BC mcphee-structure-derivation
Derives a document's structure out of its own corpus instead of picking one off a menu, using John McPhee's coding-and-sorting procedure - cold read, short topic codes one per card, a strict chronology sort run against a strict theme sort, a logged list of every disagreement resolved toward chronology, candidate juxtapositions gated by a state-and-footnote test, a named shape, and an invisibility test. Use when you hold researched material and have no structure yet, when a draft has turned into concept-named sections full of time-scrambled evidence, when deciding whether a flashback is earned, or when user mentions McPhee, coding pass, index cards, deriving structure, chronology versus theme, structure from material, or "what shape is this piece".
Derives a document's structure out of its own corpus instead of picking one off a menu, using John McPhee's coding-and-sorting procedure - cold read, short…
As a process C 55/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 5. 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 55/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 41 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3832 tokens
- 100Progress reporting. Reports progress
- 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
- +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 757: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 41 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.