CB write-skill
Write a new agent skill or improve one without bloat: the edit ladder, levels, drift and size checks, full diets. (gstack)
Claims to write and refine agent skills without bloat: tracks edit levels, parameter drift, size and composition. Contains 2067 tokens of logic with one medium-severity finding and no lint errors. Quality scores at 74 (quality) and 66 (process) suggest functional code with architectural rough edges.
In practice, generates instructions for AI assistants via gstack framework. Supports 12 platforms from Claude to DeepSeek. Safety score 95 is solid. Catch: no model runs, so promised "diets" and drift control remain untested. Worth installing if you need a lean skill generator and plan to validate on your own models.
Write a new agent skill or improve one without bloat: the edit ladder, levels, drift and size checks, full diets.
As a process B 66/100 · Nearly there — 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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: Bash Read Write Edit Grep Glob AskUserQuestion
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "preamble-tier" - note
frontmatter-keyunknown frontmatter key "triggers"
Process rating: all ten parameters 66/100
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 6 mutating operations with no state check
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 12 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2067 tokens
- 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 (3 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 122: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.