BC skill-creator-claude
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
As a process C 62/100 · Has gaps — weak spots: inputs and preconditions, running it twice
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
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Dangerous commands
cmd-autorun-instructionREADME.md:39Instructs the agent to auto-run a script on every session| 3 | "Package and Present": removed the `present_files` tool condition, simplified to always run `package_skill.py` | `present_files` is a Claude Code-exclusive tool |
-
low Dangerous commands
cmd-autorun-instructionSKILL.md:443Instructs the agent to auto-run a script on every session (quoted — discussed, not commanded)**IMPORTANT — generate the eval viewer before evaluating inputs yourself**: Whether you're in Claude Code, Cowork, or any other platform with a filesystem, always run `generate_review.py` after tests
quoted
Files scanned: 20. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7578 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 62/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 17 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Steps. 70 steps, 4 vague phrases
- 70Failures and branches. 18 branches
- 70Execution cost. Instruction body is 7578 tokens
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (9 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)
- -35 of 9 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 320: enough signal without eating the budget
- +4Structure: 33 headings
- +3Step-by-step instructions: 70 items
- +3Output format is stated explicitly
- +4Has examples (15 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.