sn-prepare-citations

用于终稿完成且脚注需要后处理时：去重 [^key] 引用，转换为 [N] 编号，并追加参考文献。

Quality

85%

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

100%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 content is exemplary: lean, fully actionable, with a clear sequenced workflow and explicit validation gates for a batch/destructive citation-rewriting operation. Progressive disclosure is handled well, with the body serving as an overview to one real script.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient — a short CLI example, a parameter table, a numbered processing-logic list, and controller requirements — with no padding and no explanation of concepts Claude already knows.	5 / 5
Actionability	Provides a fully executable, copy-paste-ready CLI command, a complete parameter table, and a concrete 9-step processing sequence covering the common pipeline cases.	5 / 5
Workflow Clarity	The 9-step sequence is explicit, and the "控制器处理要求" section adds validation checkpoints with stop/don't-deliver gates and feedback loops (orphan_citations and unresolved claim-id leakage route back to the writer).	5 / 5
Progressive Disclosure	A compact single-purpose skill whose body is an overview pointing to one real bundle file (scripts/prepare_citations.py, verified present) with no nested references and well-organized sections.	5 / 5
	Total	20 / 20 Passed

Description

71%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 concise, third-person, and clearly conveys both what the skill does and when to use it, with concrete actions and low conflict risk. Its main weakness is trigger-term coverage, which relies on a single implicit trigger rather than a range of natural user phrases.

Suggestions

Broaden the trigger clause with more natural user phrases (e.g. "Use when finalizing a report's citations, numbering footnotes, or building a reference list").

Surface the L0/TOC rendering capability in the description so the action coverage is more comprehensive.

Add explicit file/extension triggers (e.g. stitched.md, evidence.json) to improve distinctiveness and discoverability.

Dimension	Reasoning	Score
Specificity	Names the citation-processing domain and lists several concrete actions — "去重 [^key] 引用", "转换为 [N] 编号", "追加参考文献" — with only minor coverage gaps (L0/TOC handling from the body is not surfaced here).	4 / 5
Completeness	Explicitly answers both "what" (dedup/convert/append references) and "when" (final draft done, footnotes need post-processing); the "when" is concrete but not a rich set of trigger phrases.	4 / 5
Trigger Term Quality	Includes a natural trigger clause ("用于终稿完成且脚注需要后处理时") and relevant terms (终稿/脚注/参考文献), but misses common synonyms and variations users might say.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — final-draft citation post-processing for a specific pipeline — with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	16 / 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: OpenSenseNova/SenseNova-Skills
Path: skills/sn-prepare-citations/SKILL.md
Commit: 61b60bb

Reviewed: 8 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.