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.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

77%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 highly actionable, well-sequenced skill body with strong validation checkpoints, dragged down by length/redundancy and weak progressive disclosure — most detail is inlined in SKILL.md and one reference link is broken.

Suggestions

Deduplicate the command listing: keep the canonical per-command flag table in 'Commands' and have 'Runtime Contract' and 'Examples' reference it instead of re-listing scripts.

Move JSON Contract shapes, Review Index Schema, Topic File Format, and Pitfalls into reference files under references/ (e.g. references/contracts.md, references/pitfalls.md) and link to them from SKILL.md, which currently inlines all of it.

Fix or remove the broken [docs/guide.md](docs/guide.md) link, and move the Publishing-to-GitHub and Known-Bug sections out of SKILL.md into a maintainer/contributor doc since they are not needed by an agent using the skill.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly actionable with little concept-over-explanation, but the command list is repeated three times (Runtime Contract, Commands, Examples), and the Publishing-to-GitHub SSH-key section and Known-Bug section with internal source paths are padded content a using agent does not need; it could be tightened.	3 / 5
Actionability	Fully executable copy-paste-ready commands, per-command CLI flag tables, many concrete examples, and explicit JSON contract shapes covering the common add/review/search/topics/reindex cases.	5 / 5
Workflow Clarity	Setup Contract, Filing, and Bulk Import are clearly numbered with explicit validation checkpoints (run doctor.py --json, selftest.py, verify media_source in JSON output) and feedback loops (reindex after manual edits), satisfying the batch/destructive validation expectation.	5 / 5
Progressive Disclosure	The scripts/ bundle is appropriately referenced and section headers give structure, but the SKILL.md is a ~570-line monolith with JSON contracts, Review Mode internals, and Pitfalls inlined that belong in separate reference files, and the one external reference ([docs/guide.md](docs/guide.md)) does not exist on disk.	3 / 5
	Total	16 / 20 Passed

Description

87%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 description that clearly states both the capability and explicit usage triggers in third person, with concrete content types and natural trigger phrases. Minor room to broaden synonyms and de-overlap action verbs.

Dimension	Reasoning	Score
Specificity	Lists concrete content types (notes, quotes, articles, links, images, video references) and several specific actions (save, review, file, organize by topic, resurface), but the action verbs partially overlap (save/file, review/resurface) leaving minor coverage gaps versus the comprehensive 5-anchor.	4 / 5
Completeness	Explicitly answers both what ('Save and review ... 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 concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases users would say ('file something to remember', 'organize knowledge by topic', 'resurface saved items', 'review prior entries') give good coverage, but a few common synonyms (e.g. 'bookmark', 'save for later') are missing.	4 / 5
Distinctiveness Conflict Risk	The 'personal commonplace book' framing plus resurface/review-prior-entries triggers carve a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (570 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: gniting/robin
Path: SKILL.md
Commit: 75b7a6b

Reviewed: 25 days 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.