paper-outline

Use when creating, revising, validating, or repairing a research-paper outline before writing; turns experiment evidence into a clear paper idea, scoped claims, method abstraction, evaluation plan, analysis plan, and evidence boundaries without copying run logs into the manuscript.

Quality

92%

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

85%

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

A highly actionable, well-sequenced skill with concrete tool calls, a full schema template, and a properly signaled reference file. The only weakness is mild verbosity from a conceptual analogy and some repeated reminders.

Suggestions

Trim the 'Strong papers often start from simple code...Residual connections...Attention...' paragraph; Claude already understands these concepts and it does not change the instructed action.

Consolidate the analysis-count guidance (4-8 jobs) so it appears once instead of being restated in 'Mature Outline Reminder', 'Analysis Plan', and 'Validation'.

Consider moving the large inline JSON contract block into references/ if it bloats context for users who only need the workflow, keeping a minimal shape example in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and task-focused, but the residual-connections/attention analogy paragraph and repeated analysis-count reminders across three sections add padding Claude does not need.	2 / 3
Actionability	Gives concrete tool calls (artifact.validate_academic_outline(detail='full'), artifact.compile_outline_to_writing_plan(...)), a full copy-paste JSON contract shape, and specific bad/good examples.	3 / 3
Workflow Clarity	A clear 6-step Basic Workflow with an explicit validate-then-compile checkpoint in step 6, plus a dedicated Validation checklist with error-recovery guidance.	3 / 3
Progressive Disclosure	Core workflow and contract live inline while extra examples are offloaded to a real, clearly signaled one-level-deep reference (references/outline-patterns.md).	3 / 3
	Total	11 / 12 Passed

Description

100%

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 strong description: third-person voice, explicit 'Use when' trigger, and a concrete list of capabilities. It answers what and when clearly and occupies a distinct niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'creating, revising, validating, or repairing a research-paper outline' and turns evidence into 'paper idea, scoped claims, method abstraction, evaluation plan, analysis plan, and evidence boundaries'.	3 / 3
Completeness	Explicitly answers both what (turns experiment evidence into a clear paper idea, scoped claims, etc.) and when ('Use when ... before writing'), with an explicit trigger clause.	3 / 3
Trigger Term Quality	The 'Use when creating, revising, validating, or repairing a research-paper outline before writing' clause covers natural phrasings a user would say, anchored on the recognizable term 'research-paper outline'.	3 / 3
Distinctiveness Conflict Risk	The niche — preparing/repairing a research-paper outline before writing — is narrow with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: ResearAI/DeepScientist
Path: src/skills/paper-outline/SKILL.md
Commit: b366244

Reviewed: 2 days 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.