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

73%

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

92%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 body is an exemplary single-command skill: fully executable examples, exact output format, explicit defaults, and strong anti-pattern guidance that redirects bulk and specialized ingestion to the right tools. Only minor conciseness trims (a duplicated dedup note, slight intro padding) keep it from a perfect score.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence — no concept explanations, just "run `gbrain capture`. Don't reach for `gbrain put`". Minor trim opportunities: the daemon's 24h content-hash dedup is stated twice (Contract §Idempotency and Defaults §Slug) and the intro's "front door" framing is slightly padded. Anchor 4 ("Efficient; minor instances of over-explanation that could be trimmed"); not 5 because of the duplicated dedup line and intro phrasing.	4 / 5
Actionability	Seven copy-paste-ready invocations (inline, --file, --stdin, custom slug, --type, --quiet, --json) plus the exact 5-line receipt format, defaults, and frontmatter stamps. Anchor 5 ("Fully executable; copy-paste ready code or commands; specific examples cover the common cases"); not 4 because there are no meaningful gaps in the common-case coverage.	5 / 5
Workflow Clarity	This is a single-action skill (run `gbrain capture`) and the action is unambiguous: input modes, defaults, output, and failure modes (Anti-Patterns, When NOT to use) are all covered explicitly. Per the simple-skill exception, a single unambiguous action scores 5; it is not a batch/destructive operation, so the validation cap does not apply.	5 / 5
Progressive Disclosure	No references/, scripts/, or assets/ bundle exists and none is needed for a single-command skill; the body is well-organized into tight sections. Specialized cases are cleanly deferred one level deep to real sibling skills (skills/media-ingest/SKILL.md, skills/idea-ingest/SKILL.md, skills/meeting-ingestion/SKILL.md), which is well-signaled navigation. Anchor 5 fits.	5 / 5
	Total	19 / 20 Passed

Description

53%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 communicates a clear single purpose (one-command capture into the brain) and differentiates itself from internal primitives, but it entirely lacks a "when to use" clause and the natural trigger phrases users would say. The second sentence leans on internal jargon ("put_page vs commit-then-sync vs autopilot-wait") that adds little for trigger matching.

Suggestions

Add an explicit trigger clause to the description, e.g. "Use when the user says 'capture this', 'save this thought', or 'remember this', or pastes content and asks to keep it."

Fold the natural trigger phrases currently only in the frontmatter triggers list (capture this, remember this, save to brain) into the description text so the trigger_term_quality coverage is complete.

Trim the jargon-heavy second sentence ("put_page vs commit-then-sync vs autopilot-wait") and replace it with one more concrete capability, e.g. receipt output or predictable inbox slugging, to lift specificity.

Dimension	Reasoning	Score
Specificity	"Save any thought or content into the brain via one CLI command" names the domain and exactly one concrete action, but coverage stops there — no receipt, slugging, or queryability is mentioned. Anchor 3 ("Names domain and 1-2 concrete actions, but not comprehensive") fits; it is not 4 because only a single action is listed, and not 2 because that action is concrete rather than generic.	3 / 5
Completeness	The "what" is clear (save content into the brain via one CLI command) but there is no "Use when..." clause or equivalent trigger guidance anywhere in the description, which caps completeness at 3 per the judging guidelines. Not 4 because the "when" is not even weakly implied, only inferable from the verb "save".	3 / 5
Trigger Term Quality	Natural terms like "save", "thought", "content", and "brain" are present, but the common phrases a user would actually say — "capture this", "remember this", "take a note" — are absent from the description (they only exist in a separate triggers field). Matches anchor 3 ("Some relevant keywords but missing common variations or synonyms"); not 4 because several high-frequency natural trigger phrases are missing.	3 / 5
Distinctiveness Conflict Risk	References to "the brain", "one CLI command", and "The single human-facing entrypoint that replaces \"put_page vs commit-then-sync vs autopilot-wait\"" carve a distinct niche and explicitly differentiate from sibling commands. Anchor 4 ("Mostly distinct; minor overlap risk with closely related skills") fits; not 5 because closely related ingestion skills (idea-ingest, meeting-ingestion, media-ingest) share the "save into brain" trigger space without the description distinguishing them.	4 / 5
	Total	13 / 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: e78f1c3

Reviewed: 5 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.