AC systemic-protagonist
Renders a market, protocol, institution, codebase, supply chain, disease, or ecosystem as a legible protagonist without faking agency. Builds the POSIWID character sheet (revealed objective function vs. stated purpose), the agency ledger of verb repairs, the gateway-proxy admission test, the traveling-object device, the instrumented threshold scene, and climax by constraint violation. Use when the subject of a piece is a system rather than a person, when a draft says "the market decided" or "the industry learned", when analysis reads as a data dump with no protagonist, or when user mentions systemic narrative, system as character, POSIWID, anthropomorphism, agency laundering, follow the flow, or institution as protagonist.
Renders a market, protocol, institution, codebase, supply chain, disease, or ecosystem as a legible protagonist without faking agency.
As a process C 50/100 · 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 50/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 70Execution cost. Instruction body is 4816 tokens
- 100Steps. 45 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 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
- +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
- +5Description quotes 2 example trigger phrases
- +3Description length 732: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.