robin
Save and review notes, quotes, articles, links, images, and video references in a personal commonplace book. Use when the user wants to file something to remember, organize knowledge by topic, resurface saved items, or review prior entries.
66
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
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 skill description that clearly communicates both what the skill does and when to use it. It enumerates specific content types, uses natural language trigger terms, and occupies a distinct niche (personal commonplace book / knowledge management). The description is concise yet comprehensive, following the third-person voice convention.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'save and review notes, quotes, articles, links, images, and video references' along with organizing by topic and resurfacing saved items. These are concrete, enumerated capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Save and review notes, quotes, articles, links, images, and video references in a personal commonplace book') and when ('Use when the user wants to file something to remember, organize knowledge by topic, resurface saved items, or review prior entries') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'notes', 'quotes', 'articles', 'links', 'images', 'video references', 'remember', 'organize knowledge', 'topic', 'saved items', 'commonplace book'. Good coverage of terms a user would naturally use when wanting to save or retrieve information. | 3 / 3 |
Distinctiveness Conflict Risk | The 'commonplace book' concept is a clear niche. The specific combination of saving diverse content types (quotes, articles, links, images, video references) for personal knowledge management with topic-based organization is distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent workflow clarity, providing concrete CLI commands, complete JSON contracts, and clear multi-step processes with validation. However, it is severely over-long and repetitive—command lists appear three times, and extensive reference material (JSON schemas, file formats, index schemas) is inlined rather than split into separate docs. The content would benefit enormously from aggressive trimming and progressive disclosure into referenced files.
Suggestions
Extract JSON contracts, CLI flag reference, topic file format, and review index schema into separate reference files (e.g., REFERENCE.md, FORMAT.md) and link to them from the main skill
Remove duplicate listings of commands—the repo-local script list appears three times; list it once and reference it
Trim explanatory text that Claude already knows (e.g., what CLI precedence means, that JSON must be valid, what exit status 1 means) to reduce token usage by ~30-40%
Consolidate the 'Host Requirements' and 'Runtime Contract' sections which overlap significantly with the 'Setup Contract' section
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines. It repeats command lists multiple times (repo-local scripts listed 3 times), explains concepts Claude already knows (what CLI precedence is, what JSON is), and includes extensive detail that could be in referenced docs. The storage model, host requirements, and runtime contract sections contain significant redundancy. | 1 / 3 |
Actionability | The skill provides fully executable CLI commands with concrete examples, complete JSON schemas for all responses, specific flag documentation for every command, and copy-paste ready examples covering add, review, search, and other operations. The guidance is highly specific and actionable. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with explicit validation checkpoints. The setup contract has numbered steps ending with a doctor.py verification. The filing workflow has clear decision logic (check topics → match → ask user → create new). Review mode has explicit state transitions. The bulk import workflow includes validation guidance. Failure rules are comprehensive with clear error handling expectations. | 3 / 3 |
Progressive Disclosure | There is one reference to docs/guide.md for advanced setup, but the vast majority of content is inline in a single monolithic file. The JSON contracts, CLI reference, topic file format, review index schema, and pitfalls sections could all be split into separate reference files. The content that is inline would benefit greatly from being organized into referenced documents. | 2 / 3 |
Total | 9 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (519 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
- Repository
- gniting/robin
- Commit
d9a6d9d
- 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.