BC ladder-of-abstraction
Moves prose deliberately between the concrete and the abstract and stops it stranding in the middle rung where bureaucratic prose lives. Tags every paragraph R1 (named particulars) to R4 (meaning), enforces run rules, detects the middle-rung trap, repairs it by climbing down to a real particular rather than simplifying vocabulary, gates the top rung with a counter-sentence test, and closes with an A-frame descent. Use when a draft reads as dense, vague, or jargon-heavy, when a readability score fails, when a conclusion feels grandiose or unearned, when technical material will not land for a general reader, or when user mentions ladder of abstraction, too abstract, too vague, concrete example, middle rung, dead zone, jargon, altitude, zoom in, zoom out, and thus capitalism.
Moves prose deliberately between the concrete and the abstract and stops it stranding in the middle rung where bureaucratic prose lives.
As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 4. 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 56/100
- 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
- 30Running it twice. 6 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 44 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3588 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- high The skill tells the model to perform an irreversible action with no human approval
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 783: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 44 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.