skillpack-harvest

Lift a proven skill from a host repo (e.g. your OpenClaw fork) back into gbrain's bundle so other clients can scaffold it. Editorial workflow: the CLI does the file copy + privacy lint; this skill drives the judgment-heavy genericization (scrub real names, generalize triggers, lift fork-specific conventions to references).

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/skillpack-harvest/SKILL.md

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 clearly sequenced, well-validated workflow, but it carries some cross-section redundancy and keeps all detail inline rather than progressively disclosing it to reference files.

Suggestions

De-duplicate the copy-not-move and no-batch-harvest points, which appear in both the Anti-Patterns and 'What harvest does NOT do' sections.

Consider extracting the detailed Phase 3 genericization checklist into a reference file (e.g. GENERICIZATION-CHECKLIST.md) linked from the main workflow to reduce the inline length.

Tighten the Preconditions section, which restates maturity/generalizability points already covered in the Contract and 'When to invoke' sections.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concepts Claude already knows, but the Anti-Patterns, Contract, and 'What harvest does NOT do' sections overlap (e.g. the copy-not-move point appears in two places), so it could be tightened.	2 / 3
Actionability	Provides fully executable commands (gbrain skillpack harvest ... --dry-run / --no-lint), concrete test commands, and a genericization checklist with specific before/after replacements (Wintermute → your OpenClaw, email → example@example.com).	3 / 3
Workflow Clarity	Six phases are clearly sequenced with explicit validation checkpoints (dry-run preview, privacy lint with rollback, conformance test, check --strict, diff review) and a feedback loop from lint_failed back to Phase 3.	3 / 3
Progressive Disclosure	Well-organized into clear sections, but it is a single ~270-line monolithic file with no external reference files, and content that could be split out (the detailed Phase 3 checklist) is inline.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 and distinctive with a clear niche, but it lacks an explicit "when to use" clause and relies on somewhat technical jargon over natural user phrasing.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when a skill has proven itself in a host fork and is ready to be generalized and published to the gbrain bundle.'

Swap jargon like 'genericization' and 'fork-specific conventions' for natural trigger terms a user would say (e.g. 'harvest', 'publish upstream', 'share with other clients').

Surface the verb 'harvest' in the description itself, since it is the primary trigger word users would naturally invoke.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Lift a proven skill", "file copy + privacy lint", "scrub real names, generalize triggers, lift fork-specific conventions to references" — rather than vague language.	3 / 3
Completeness	Clearly answers "what" the skill does, but there is no explicit "Use when..." clause or equivalent trigger guidance, which caps completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	Contains some relevant terms ("lift", "host repo", "harvest" implied) but leans on jargon like "genericization" and "fork-specific conventions" and omits common natural variations a user would actually say.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (lifting host skills upstream into gbrain's bundle) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 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
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: garrytan/gbrain
Path: skills/skillpack-harvest/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.