BC auto-improve
GAN-style iterative improvement loop for any text artifact. Mutates a file, grades each change against a rubric with a SEPARATE model, keeps only verified wins (pairwise-judged), reverts the rest. The git history is the improvement log. Use when the user wants to autonomously improve the quality of a document, email, prompt, landing page, README, contract, or any text file.
The skill promises an autonomous text improvement loop: mutates a file, grades each change with a separate model, compares results pairwise, reverts losses. Git history logs the improvements. Sounds like a machine that refines text without human intervention.
Grade B, quality 85, process 57—the gap suggests implementation issues. No critical findings, but the process score flags gaps. Supports all major platforms. 39 files, 7 scripts, but no sandbox or model runs—unclear if the loop actually works or remains a concept with code. Reverts and comparisons are untested.
Install cautiously: the idea holds water, but without real model runs, you won't know if the evaluator hangs on iteration three or actually reverts losers.
GAN-style iterative improvement loop for any text artifact.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 · 0
✓ No critical or high findings
Files scanned: 37. 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 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 7 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 541 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (4 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
- +2Single-language instructions
- +3Description length 376: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 7 items
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.