AC build-protocol
Rigorous workflow for producing long-form knowledge content (textbooks, knowledge bases, deep reports) with multi-agent collaboration. Use when the task requires >5,000 words, >2 parallel sub-agents, or >10 steps, or when the deliverable will be referenced long-term by the user. Enforces 8 iron rules (independent Audit unmissable / Plan before Execute / ≤2 parallel sub-agents for writing tasks / Why This Way reasoning / version + errata iteration / 3-layer consistency / anti-sycophancy content / independent review ≠ self-audit) and a 9-step standard workflow. Includes machine-verification scripts for PMID citations, red/green evaluation ratios, safety-keyword coverage, and H1-level checks. Triggers on explicit requests like 'build knowledge base / textbook / deep report' or implicitly on any long-form knowledge production.
Rigorous workflow for producing long-form knowledge content (textbooks, knowledge bases, deep reports) with multi-agent collaboration.
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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
- note
edit-residuethe text marks something as outdated (lines 96): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 58/100
- 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
- 30Running it twice. 4 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 31 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2013 tokens
- low 13 top-level sections: this looks like several domains in one skill
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
- +3Description length 834: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -215 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 14 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.