paper-narrative

Shape the scientific story across a manuscript, abstract, figures, and evidence. Use when a task asks for paper structure, figure order, argument flow, missing analyses, or manuscript revision strategy.

Quality

85%

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

Quality

Content

86%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 tight, well-sequenced instruction-only skill that assumes Claude's competence and gives specific actionable steps with clear routing to sibling skills. The main gap is the absence of a worked example showing the expected revision-plan output.

Suggestions

Add a brief worked example or template of the expected revision-plan output (e.g. claim → evidence arc → per-figure decision) to lift actionability from concrete to fully copy-paste-ready.

Consider an explicit final review step such as 'Re-read the plan end-to-end and confirm each figure decision is backed by a stated piece of evidence' to add a lightweight validation checkpoint.

Optionally include one or two example trigger phrasings a user might say (e.g. 'help me reorganize my figures') to bridge the description triggers and the in-skill workflow.

Dimension	Reasoning	Score
Conciseness	Lean ~14-line body with no padding and no explanation of concepts Claude already knows; every line is direct instruction, so every token earns its place.	5 / 5
Actionability	Concrete, specific guidance ('Extract the central claim, audience, evidence chain, figure order...'; 'Reorder, merge, split, or cut sections and panels based on the argument') with explicit routing to figure-composer/figure-style, but lacks worked examples of the expected revision-plan output format.	4 / 5
Workflow Clarity	A clear five-step sequence that is well ordered and routes sub-tasks to sibling skills, but it has no explicit review/validation checkpoint; this is acceptable since the skill produces a plan rather than performing destructive or batch operations, so no cap applies.	4 / 5
Progressive Disclosure	Under 50 lines with no need for external references and no bundle files present; the single organized Workflow section is appropriate structure for a skill of this size, qualifying for the top anchor under the simple-skill exception.	5 / 5
	Total	18 / 20 Passed

Description

83%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.

A well-crafted description that clearly states both capability and trigger conditions with natural, specific language. It is concise and largely free of fluff, with only minor room to add synonyms and sharpen the core action verb.

Dimension	Reasoning	Score
Specificity	Names the domain and several specific components ('manuscript, abstract, figures, and evidence') but the core action 'shape the scientific story' is somewhat abstract rather than a list of concrete operations, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' ('Shape the scientific story across a manuscript, abstract, figures, and evidence') and 'when' ('Use when a task asks for...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Strong natural trigger phrases ('paper structure, figure order, argument flow, missing analyses, or manuscript revision strategy') that users would actually say, though a few synonyms (e.g. 'drafting', 'story') are missing and no file-extension terms apply to this domain.	4 / 5
Distinctiveness Conflict Risk	Clear niche (scientific paper narrative) with distinct triggers and minimal conflict risk, but there is minor overlap with closely related figure skills (figure-composer, figure-style) referenced in the body.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: companion-inc/feynman
Path: skills/paper-narrative/SKILL.md
Commit: 95c51d9

Reviewed: about 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.