AC research-lookup
Compiles current scholarly evidence for a scientific manuscript or research brief when the user explicitly asks to gather literature, references, background evidence, competing findings, or a manuscript research packet. Uses Parallel Search by default, Parallel Extract for source retrieval, Parallel Research for explicitly deep/exhaustive work, optional explicit Parallel Chat, and optional Perplexity only when requested or allowed as a failure fallback.
Compiles current scholarly evidence for a scientific manuscript or research brief when the user explicitly asks to gather literature, references, background…
As a process C 64/100 · Has gaps — weak spots: 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 264): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 64/100
- 30Inputs and preconditions. Does not say what the process needs to start
- 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, 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
- 70Execution cost. Instruction body is 4009 tokens
- 85Steps. 66 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 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)
- -31 of 2 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 457: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 66 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.
In the sandbox The scripts kept to themselves
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Запущено 2 скрипта; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
Из них 1 не дошёл до работы, и об их поведении мы ничего не узнали.
scripts/manuscript_packet.py | ничего за пределами своей папки |
scripts/research_lookup.py | не запустился: python research_lookup.py "comprehensive quantum error correction review" --force-backend research --processor pro |
5 Oct 2026