overleaf-sync
Two-way sync between a local paper directory and an Overleaf project via the Overleaf Git bridge (Premium feature). Lets you keep ARIS audit/edit workflows on the local copy while collaborators edit in the Overleaf web UI. Token never touches the agent — user does the one-time auth via macOS Keychain. 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.
89
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
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.
This is an excellent skill description that clearly defines a specific capability (two-way Overleaf sync via Git bridge), provides rich bilingual trigger terms, and explicitly states when to use it. The description is distinctive enough to avoid conflicts while being comprehensive about both the 'what' and 'when'. Minor note: it includes some implementation details (macOS Keychain, Premium feature) that add context without cluttering the core message.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: two-way sync, local paper directory, Overleaf Git bridge, ARIS audit/edit workflows on local copy, collaborators editing in Overleaf web UI, one-time auth via macOS Keychain. Very specific about what it does and how. | 3 / 3 |
Completeness | Clearly answers both 'what' (two-way sync between local paper directory and Overleaf project via Git bridge) and 'when' (explicit 'Use when' clause with specific trigger phrases and a conceptual trigger scenario). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms in both English and Chinese: '同步 overleaf', 'overleaf sync', '推送到 overleaf', 'connect overleaf', 'Overleaf 桥接', 'pull overleaf', 'push overleaf', plus the conceptual trigger 'bridge their ARIS paper directory with an Overleaf project'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific niche (Overleaf Git bridge sync with ARIS paper directory). The combination of Overleaf, Git bridge, ARIS, and bilingual trigger terms makes it extremely unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, well-architected skill that excels in actionability and workflow clarity — every operation has concrete commands, validation steps, and clear decision protocols. The security design with defense-in-depth layers is impressive and well-documented. The main weaknesses are moderate verbosity (some sections could be tightened) and the monolithic structure that could benefit from splitting detailed reference content into separate files.
Suggestions
Trim the 'When to Use This Skill' section — the trigger phrases in the YAML description already cover this, and Claude can infer use cases from the skill's content.
Consider splitting the Token Security and Conflict Resolution sections into referenced files (e.g., SECURITY.md, CONFLICTS.md) to reduce the main skill's length and improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is thorough and mostly earns its length given the complexity of two-way sync with security concerns, but there's some redundancy — the token security section repeats behavioral rules that are already enforced by the technical guards described in the same section. The architecture diagram and mutual-exclusion rule add value, but the 'When to Use This Skill' section explains things Claude could infer from context. | 2 / 3 |
Actionability | Excellent actionability throughout — every sub-command has copy-paste-ready bash commands, the diff protocol has a concrete decision table per hunk type, rsync commands include proper exclude flags, and commit message examples show exact format. The setup verification steps are fully executable. | 3 / 3 |
Workflow Clarity | Outstanding workflow clarity with explicit validation checkpoints at every stage: setup has a post-verification checklist, pull has a per-hunk decision table before syncing, push has a mandatory confirmation gate before `git push`, and conflict resolution has a clear 'stop and ask' protocol. The three-way status table elegantly maps states to recommended actions. Feedback loops are present for error recovery (e.g., ff-only failure → show divergence → ask user). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sub-command sections and tables, but it's a long monolithic document (~200+ lines) with no references to external files for detailed content. The token security table, conflict resolution, and mutual-exclusion rules could be split into referenced files. The bundle has no supporting files despite referencing `tools/overleaf_setup.sh` and `tools/overleaf_audit.sh`. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
2028ac4
- Reviewed
Table of Contents
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.