AC paper-deep-reader
Very helpful in deep-reading one selected research paper, journal article, arXiv paper, working paper, technical report, benchmark paper, dataset paper, replication study, or synthesis paper and producing a rigorous markdown reading note, technical summary, critique, or implementation memo. Always use when the task requires reconstructing equations, notation, derivations, theorems, estimators, algorithms, empirical identification, experiments, benchmark design, dataset construction, figures, tables, appendix evidence, assumptions, limitations, or literature context across fields such as machine learning, statistics, physics, economics, quantitative finance, systems, and related technical disciplines. Not for shallow abstract rewrites or broad multi-paper surveys unless the selected paper itself is a survey or synthesis.
As a process C 54/100 · 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: 37. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "slug"
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
- 30Running it twice. 6 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Failures and branches. 5 branches
- 100Steps. 107 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2599 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 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 831: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 27 headings
- +3Step-by-step instructions: 107 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (5 of 6)
- +3All 6 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.