CC claude-code
Delegate coding to Claude Code CLI (features, PRs).
Delegate coding to Claude Code CLI (features, PRs).
As a process C 63/100 · Has gaps — weak spots: when it triggers, execution cost, running it twice
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 1
-
high Dangerous commands
cmd-destructive-fsSKILL.md:632Destructive filesystem command (wipes root/home/drive) (detector / deny-list definition)"hooks": [{"type": "command", "command": "if echo \"$CLAUDE_TOOL_INPUT\" | grep -qE 'rm -rf|git push.*--force|:(){ :|:& };:'; then echo 'Dangerous command blocked!' && exit 2; fi"}]detector
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whenneither description nor a "## When to Use" section says when to use the skill - warning
body-longSKILL.md body ≈ 8451 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 63/100
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 24 mutating operations with no state check
- 40Execution cost. Instruction body is 8451 tokens: crowds the task out of the window
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 60Consistency. The Hermes dialect needs category and tags
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 76 steps, 1 vague phrases
- 100Result and completion. Output format and completion criterion are stated
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 20 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (26 tags): a typed call is more reliable
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 51: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 72 headings
- +3Step-by-step instructions: 76 items
- +3Output format is stated explicitly
- +4Has examples (33 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.