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

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

73%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 thorough, well-sequenced bootstrapping workflow with strong validation checkpoints and largely executable guidance. The chief weaknesses are verbosity from repeated safety framing and ClawVisor marketing prose, and a monolithic structure that underuses progressive disclosure despite being a long, multi-phase skill.

Suggestions

Consolidate the credential-safety messaging into one place (e.g. the Contract) and have later phases reference it, instead of restating the 'never hold raw tokens' warning in Phase 0, the decline section, and Anti-Patterns.

Trim the ClawVisor 'What it gives you' marketing bullets and the gateway description to the operational essentials an agent needs, or move the full ClawVisor setup into a referenced reference file.

Split the per-phase detail (especially Phase 0 ClawVisor setup and the longer processing rules) into one-level-deep reference files linked from the priority stack, so SKILL.md reads as a navigable overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but the ClawVisor marketing prose ('is a credential gateway that sits between the agent and your APIs... injects them at request time, enforces policies, and logs everything') and the safety admonition repeated across Contract, Phase 0, the decline section, and Anti-Patterns could be tightened.	3 / 5
Actionability	Provides executable bash discovery scripts, gbrain import/extract/stats commands, and concrete processing and filtering rules; the ClawVisor JavaScript is explicitly labeled pseudo-code, a justified minor gap rather than a missing detail.	4 / 5
Workflow Clarity	A clearly sequenced Phase 0–8 workflow with a priority stack table, explicit validation checkpoints (gbrain doctor --json, contact quality gate, archive-crawler safety gate), a resume protocol, and a post-bootstrap checklist — feedback loops are present for these batch/mutating operations.	5 / 5
Progressive Disclosure	Well-organized into labeled sections with clearly signaled references to external skills (skills/google-loops/SKILL.md, skills/migrate/SKILL.md, archive-crawler, meeting-ingestion), but the ~500-line body is monolithic and the ClawVisor Phase 0 detail could live in a separate reference file.	4 / 5
	Total	16 / 20 Passed

Description

88%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, third-person description that clearly states both what the skill does and when to invoke it, with concrete source coverage and a natural trigger phrase. The main gap is the absence of file-extension synonyms that would round out trigger term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and sources — 'Gmail import, calendar sync, contacts seeding, X/Twitter archive, conversation imports, and file archives' plus 'Sequences the highest-leverage data sources' and credential handling — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ('Sequences the highest-leverage data sources... Covers Gmail import, calendar sync...') and when ('Use when a user has just finished gbrain setup and asks "now what?"') with a concrete quoted trigger phrase.	5 / 5
Trigger Term Quality	Good keyword coverage including natural phrases ('now what?', 'day-one', Gmail, calendar, contacts, X/Twitter) but lacks synonyms and file extensions like .csv, .ics, mbox, so it does not reach the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Has a clear cold-start bootstrapping niche with distinct triggers ('now what?', 'day-one'), but the broad source coverage creates minor overlap risk with individual import skills like google-loops and archive-crawler.	4 / 5
	Total	18 / 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
skill_md_line_count	SKILL.md is long (546 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: 43597b1

Reviewed: 1 day 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.