nudocs
Upload, edit, and export documents via Nudocs.ai. Use when creating shareable document links for collaborative editing, uploading markdown/docs to Nudocs for rich editing, or pulling back edited content. Triggers on "send to nudocs", "upload to nudocs", "edit in nudocs", "pull from nudocs", "get the nudocs link", "show my nudocs documents".
86
86%
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 hits all the marks. It provides specific actions (upload, edit, export), clear 'Use when' guidance with concrete scenarios, and explicit trigger phrases that are natural and product-specific. The Nudocs.ai branding makes it highly distinctive and unlikely to conflict with other document-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: upload, edit, export documents, creating shareable links, uploading markdown/docs for rich editing, and pulling back edited content. | 3 / 3 |
Completeness | Clearly answers both 'what' (upload, edit, export documents via Nudocs.ai) and 'when' (explicit 'Use when' clause with scenarios plus explicit trigger phrases). Both dimensions are thoroughly covered. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would say: 'send to nudocs', 'upload to nudocs', 'edit in nudocs', 'pull from nudocs', 'get the nudocs link', 'show my nudocs documents'. These are realistic user utterances covering multiple interaction patterns. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific product name 'Nudocs.ai' and product-specific trigger terms. Very unlikely to conflict with generic document editing or other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with strong actionability and good progressive disclosure. Its main weaknesses are the verbose natural language triggers section (which Claude can infer) and the lack of validation checkpoints in workflows involving external API calls. The error handling table and safety boundaries are valuable additions.
Suggestions
Remove or significantly trim the 'Natural Language Triggers' section — Claude can infer user intent from the skill description and command names without exhaustive phrase lists.
Add validation checkpoints to workflows, e.g., 'Verify upload succeeded (check for returned ULID/link)' and 'Confirm file was downloaded before reading it'.
Remove the 'Document Best Practices' section or reduce it to a single line pointing to document-design.md — Claude already knows basic document structure principles.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary sections. The 'Natural Language Triggers' section is verbose and lists many trigger phrases that Claude can infer from the description. The 'Document Best Practices' section explains basic document structure concepts Claude already knows. The example session, while helpful, could be more compact. | 2 / 3 |
Actionability | Commands are concrete and copy-paste ready with clear syntax. Setup instructions include specific bash commands for configuration. The workflow sections provide specific command invocations, and the error handling table gives concrete solutions for each error case. | 3 / 3 |
Workflow Clarity | Upload and pull flows are clearly sequenced, but there are no validation checkpoints. The upload flow doesn't verify the upload succeeded before sharing the link, and the pull flow doesn't validate the downloaded file. For operations involving external API calls and file transfers, explicit verification steps (e.g., checking command exit status, confirming file was downloaded) would improve reliability. | 2 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-organized sections and appropriately references external files ('formats.md' and 'document-design.md' in the references folder) for detailed content. Navigation is straightforward with one-level-deep references and logical section ordering from setup through commands, workflows, and error handling. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
- Repository
- jdrhyne/agent-skills
- Commit
6768672
- 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.