SKILLEMALL.ai
GitHub ↗ RU Sign in

CF lit-sync

Sync research references from .bib files to Zotero library + Obsidian literature notes. Extract cross-cutting concept notes when enough literature accumulates. Works after /search-lit or standalone.

Aperivue/medsci-skills Agent Skills author: Aperivue MIT 8 files · 4 scripts body ≈ 5 734 tokens Open the sourcegithub.com↗ analyzed 33 h ago

Sync research references from .bib files to Zotero library + Obsidian literature notes. Extract cross-cutting concept notes when enough literature…

As a process F 60/100 · Will not run — References files that are not bundled: references/zotero_collection.json, references/fulltext_retrieval.json

ReferenceObsidianData and analyticsInfrastructuretype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
83/100
safety, quality, tests
Safety 60%
97
Quality 40%
63
Run on models
none yet
Process rating
F
60/100
Will not run
References files that are not bundled: references/zotero_collection.json, references/fulltext_retrieval.json
Tools and files w 18
0
Result and completion w 14
0
When it triggers w 12
70
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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 · 3

✓ No critical or high findings

Medium and low: 3
  • low Secrets in code secret-high-entropy-token references/bbt_lookup.md:54
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    BBT's default pattern is author + title words + year: `smit…024`.
    detector
  • low Secrets in code secret-high-entropy-token SKILL.md:92
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    #     Better BibTeX keys look like `smit…024`
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:228
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    "citekeys_verified": ["smit…024", "..."]
    placeholder

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5734 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/zotero_collection.json
  • warning missing-ref reference to a missing file: references/fulltext_retrieval.json
  • note frontmatter-key unknown frontmatter key "triggers"
  • note frontmatter-key unknown frontmatter key "tools"
  • note edit-residue the text marks something as outdated (lines 168, 287): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 60/100

Will not run. References files that are not bundled: references/zotero_collection.json, references/fulltext_retrieval.json
  • 0Tools and files. 2 referenced file(s) missing: references/zotero_collection.json, references/fulltext_retrieval.json
  • 0Result and completion. Does not say what the result is
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 5734 tokens
  • 85Steps. 57 steps, 2 vague phrases
  • 100Inputs and preconditions. Inputs and preconditions are listed
  • 100Failures and branches. 3 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 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)
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 198: enough signal without eating the budget
  • +4Structure: 42 headings
  • +3Step-by-step instructions: 57 items
  • +4Has examples (15 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.