CtrlK
BlogDocsLog inGet started
Tessl Logo

auto-capture

Automatically capture ACT NOW items and a session summary to Open Brain when a work session is ending. Use when wrapping a brainstorm, parking a project, finishing a Panning for Gold run, or otherwise closing a session with decisions worth remembering. Use the Open Brain capture tool available in the current client (often named `capture_thought`; prefixes vary by connector). This is a behavioral protocol, not a background hook.

66

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 lean, well-organized behavioral protocol with concrete, actionable steps and good section structure. The main weaknesses are mild repetition of the tool-name caveat and the absence of an explicit retry feedback loop for capture failures.

Suggestions

State the 'tool names vary by connector / not a background hook' caveat once and reference it, instead of repeating it in the description, step 1, step 3, and Notes.

Add a short validate-retry loop for capture failures (e.g., retry once, then report to the user) so the workflow has an explicit recovery checkpoint rather than only a failure-report step.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence, but the tool-name-varies caveat and the 'behavioral protocol, not a hook' framing are each repeated across the description, step 1, and the Notes, which is minor over-explanation that could be trimmed.

4 / 5

Actionability

The Process steps give concrete, specific guidance — capture each ACT NOW item as a self-contained thought with sub-bullets for idea, why-it-matters, 2-3 next actions, and provenance, plus a useful good/bad example — but it stops short of fully copy-paste-ready capture calls because tool names intentionally vary by connector.

4 / 5

Workflow Clarity

The six numbered steps form a clear sequence with a pre-capture dedup checkpoint (step 3) and a quality gate (step 6), but there is no explicit validate-fix-retry feedback loop for capture failures — only an instruction to report failure — which keeps it just below the top anchor.

4 / 5

Progressive Disclosure

The single-purpose body is well organized into clearly headed sections (Problem, Trigger Conditions, Process, Output, Notes), and the only external link — the OB1-specific Auto-Capture recipe — is one level deep and explicitly signaled, matching the top anchor for a well-structured overview.

5 / 5

Total

17

/

20

Passed

Description

82%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, well-structured description that clearly states both the capability and the natural trigger conditions with domain-specific vocabulary. The only soft spot is specificity, where it names just two concrete capture actions rather than a fuller enumeration.

DimensionReasoningScore

Specificity

The description names the Open Brain domain and two concrete actions — 'capture ACT NOW items' and 'a session summary' — which matches the '1-2 concrete actions, not comprehensive' anchor rather than the 'several specific actions' needed for a 4.

3 / 5

Completeness

It explicitly answers both what ('Automatically capture ACT NOW items and a session summary to Open Brain') and when ('Use when wrapping a brainstorm, parking a project, finishing a Panning for Gold run, or otherwise closing a session...') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

It lists several natural trigger phrases a user would say — 'wrapping a brainstorm', 'parking a project', 'finishing a Panning for Gold run', 'closing a session' — giving good coverage, though a few common variants like 'wrap up' or 'goodnight' (which appear only in the body) are missing.

4 / 5

Distinctiveness Conflict Risk

The niche vocabulary — Open Brain, ACT NOW items, Panning for Gold runs — defines a clear, distinctive trigger surface with minimal overlap risk against generic skills.

5 / 5

Total

17

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository
NateBJones-Projects/OB1
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.