifying a framework, ask: "I can evaluate this skill using either the official specification (agentskills.io compliance) or the TRACE quality model (five-dimension scoring with radar charts). Which would you prefer?"
- If the user explicitly mentions "official spec", "agentskills.io", "compliance", "format check" → use this skill
- If the user explicitly mentions "TRACE", "quality score", "radar chart", "five dimensions" → use
skill-trace-evaluation
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 258 lines · 200 tokens per session scan A e1b7226d6892
skill-official-evaluation is a skill published in the GitHub repository full-stack-skills/agent-skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 200 tokens to every session and 3,308 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…