BC skill-reviewer
Score and grade AgentSkills across four dimensions: design quality, content quality, security, and usability. Use when asked to score, grade, evaluate, or rate a skill's quality — producing a numeric scorecard with dimension-by-dimension ratings. Triggers on "score this skill", "grade skill", "rate skill quality", "evaluate skill", "skill scorecard", "给技能打分", "技能评分".
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 7
✓ No critical or high findings
Medium and low: 7
-
medium Dangerous commands
cmd-pipe-to-shellreferences/security.md:65Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)| C3 | Remote execution: curl\|bash, wget\|sh, eval $(curl), pip install from HTTP URLs | |
security skill -
low Risky intent
intent-offensive-securityreferences/security.md:44Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# C8: Privilege escalation
-
low Risky intent
intent-offensive-securityreferences/security.md:63Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| C1 | Credential harvesting: reads API keys/tokens in code AND makes network calls | Both must be present in same file |
-
low Dangerous commands
cmd-privilegereferences/security.md:70Privilege escalation / world-writable permissions (documentation of a security skill)| C8 | Privilege escalation: sudo, chmod 777, setuid, writes to system paths | In executable code, not docs |
security skill -
low Risky intent
intent-offensive-securityreferences/security.md:70Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| C8 | Privilege escalation: sudo, chmod 777, setuid, writes to system paths | In executable code, not docs |
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Score and grade AgentSkills across four dimensions: design quality… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (skill-reviewer) differs from the folder (skill-quality-auditor)
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 4 branches
- 100Tools and files. No external tools needed
- 100Steps. 14 steps
- 100Execution cost. Instruction body is 680 tokens
- 100Running it twice. No mutating operations
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 369: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.