figure-first-paper-reader

Reads a paper figure by figure before re-integrating the full narrative, so the user can identify the core findings quickly and check whether each visual actually supports the authors' main claims. Always separate figure content, figure-linked claim, evidentiary strength, and unsupported interpretation. Never fabricate references, PMIDs, DOIs, figure content, panel labels, result values, or study details that were not actually provided.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./awesome-med-research-skills/Evidence Insight/figure-first-paper-reader/SKILL.md

Quality

Content

67%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.

The body is well-structured and actionable, with a clear sequenced workflow and genuinely useful one-level-deep reference modules. The main weakness is conciseness — the same guidance is restated across four near-duplicate sections that could be consolidated.

Suggestions

Consolidate the redundant directive sections — 'Core Function', 'Hard Rules', 'What This Skill Should Not Do', and 'Quality Standard' overlap heavily; merge the 'should not' list and the 15 hard rules into a single concise rules section.

Move the duplicated 'separate observed content from attached interpretation' and 'never fabricate' guidance to the relevant reference modules and reference them once instead of repeating inline.

Consider promoting the 15 Hard Rules into a dedicated reference file (e.g. references/integrity-and-rules.md) so SKILL.md stays a lean overview plus the 8-step workflow.

Dimension	Reasoning	Score
Conciseness	The body is on-topic and avoids explaining concepts Claude already knows, but it restates the same directives across multiple redundant sections — 'Core Function', 'Hard Rules' (15 rules), 'What This Skill Should Not Do', and 'Quality Standard' all repeat 'separate observed content from claim', 'don't confuse striking with strong', and 'never fabricate' — and could be consolidated.	3 / 5
Actionability	As an instruction-only skill it provides concrete, specific guidance: an ordered 8-step execution sequence that names the reference module to apply at each step, explicit output sections A–H with required fields, and specific classification taxonomies (support levels, figure types), leaving only minor judgment gaps to Claude.	4 / 5
Workflow Clarity	The 8 steps are clearly sequenced and Step 8 provides an explicit self-critical final-check checkpoint; this is an analysis (not destructive/batch) workflow so the destructive-cap does not apply, though the checkpoint is a review pass rather than a validate→fix→retry feedback loop.	4 / 5
Progressive Disclosure	The body is an overview-plus-workflow that points to 7 real one-level-deep reference modules, each clearly signaled with a 'Use for/Use when' purpose annotation; the minor gap is that several directive sections are inlined in SKILL.md rather than consolidated into the reference files.	4 / 5
	Total	15 / 20 Passed

Description

75%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 is specific, distinctive, and clearly states what the skill does, but it lacks an explicit 'when to use' trigger clause, which the rubric caps at completeness 3. Adding a 'Use when...' sentence with broader trigger synonyms would raise the score.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to read a paper figure by figure, check whether figures support the claims, or get a fast figure-first read before deciding whether to read the full paper.'

Broaden trigger keywords to include synonyms users naturally say — 'chart', 'plot', 'panel', 'graph', 'figures support the conclusion' — alongside 'figure' and 'paper'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Reads a paper figure by figure', 're-integrating the full narrative', 'identify the core findings', 'check whether each visual actually supports the authors' main claims', and 'separate figure content, figure-linked claim, evidentiary strength, and unsupported interpretation' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	The 'what' is clearly and specifically stated, but there is no explicit 'Use when...' clause or equivalent trigger guidance for when Claude should invoke the skill; per the rubric a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Contains natural terms a user would say — 'paper', 'figure', 'figure by figure', 'core findings', 'claims', 'visual' — but omits common synonyms and variants (e.g. 'chart', 'plot', 'panel', 'graph', '.pdf'), so a few natural terms are missing.	4 / 5
Distinctiveness Conflict Risk	The 'figure-first' / 'figure-to-claim' framing carves a clear niche that is explicitly contrasted with generic paper summaries, yielding distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
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: awesome-med-research-skills/Evidence Insight/figure-first-paper-reader/SKILL.md
Commit: 63c61d3

Reviewed: 8 hours ago

Table of Contents

Discovery Implementation Validation

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.