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

91%

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

88%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-engineered, highly actionable skill body with strong workflow sequencing and validation gates for risky shared-write operations. The only lever for improvement is progressive disclosure: some inline reference-grade tables could be split into bundled reference files.

Suggestions

Move the diff-hunk decision table and the token-security defense-in-depth table into a bundled reference file (e.g. references/pull-protocol.md and references/token-security.md) referenced one level deep from SKILL.md to improve progressive_disclosure.

Trim the narrative in 'Token Security — Defense in Depth' and 'Mutual-Exclusion Rule' to bullet directives; the enforcement is already technical so the prose adds tokens without adding actionability.

Consider extracting the per-subcommand bash blocks into a scripts/ helper or reference so SKILL.md reads as an overview with signaled detail.

Dimension	Reasoning	Score
Conciseness	Lean and action-oriented with no padding of basic concepts (git, Overleaf, rsync are not explained); a few protocol tables and the defense-in-depth narrative could be tightened, so it sits above anchor 3 but not at a fully token-optimal 5.	4 / 5
Actionability	Every subcommand ships copy-paste-ready, executable bash/rsync/git blocks (pull diff, push rsync with excludes, status three-way check) covering the common cases, matching anchor 5.	5 / 5
Workflow Clarity	Clear sequences with explicit validation checkpoints throughout (setup verification block, pull diff protocol, push confirmation gate, status divergence table, conflict-resolution do-not rules); destructive/shared-write operations all carry validation, so the destructive-ops cap does not apply.	5 / 5
Progressive Disclosure	No bundle files exist; the single SKILL.md is well-sectioned with no nested references, but inline material (the diff-hunk decision table and token-security table) that could live in a separate reference file keeps it at anchor 4 rather than 5.	4 / 5
	Total	18 / 20 Passed

Description

95%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 strong, highly specific description that cleanly answers what the skill does and when to invoke it, with rich bilingual trigger terms. It is just shy of a perfect specificity score only because the action list could enumerate the subcommands (setup/pull/push/status) more explicitly.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Two-way sync', 'ARIS audit/edit workflows stay on the local copy', 'collaborators edit in the Overleaf web UI'); minor gaps in coverage keep it just below anchor 5. Third-person voice throughout, so no person-penalty applies.	4 / 5
Completeness	Explicitly answers both 'what' (two-way sync between local paper dir and Overleaf project) and 'when' via a concrete 'Use when user says...' clause with multiple trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms and bilingual variants ('同步 overleaf', 'overleaf sync', '推送到 overleaf', 'connect overleaf', 'Overleaf 桥接', 'pull overleaf', 'push overleaf'), matching the anchor 5 example.	5 / 5
Distinctiveness Conflict Risk	Clear niche (Overleaf Git bridge for ARIS paper workflows) with distinct, unlikely-to-collide triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 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
Path: skills/overleaf-sync/SKILL.md
Commit: f4f20f9

Reviewed: 1 day 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.