AF research-mentor-distiller
Use this skill when the user wants to distill a real researcher, professor, advisor, lab, or research community into an evidence-grounded cyber mentor skill from papers, academic homepages, talks, interviews, CVs, Google Scholar/Semantic Scholar/OpenAlex/arXiv records, PDFs, Zotero libraries, or provided source folders. Applies to building, updating, validating, or critiquing mentor/persona skills that capture research taste, worldview, methodology, problem-selection heuristics, evaluation standards, writing preferences, cross-direction research methodology, direction-specific methodology, and mentor interaction protocols.
Use this skill when the user wants to distill a real researcher, professor, advisor, lab, or research community into an evidence-grounded cyber mentor skill…
As a process F 63/100 · Will not run — References files that are not bundled: references/evidence-snapshot.md, references/publication-index.md, references/research-taste-profile.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/evidence-snapshot.md - warning
missing-refreference to a missing file: references/publication-index.md - warning
missing-refreference to a missing file: references/research-taste-profile.md - warning
missing-refreference to a missing file: references/fulltext-distillation.md - warning
missing-refreference to a missing file: references/validation.md
Process rating: all ten parameters 63/100
- 0Tools and files. 5 referenced file(s) missing: references/evidence-snapshot.md, references/publication-index.md, references/research-taste-profile.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 9 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 85 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3553 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 6 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 630: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 85 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.