cold-start

Day-one data bootstrapping for a new brain. Sequences the highest-leverage data sources to go from empty brain to useful brain in one session. Uses ClawVisor for safe credential handling — the agent never holds raw API keys. Covers Gmail import, calendar sync, contacts seeding, X/Twitter archive, conversation imports, and file archives. Use when a user has just finished gbrain setup and asks "now what?"

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear, well-validated workflow, but it is verbose — repeating the ClawVisor safety argument and inlining every phase's detail into one monolithic file. Tightening the repeated rationale and splitting per-phase detail into reference files would lift the two lower dimensions.

Suggestions

State the ClawVisor safety rationale once (in Phase 0 or the Contract) and reference it elsewhere instead of repeating the 'uncontrolled attack surface / one prompt injection' argument in three sections.

Move per-phase detail (Phases 2–8) into one-level-deep reference files (e.g. references/phase-contacts.md) and keep SKILL.md as a concise overview pointing into them via the priority stack.

Trim motivational framing such as 'live context membrane that makes every future interaction smarter' that does not change agent behavior.

Dimension	Reasoning	Score
Conciseness	Mostly actionable but padded with motivational framing ('A brain with your email history... is a live context membrane') and the ClawVisor safety rationale restated three times (Contract, Phase 0, Anti-Patterns) plus a marketing-style feature bullet list; could be tightened.	2 / 3
Actionability	Provides fully executable bash ('gbrain migrate --from obsidian --path /path/to/vault', 'gbrain import ... --no-embed --workers 4'), JavaScript ('clawvisor(...)') and curl examples alongside specific filter rules, matching the copy-paste-ready anchor.	3 / 3
Workflow Clarity	Clear 8-step priority sequence with explicit validation checkpoints (sample-page review after 5 contacts, 'gbrain doctor --json', scan-only archive pass), consent gating, state-tracking for resume, and a post-bootstrap checklist with feedback loops for batch/destructive operations.	3 / 3
Progressive Disclosure	All eight phases plus marketing, anti-patterns, output format, and tools are inlined into a single ~460-line SKILL.md with no bundle files; the priority stack is an overview but detail that could be split into references remains inline, matching the anchor for content that should be separate.	2 / 3
	Total	10 / 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 strong: it names concrete capabilities, covers natural trigger terms, explicitly answers both what and when, and occupies a distinct niche. No material weakness to address.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Sequences the highest-leverage data sources' and 'Covers Gmail import, calendar sync, contacts seeding, X/Twitter archive, conversation imports, and file archives' — matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Clearly states what it does ('Day-one data bootstrapping... Sequences the highest-leverage data sources') and when to use it ('Use when a user has just finished gbrain setup and asks "now what?"'), answering both with an explicit trigger.	3 / 3
Trigger Term Quality	Includes natural source terms (Gmail, calendar, contacts, X/Twitter) plus the explicit 'now what?' trigger a user would actually say, giving good coverage of natural language.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche — 'Day-one data bootstrapping for a new brain' tied to post-setup 'now what?' — with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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
skill_md_line_count	SKILL.md is long (507 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: skills/cold-start/SKILL.md
Commit: 3fafb69

Reviewed: about 20 hours 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.