BC scene-construction-scam
Builds scenes that are reported rather than generated, by running a four-slot SCAM qualification gate (Setting, Character, Action, Meaning) with a source required per slot, a scene floor and ceiling, the 1-of-20 telling-detail cut with a provenance veto, the RUE pass, and a scene/summary narrative-distance audit against per-form ratio targets. Every technique has a person variant and a system variant (market, protocol, institution, codebase, supply chain). Use when turning research notes into a scene, opening a section with a moment, deciding whether a passage is a scene or summary, or auditing whether a vivid paragraph is actually sourced, or when user mentions scene, SCAM, show don't tell, telling detail, scene vs summary, summary in costume, establishing shot, make this vivid, or in medias res.
Builds scenes that are reported rather than generated, by running a four-slot SCAM qualification gate (Setting, Character, Action, Meaning) with a source…
As a process C 55/100 · Has gaps — weak spots: result and completion, 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: 6. 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
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Execution cost. Instruction body is 4249 tokens
- 100Steps. 46 steps
- 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
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 808: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 10 headings
- +3Step-by-step instructions: 46 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.