overleaf-sync

Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to bridge their ARIS paper directory with an Overleaf project.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

A dense, highly actionable operations doc with strong workflow sequencing and validation gates. Its main weaknesses are redundant security messaging that bloats token usage and a monolithic structure that keeps detail inline instead of splitting it into bundled reference files.

Suggestions

Collapse the token-security guidance into one place: keep the 'Defense in Depth' table and remove the duplicate guard list from the setup steps and the restated 'Never write a token to a file/remote URL' behavioral rules.

Move the per-hunk diff-protocol table and commit-message examples into a references/ file (e.g. PULL_PROTOCOL.md), leaving SKILL.md a concise overview with a one-level pointer.

Ship the referenced tools/overleaf_setup.sh and tools/overleaf_audit.sh in a scripts/ bundle so the cited 'Where enforced' paths actually exist alongside the skill.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (no git/rsync/Overleaf primers), but the token-security guards are restated three times — in the setup step list, the 'Defense in Depth' table, and again in the behavioral rules — so it could be tightened.	2 / 3
Actionability	Provides copy-paste-ready bash for pull/push/status, a literal user instruction block for setup, and concrete verification commands; guidance is executable rather than described.	3 / 3
Workflow Clarity	Multi-step flows are explicitly sequenced with validation checkpoints — the post-setup verification block, the pull diff-protocol decision table, and the push confirmation gate — plus a conflict-resolution branch that forbids destructive ops.	3 / 3
Progressive Disclosure	Sections are well-organized and reference external scripts (tools/overleaf_setup.sh, tools/overleaf_audit.sh) at one level, but no bundle files ship and the diff-protocol tables, security matrix, and command catalogs all live inline in a ~210-line monolithic SKILL.md rather than being split into reference files.	2 / 3
	Total	10 / 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, third-person description that names concrete capabilities and pairs them with an explicit 'Use when...' trigger clause covering both English and Chinese phrasings. It is specific, complete, and clearly scoped to a distinct niche.

Dimension	Reasoning	Score
Specificity	States concrete actions — 'Two-way sync between a local paper directory and an Overleaf project' and 'ARIS audit/edit workflows stay on the local copy' — listing multiple specific operations (sync, audit, edit) rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Two-way sync ... so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI') and when ('Use when user says ...').	3 / 3
Trigger Term Quality	Includes many natural phrasings a user would actually say: '同步 overleaf', 'overleaf sync', '推送到 overleaf', 'connect overleaf', 'Overleaf 桥接', 'pull overleaf', 'push overleaf'.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (Overleaf Git bridge for ARIS paper dirs) with distinctive, unlikely-to-collide triggers, so it would not fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Commit: 82076e5

Reviewed: 5 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.