BC four-dimensional-deep-reading
Four-Dimensional Deep Reading skill. Triggers when: (1) User provides a book title or file for analysis (2) Multi-perspective breakdown of content is needed (3) First principles, structured notes, counterarguments, and random identity perspectives are desired. Summons 4 virtual personas to read simultaneously, then synthesizes and saves to reports folder. Supports multi-language output (English/Chinese/Japanese/Korean/etc.). Version 1.8.0 - Added export functionality (Anki/Obsidian/Notion) + Flashcard generation.
As a process C 60/100 · Has gaps — weak spots: inputs and preconditions, execution cost, running it twice
How to improve
- 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: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 7, column 14: description: Four-Dimensional Deep Reading skill. Triggers when: (1) User provi… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
body-longSKILL.md body ≈ 20015 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "author_website" - note
frontmatter-keyunknown frontmatter key "author_brand" - note
frontmatter-keyunknown frontmatter key "author_pen_name"
Process rating: all ten parameters 60/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 10Execution cost. Instruction body is 20015 tokens: crowds the task out of the window
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 110 steps, 1 vague phrases
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- low 33 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)
- -242 emoji in the instructions: noise for the model
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +3Description length 518: enough signal without eating the budget
- +4Structure: 143 headings
- +3Step-by-step instructions: 110 items
- +3Output format is stated explicitly
- +4Has examples (83 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +2Bilingual instructions (RU + EN)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.