auto-capture-claude-code

Claude Code adapter for the auto-capture skill. Extends auto-capture with automatic session-end hooks that capture transcripts to Open Brain without manual intervention. Use this when you want every meaningful Claude Code session to be preserved automatically — not just the ones where you remember to say "wrap up".

Quality

59%

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/auto-capture-claude-code/SKILL.md

Quality

Content

56%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 well-organized with concrete installation guidance and a clear workflow, but it is undermined by a missing referenced script and some redundant prose. Shipping the referenced bundle file would most improve it.

Suggestions

Add the referenced session-end-capture.mjs to a scripts/ bundle directory so the 'included' script actually exists and the install steps are executable.

Consolidate the three restatements of the base-skill/adapter complementarity into one section to remove padding.

Move the sensitivity-patterns and retry-queue configuration details into a short reference file and link to it, keeping SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and well-structured, but the complementary relationship between the base skill and adapter is restated three times (Relationship to Upstream Skill, What This Adapter Adds, and Notes), which is padding that could be tightened.	3 / 5
Actionability	Provides concrete install steps, a copy-paste JSON hook config, env vars, and named config knobs (RETRY_MAX_ATTEMPTS, HARD_TIMEOUT_MS), but the core 'included session-end-capture.mjs' script is referenced yet not present in any bundle directory, leaving a key executable gap.	3 / 5
Workflow Clarity	A clear 4-step 'How It Works' sequence and a 5-step install flow with an explicit verification step (step 5) and a retry feedback loop for the batch/automatic capture; minor validation gaps keep it just below 5.	4 / 5
Progressive Disclosure	Sections are well-organized, but the skill is over 50 lines with no bundle files present, and the body references an 'included' script (session-end-capture.mjs) and config paths that do not exist in the bundle, so the references are not actually real or navigable.	3 / 5
	Total	13 / 20 Passed

Description

62%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 communicates both the skill's purpose and when to use it, with concrete actions and a distinct niche. Its main weaknesses are second-person voice and trigger phrasing that is only moderately natural.

Suggestions

Rewrite in third person (e.g., 'Captures Claude Code session transcripts to Open Brain automatically') and drop 'you want'/'you remember' to avoid the specificity penalty.

Add more natural trigger keywords users would actually say, such as 'save session', 'log transcript', or 'preserve conversation', alongside 'wrap up'.

Sharpen the 'when' clause to name the specific situations (terminal close, Ctrl+C, walking away) rather than the abstract 'every meaningful session'.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ('automatic session-end hooks that capture transcripts to Open Brain', 'without manual intervention'), but the description uses second person ('you want', 'you remember to say'), which per the guidelines reduces the specificity score by one from a base of 4.	3 / 5
Completeness	Clearly states what it does (adapter extending auto-capture with session-end hooks capturing transcripts to Open Brain) and gives an explicit 'Use this when' trigger; the 'when' is concrete but could be slightly more specific, so it sits just below a 5.	4 / 5
Trigger Term Quality	Includes the natural phrase 'wrap up' and a 'Use this when...' clause, but the trigger ('when you want every meaningful Claude Code session to be preserved automatically') is only moderately natural and lacks common synonyms or variations.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Claude Code session-end hook → Open Brain ambient capture) with distinct triggers, with only minor overlap risk against the closely related base auto-capture skill.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: NateBJones-Projects/OB1
Path: skills/auto-capture-claude-code/SKILL.md
Commit: e79e9cb

Reviewed: 11 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.