AC logic-pacer
Rewrite EXISTING admired Chinese/English expository prose so its reasoning is easier to follow — shrink the inferential STEP SIZE and re-anchor each step on ground the reader already holds (given-new), while KEEPING the voice, the vocabulary (never 对齐词汇), the facts/claims/stance, and staying lean (net length <= ~1.3x). Method: detect >=2-move leaps, unfold each into its minimal chain, subtract ornament. Use for "这段逻辑跳太快，放慢但别动文风/词汇", "reduce the inferential step size", "$logic-pacer". ABSTAIN if the prose is already followable. NOT de-AI (→humanizer-academic), NOT simplify-words/对齐词汇, NOT summarize/translate, NOT reorder points, NOT generate new prose.
Rewrite EXISTING admired Chinese/English expository prose so its reasoning is easier to follow — shrink the inferential STEP SIZE and re-anchor each step on…
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Write Edit Bash Task
Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 46 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2132 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 659: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 46 items
- +4Reference files are cited in the instructions (4 of 4)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.