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

66%

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

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.

The body is a well-structured, actionable workflow with strong validation and feedback loops; its main weakness is redundancy across the Anti-Patterns, 'What harvest does NOT do', and inline notes that inflates length.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational guidance that assumes Claude's competence, but the 'Anti-Patterns', 'What harvest does NOT do', and Phase 2 dry-run note repeat the same points (copy-not-move, don't skip dry-run) and could be tightened.	3 / 5
Actionability	Provides concrete executable commands (gbrain skillpack harvest ... --dry-run, bun test ..., gbrain skillpack check --strict) and specific scrub examples (garry -> the user, acme-example, #some-channel); not a 5 because slug/host placeholders and the human-driven editorial pass leave minor gaps.	4 / 5
Workflow Clarity	Six clearly sequenced phases with explicit validation checkpoints (dry-run, privacy lint with rollback, Phase 5 verify), a feedback loop (lint_failed -> back to Phase 3), and a checklist for the complex editorial pass; the destructive/batch cap does not apply since validation is present and batch is unsupported.	5 / 5
Progressive Disclosure	Single-file skill with no bundle references, organized into clear navigable sections (Contract, Workflow phases, Bypass, etc.); not a 5 because of length and redundancy between the Anti-Patterns and 'What harvest does NOT do' sections.	4 / 5
	Total	16 / 20 Passed

Description

58%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 conveys what the skill does with concrete actions and a distinct niche, but lacks an explicit 'when to use' clause and the natural trigger synonyms that would help users discover it.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user wants to harvest or publish a proven host skill upstream into gbrain's bundle so other clients can scaffold it.'

Weave natural trigger terms (harvest, publish, promote, share) into the description so the wording matches what users actually say.

Clarify the boundary from the scaffold skill in one phrase (e.g. 'inverse of scaffold') to reduce overlap confusion.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('the CLI does the file copy + privacy lint', 'scrub real names, generalize triggers, lift fork-specific conventions to references'); not a 5 because it omits the verification/landing step from the action list.	4 / 5
Completeness	The 'what' is clear and concrete, but there is no explicit 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Contains relevant keywords ('Lift a proven skill', 'host repo', 'scaffold') but is missing the natural synonyms users say (harvest, publish, promote, share) that appear only in the triggers array.	3 / 5
Distinctiveness Conflict Risk	Carves a distinct niche (editorial genericization of a proven skill upstream into gbrain's bundle), but the phrase 'so other clients can scaffold it' introduces minor overlap risk with the scaffold 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: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: skills/skillpack-harvest/SKILL.md
Commit: 055ac6c

Reviewed: about 2 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.