paper-writer

Drafts publishable paper prose from the author's own materials, from a single paragraph to a full manuscript, across STEM and non-STEM fields. Every factual claim traces to user input, verified retrieval, or field common knowledge; citations pass an independent verification ladder; delivery is clean prose with zero placeholder tags. Use when the user asks to write a section, turn an idea or results into paper text, or draft a full paper.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%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 well-structured, actionable skill body with a clear gated workflow and clean progressive disclosure into verified reference files. The main improvement is trimming restated rules and surfacing a couple of deferred specifics inline.

Suggestions

Reduce redundancy between the 'Hard rules' list, Phase 4's writing rules, and the Phase 4.5 red-flag table, which restate the 'no invented specifics' ban in three places.

Inline the one or two most-used specifics currently deferred to references (e.g., the L1-L4 evidence-level definitions or the citation entry format) so the gate can be applied without a context switch.

Give one concrete retrieval-tool invocation example (e.g., a Crossref/Semantic Scholar query) instead of only naming the APIs, to strengthen actionability for the literature-search phase.

Dimension	Reasoning	Score
Conciseness	Lean throughout and assumes Claude's competence (no explaining what a paper or citation is), but the hard rules and the 'no invented specifics' ban list are partly restated in Phase 4 and the red-flag table, creating minor redundancy.	4 / 5
Actionability	Concrete, executable guidance throughout (evidence levels L1-L4 mapped to exact claim-strength caps, prescribed phrasings like 'we observe' vs 'the authors report', citation-density ranges, bidirectional reference matching); a few specifics are deferred to reference files rather than given inline.	4 / 5
Workflow Clarity	Six phases are clearly sequenced with explicit gates (the L0-L3 source gate, review-waits-until-no-unresolved-entries) and feedback loops (search -> rewrite/delete; validate -> fix), covering the destructive claim-deletion path with checkpoints.	5 / 5
Progressive Disclosure	The body is a structured overview pointing to one-level-deep, clearly signaled reference files (evidence-discipline.md, verification-ladder.md, verification-checklist.md, prose-delivery.md, section-guidance.md, citation-style.md), all of which exist in the bundle, with easy navigation and no nested references.	5 / 5
	Total	18 / 20 Passed

Description

88%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 specific, well-triggered description that explicitly covers both capability and use-conditions with concrete natural-language triggers. The only weakness is slight overlap with sibling writing skills and a few missing trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (drafts publishable prose, traces every claim to a source, passes citations through a verification ladder, delivers zero-placeholder prose) with comprehensive scope from a single paragraph to a full manuscript across STEM and non-STEM fields.	5 / 5
Completeness	Clearly states what it does (draft publishable, traceable, verified, placeholder-free prose) and gives an explicit 'Use when...' clause with concrete trigger phrases, answering both what and when.	5 / 5
Trigger Term Quality	Includes natural phrases users say ('write a section,' 'turn an idea or results into paper text,' 'draft a full paper') but misses a few common variants like 'manuscript' as a trigger; solid keyword coverage with minor gaps.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche (prose drafting under an evidence-traceability condition) and distinct triggers, with only minor overlap risk against adjacent writing skills that are explicitly bounded in the body.	4 / 5
	Total	18 / 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: HKUSTDial/Supervisor-Skills
Path: skills/paper-writer/SKILL.md
Commit: 207bc6f

Reviewed: 9 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.