CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

find-paper-references

Automatically find references for academic paper Markdown files. Reads full paper text, identifies each knowledge point requiring citation (epidemiological data, mechanism descriptions, existing research conclusions, etc.), searches PubMed for 3-5 most relevant articles per kn...

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A strong, highly actionable workflow skill: concrete commands verified against the real script bundle, explicit feedback loops for the batch search, and clear scope boundaries toward sibling formatting skills. Its main weaknesses are minor: duplicated NCBI API key content and detail about a script this skill never invokes.

DimensionReasoningScore

Conciseness

The workflow is dense and imperative with no padding of concepts Claude already knows, but NCBI API key setup is given twice (Step 0 and the later 'NCBI API Key (Optional, Free)' section) and ~15 lines document remap_refs.py's marker-format tolerance even though 'remap_refs.py — ... (not called by this skill)'. These minor instances could be trimmed.

4 / 5

Actionability

Guidance is copy-paste ready and verified against the actual bundle: the Step 4 command 'python "SKILL_DIR/scripts/batch_search.py" "%TEMP%\ref_queries.json" --max 5' matches batch_search.py's real CLI, the input/output JSON schemas are shown verbatim, and naming rules include worked examples ('TRIM3_ferroptosis.md → TRIM3_ferroptosis_refs.md') plus a before/after marker insertion example.

5 / 5

Workflow Clarity

Steps 0–8 are explicitly sequenced with validation checkpoints and feedback loops for this batch operation: 'If any result is empty, create a new JSON file with adjusted keywords and re-run', 'if fewer than 30, return to Step 2', and word-count-based target ranges for Reviews; plus protective rules ('Do not overwrite the original file', 'Do not run remap_refs.py or convert_to_docx.py').

5 / 5

Progressive Disclosure

The three scripts are listed up front with roles and the main entry point flagged, and each is referenced by relative path exactly where used; however the ~300-line body inlines material (article-type citation rules, API-key details split across two sections) that could live in reference files, leaving minor organization gaps.

4 / 5

Total

18

/

20

Passed

Description

66%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description communicates a specific, distinct capability with concrete actions and domain keywords, but it is literally truncated mid-sentence and omits any 'when to use this' trigger guidance. Fixing the truncation and adding a Use-when clause would raise it to the top anchors.

Suggestions

Restore the truncated text — the description ends mid-word at 'per kn...', losing the remainder of the final action and leaving the 1024-char budget mostly unused.

Add an explicit trigger clause, e.g. 'Use when the user has an academic paper in Markdown and asks to find, add, or check citations/references for it.'

Include natural synonyms users would actually say: 'citations', 'bibliography', 'literature search', and the '.md' file extension.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Reads full paper text', 'identifies each knowledge point requiring citation (epidemiological data, mechanism descriptions...)', 'searches PubMed for 3-5 most relevant articles' — but the field is literally truncated mid-word ('per kn...'), so coverage is incomplete rather than comprehensive.

4 / 5

Completeness

The 'what' is clear and detailed, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3; the truncation ('per kn...') further cuts off the final stated action.

3 / 5

Trigger Term Quality

Good natural keywords are present ('references', 'citation', 'academic paper', 'Markdown files', 'PubMed'), but common variations users would say are missing — 'bibliography', 'literature search', 'cite', and the '.md' extension.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (finding PubMed references for academic Markdown papers) that is distinguishable from the sibling format-references-endnote/zotero skills, but those siblings share the 'references' keyword family, leaving minor overlap risk on queries like 'add references to my paper'.

4 / 5

Total

15

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

aipoch/medical-research-skills

Path

scientific-skills/Academic Writing/find-paper-references/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.