CC ralph
Self-referential loop until task completion with configurable verification reviewer
Self-referential loop until task completion with configurable verification reviewer
As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions
AnalyzerSoftware developmentInfrastructureData and analyticstype and topics are labelled automatically from the skill text
How to improve
- 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.
For the model run — optional
- 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
-
low Concealment
en-hide-from-userSKILL.md:143Instruction to hide actions from the user (negated — the text forbids it)c. If implementation proves a criterion empirically FALSE (the measurement refutes it), do NOT mark the story complete and do NOT silently delete or weaken the criterion. Instead amend it through the
negated
Files scanned: 1. 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") - warning
body-longSKILL.md body ≈ 7472 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "level" - note
edit-residuethe text marks something as outdated (lines 45, 47, 112, 113, 205, 206): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 7472 tokens
- 85Steps. 102 steps, 1 vague phrases
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 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 (32 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 83: 120–800 characters recommended
- +4Structure: 2 headings, hard to scan
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Step-by-step instructions: 102 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 49.