BC writing-triadic
Privacy-first 3-role writing framework with explicit consent controls. Creator mines intent via progressive Q&A (full) or Instant Mode (≤2 rounds, direct output), intelligent blend matching, Executor produces drafts with dual-temp writing (high creativity + low calibration) and multi-modal iteration, Reader scores with adaptive weighted review. Evolution Engine v2 adds preference drift + veto with consent-gated memory. v2.9 adds SEO Content Optimization Module; v2.9.1 adds a state contract and stable 100-point scoring for SEO/style extensions; v2.9.2 adds PRIVACY.md, consent gates for web research and style cloning, data minimization, and narrowed triggers. v2.10 adds Template #17 (WeChat Official Account), expanded 2026 AI fatigue word lists, and 3 new end-to-end examples (style cloning+SEO, instant mode, long-form). Style Cloning Engine, Long-Form Chapter Manager, and 17 templates retained.
As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 22. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 6412 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 54/100
- 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
- 30Running it twice. 2 mutating operations with no state check
- 55Failures and branches. 1 branches
- 70Execution cost. Instruction body is 6412 tokens
- 100Tools and files. No external tools needed
- 100Steps. 177 steps
- 100Consistency. Name and required fields are in place
- low 24 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 905: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -257 emoji in the instructions: noise for the model
- +2Single-language instructions
- +4Structure: 89 headings
- +3Step-by-step instructions: 177 items
- +4Has examples (29 code blocks)
- +4Reference files are cited in the instructions (14 of 14)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.