raindrop-api
This skill provides comprehensive instructions for interacting with the Raindrop.io bookmarks service via its REST API using curl and jq. It covers authentication, CRUD operations for collections, raindrops (bookmarks), tags, highlights, filters, import/export, and backups. Use this skill whenever the user asks to work with their bookmarks from Raindrop.io, including reading, creating, updating, deleting, searching, or organising bookmarks and collections.
90
86%
Does it follow best practices?
Impact
100%
1.28xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
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 a strong, well-crafted description that clearly identifies the specific service (Raindrop.io), the tools involved (curl, jq), the concrete operations supported, and explicit guidance on when to use the skill. It covers both the 'what' and 'when' thoroughly with natural trigger terms that users would actually say.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: authentication, CRUD operations for collections, raindrops/bookmarks, tags, highlights, filters, import/export, and backups. Also specifies the tools used (curl and jq) and the service (Raindrop.io REST API). | 3 / 3 |
Completeness | Clearly answers both 'what' (interacting with Raindrop.io via REST API for CRUD on collections, bookmarks, tags, highlights, etc.) and 'when' (explicit 'Use this skill whenever the user asks to work with their bookmarks from Raindrop.io' with specific trigger scenarios listed). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'bookmarks', 'Raindrop.io', 'collections', 'tags', 'highlights', 'searching', 'organising bookmarks'. Also covers action verbs like 'reading, creating, updating, deleting, searching, or organising' which map well to user requests. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific service (Raindrop.io) with specific tools (curl, jq) and a specific API. Very unlikely to conflict with other skills unless another Raindrop.io skill exists. | 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, highly actionable API reference skill with excellent executable examples and good progressive disclosure to reference files. Its main weaknesses are verbosity (some content like HTTP status codes and basic field descriptions could be trimmed or offloaded) and the lack of explicit post-operation validation steps in workflows, particularly for destructive or bulk operations.
Suggestions
Add explicit response validation after write/delete operations (e.g., check that the response contains 'result: true' or verify the expected HTTP status code) to create feedback loops for destructive actions.
Move the detailed field listings (raindrop fields, collection fields) to a reference file to reduce the main skill's token footprint while keeping the common patterns section intact.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~400 lines) and includes some information Claude could infer (e.g., HTTP status code meanings, CORS support, ISO 8601 timestamps). The endpoint reference tables are useful but the full field listings for raindrop creation/update and collection fields add bulk that could be offloaded to reference files. However, most content is genuinely useful API-specific detail. | 2 / 3 |
Actionability | Nearly every operation includes fully executable curl+jq commands that are copy-paste ready with clear placeholder values. The common patterns section provides complete, working examples for all major use cases including pagination, search, export, and error handling. | 3 / 3 |
Workflow Clarity | The workflow summary at the end provides a clear sequence, and the confirmation requirement for destructive actions is well-defined. However, there are no explicit validation/verification steps after write operations (e.g., verify a bookmark was created by checking the response, confirm deletion succeeded). For destructive bulk operations like emptying trash or merging tags, there's no feedback loop beyond the confirmation prompt. | 2 / 3 |
Progressive Disclosure | The skill appropriately delegates detailed topics to reference files (search-operators.md, collections-sharing.md, highlights.md) with clear one-level-deep references. The main file serves as a comprehensive but navigable overview with well-organized sections, tables, and links to official docs. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (558 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- intellectronica/agent-skills
- Commit
9b0e00a
- 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.