AB paper-deep-reading
Deep-read research papers into source-aware reports, traceable claim evidence, and research-direction seeds. Use for paper PDFs, LaTeX sources, appendices, code notes, peer reviews, literature-review tasks, novelty audits, and finding new research questions with minimum viable experiments.
As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions, progress reporting
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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Secrets in code
secret-high-entropy-tokentemplates/latex_paragraphs.template.json:6High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"paragraph_id": "P-se…001",
quoted -
low Secrets in code
secret-high-entropy-tokentemplates/traceability_manifest.template.json:18High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"paragraph_id": "P-se…008",
detector
Files scanned: 20. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6303 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 6303 tokens
- 100Steps. 292 steps
- 100Failures and branches. 18 branches, has a failure section
- 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
- low 19 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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +3Description length 290: enough signal without eating the budget
- +4Structure: 40 headings
- +3Step-by-step instructions: 292 items
- +4Reference files are cited in the instructions (3 of 4)
- +3All 4 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.