CtrlK
BlogDocsLog inGet started
Tessl Logo

autodream-brain-sync

Syncs Claude Code's local memory system to Open Brain. Triggers whenever memories are saved via dreaming, autodream, or explicit "remember this" requests. After every local memory file write, captures the same content to Open Brain via mcp__open-brain__capture_thought so that memories are accessible from all connected AI clients (ChatGPT, Claude Desktop, Codex) and across all devices. Trigger on: memory saves, autodream, dreaming, "remember", "save to memory", or any write to the .claude/projects/*/memory/ directory.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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-structured and actionable with a clear workflow and sensible failure handling, appropriate for a simple instruction skill. Minor conciseness gains are available by trimming the redundant Problem statement and the other-client notes.

Suggestions

Tighten the 'Problem' section — it overlaps the description; a single sentence framing the silo problem would suffice.

Consider condensing 'Notes for Other Clients' to one line, since it describes behavior outside this skill's scope.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence, but the 'Problem' section restates the description and 'Notes for Other Clients' adds tangential context that could be trimmed for a tighter body.

2 / 3

Actionability

Gives concrete executable guidance — the exact tool name mcp__open-brain__capture_thought, a precise prefix format example '[feedback] Don't mock the database in integration tests', and an explicit 'use the memory content (not the frontmatter)' rule.

3 / 3

Workflow Clarity

A clear 3-step Process sequence with a failure-handling checkpoint in Guard Rails ('if capture fails, complete the local memory save anyway and note the sync failure'), which is strong for a simple skill.

3 / 3

Progressive Disclosure

A short (~45 line) single-purpose skill with no bundle files, organized into clearly labeled sections; per the simple-skills note, well-organized sections alone warrant a 3.

3 / 3

Total

11

/

12

Passed

Description

100%

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 is specific, third-person, and explicitly states both capabilities and trigger conditions with natural keywords. It is a strong, well-scoped description with no notable weaknesses.

DimensionReasoningScore

Specificity

Lists concrete actions — 'Syncs Claude Code's local memory system to Open Brain' and 'captures the same content to Open Brain via mcp__open-brain__capture_thought' — naming the exact MCP tool used.

3 / 3

Completeness

Explicitly answers both what (sync local memories to Open Brain for cross-client/device access) and when ('Triggers whenever memories are saved...' and 'Trigger on:...'), with an explicit trigger clause.

3 / 3

Trigger Term Quality

Covers natural user phrasings including "remember", "save to memory", "dream", "autodream", plus technical triggers like writes to .claude/projects/*/memory/, giving broad coverage users would actually say.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche — mirroring Claude Code local memory writes to Open Brain — with distinct triggers unlikely to collide with other skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

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.