capture

Save any thought or content into the brain via one CLI command. The single human-facing entrypoint that replaces "put_page vs commit-then-sync vs autopilot-wait" with one command that just works.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/capture/SKILL.md

Quality

Content

88%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.

The content is a lean, executable single-purpose skill with copy-paste commands, clear contract/defaults/output, and explicit routing to specialized sibling skills. Minor trimming of the Anti-Patterns section would push conciseness to the top anchor.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with tight contract/defaults/output sections, though the Anti-Patterns section is slightly padded relative to the rest.	4 / 5
Actionability	The 'How to use' block gives copy-paste-ready executable commands covering inline, file, stdin, slug, type, source, quiet, and json variants — fully actionable.	5 / 5
Workflow Clarity	The Contract and Defaults sections sequence inputs→outputs→side effects with explicit verification signals (idempotency, content-hash dedup, receipt block), giving clear checkpoints and feedback for the single-purpose capture flow.	5 / 5
Progressive Disclosure	Sections are well-organized and it cleanly routes the reader to sibling skills (media-ingest, idea-ingest, meeting-ingestion); no bundle files exist so there is nothing to offload, leaving only minor room for tighter grouping.	4 / 5
	Total	18 / 20 Passed

Description

46%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.

The description clearly states the skill's purpose and differentiates it from sibling commands, but it lacks an explicit trigger/when clause and leans on internal jargon instead of natural user language. Adding a 'Use when...' clause with plain trigger phrases would lift the weaker dimensions.

Suggestions

Add an explicit 'Use when the user says "save this", "capture this thought", or "remember this"' clause to the description.

Replace the internal-jargon parenthetical ('put_page vs commit-then-sync vs autopilot-wait') with concrete, user-facing terms.

Name a few more concrete actions (e.g., capture inline text, a file, or piped stdin) to broaden the specificity coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ('save any thought or content into the brain') and one concrete action ('via one CLI command'), but coverage is limited to a single action without enumerating several specific operations.	3 / 5
Completeness	The 'what' is clear (one CLI command to save thoughts/content), but there is no explicit 'Use when...' clause, so the 'when' is only weakly implied — capping completeness at 3 per the guidelines.	3 / 5
Trigger Term Quality	It leans on internal jargon ('put_page vs commit-then-sync vs autopilot-wait') rather than natural user phrases; the actual trigger words live in the body, not the description.	2 / 5
Distinctiveness Conflict Risk	It carves a clear niche as the single human-facing ingestion entrypoint and explicitly contrasts it with the primitives it replaces, leaving only minor overlap risk with sibling ingest skills.	4 / 5
	Total	12 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: garrytan/gbrain
Path: skills/capture/SKILL.md
Commit: 43597b1

Reviewed: 1 day 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.