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

92%

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%

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

The body is exemplary for a small, single-purpose skill: concise, actionable, with a clear sequence and explicit validation checkpoints, and a single well-signaled reference to a real script.

Dimension	Reasoning	Score
Conciseness	The body is lean — a concrete command, a tight parameter table, and a numbered logic list — with no padding or explanation of concepts Claude already knows, fitting the score-3 anchor.	3 / 3
Actionability	It provides a fully executable bash invocation with every argument shown, plus a real referenced script (scripts/prepare_citations.py), making the guidance copy-paste ready.	3 / 3
Workflow Clarity	A 9-step processing sequence is paired with explicit validation checkpoints in '控制器处理要求' (orphan_citations / claim_id_leakage → do not deliver, return to writer), supplying feedback loops for a batch operation.	3 / 3
Progressive Disclosure	As a single-purpose skill under 50 lines with well-organized sections and a one-level-deep reference to a real script, it meets the simple-skill bar for score 3.	3 / 3
	Total	12 / 12 Passed

Description

85%

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, complete, and distinct, clearly naming its actions and an explicit trigger. Its main weakness is trigger-term naturalness: the phrasing leans on pipeline jargon rather than terms a user would spontaneously say.

Suggestions

Broaden trigger terms to include common user phrasings (e.g. '把脚注转成编号引用', '整理参考文献', '处理引用编号') so the skill surfaces for natural requests.

Consider mentioning the input/output artifacts (stitched.md → report.md) in the description so the trigger is recognizable outside the sn-deep-research context.

Dimension	Reasoning	Score
Specificity	Lists three concrete actions — '去重 [^key] 引用', '转换为 [N] 编号', '追加参考文献' — matching the multi-action score-3 anchor rather than the partial coverage of score 2.	3 / 3
Completeness	Both what (dedup, convert to [N], append references) and when ('用于...时' explicit trigger) are clearly stated; the explicit trigger guidance avoids the score-2 cap.	3 / 3
Trigger Term Quality	The trigger '用于终稿完成且脚注需要后处理时' includes relevant keywords (脚注/引用/参考文献) but reads as pipeline-specific jargon and misses common user phrasings, fitting score 2 rather than full score-3 coverage.	2 / 3
Distinctiveness Conflict Risk	It targets a clear niche — citation/footnote post-processing for sn-deep-research — with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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: 179fea1

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.