migrate-nanoclaw

Extracts user customizations from a fork, generates a replayable migration guide, and upgrades to upstream by reapplying customizations on a clean base. Replaces merge-based upgrades with intent-based migration.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/migrate-nanoclaw/SKILL.md

Quality

Content

81%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 content is a highly actionable, well-sequenced migration workflow with strong validation and safety nets, scoring top marks on actionability and workflow clarity; its main weakness is moderate verbosity and an inlined guide template that nudges progressive disclosure down slightly.

Suggestions

Extract the full migration-guide markdown template (lines ~203–262) and the standard/non-standard example entries into a references file (e.g. references/guide-template.md) and link to it, reducing inline length.

Deduplicate the repeated 'Service labels are per-install — derive them from setup/lib/install-slug.sh' blocks in 2.7 and 2.9 by referencing a single shared snippet.

Tighten Phase 0 self-refresh prose and the restated preflight in 2.0 by pointing back to 1.0 instead of restating the checks.

Dimension	Reasoning	Score
Conciseness	The body is dense with executable commands and avoids explaining concepts Claude already knows, but at ~500 lines it includes redundancy (repeated 'Service labels are per-install' blocks, a verbose guide template, restated preflight logic) that could be tightened.	3 / 5
Actionability	Fully executable throughout — concrete bash (git worktree add, git fetch, pnpm install/build/test), copy-paste sub-agent prompts, and complete code snippets in the standard/non-standard guide examples cover the common cases.	5 / 5
Workflow Clarity	A clearly sequenced two-phase process (Phase 0 + 1.0–1.7, Phase 2 2.0–2.9) with explicit validation checkpoints (clean-tree preflight, build validation 2.6, live test 2.7, post-upgrade build 2.9, guide verification 1.7), feedback loops on build failure, and a backup-tag rollback safety net for the destructive reset.	5 / 5
Progressive Disclosure	Well-organized into labeled phases and subsections with a single one-level-deep, clearly signaled reference (.claude/skills/migrate-nanoclaw/diagnostics.md); no bundle files exist, so the main gap is the long inlined guide template and example entries that could live in a separate reference file.	4 / 5
	Total	17 / 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 is specific and distinct, clearly conveying a three-step migration workflow, but it lacks any explicit 'Use when...' trigger guidance, which limits its trigger-term quality and completeness.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when upgrading a forked NanoClaw install to upstream, migrating customizations, or when merge-based upgrades produce conflicts.'

Include natural user-facing trigger phrases and synonyms like 'upgrade my fork', 'migrate my customizations', or 'resolve upgrade merge conflicts'.

Consider naming the target project (NanoClaw) in the description itself, not just the skill name, to reduce overlap with generic migration/update skills.

Dimension	Reasoning	Score
Specificity	Names three concrete actions — 'Extracts user customizations', 'generates a replayable migration guide', 'upgrades to upstream by reapplying customizations on a clean base' — covering the workflow comprehensively, though the closing 'Replaces merge-based upgrades with intent-based migration' is positioning rather than an additional capability.	4 / 5
Completeness	The 'what' is clearly stated (extract, generate guide, upgrade) but there is no 'Use when...' clause or equivalent trigger, so 'when' is only weakly implied — capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Relevant domain terms appear ('fork', 'customizations', 'migration guide', 'upstream', 'merge-based upgrades') but the description omits the natural phrases a user would actually say ('upgrade my fork', 'migrate my customizations') and common synonyms, and lacks explicit trigger guidance.	3 / 5
Distinctiveness Conflict Risk	The fork-to-upstream migration niche is clearly carved out and distinguished from a plain update via 'Replaces merge-based upgrades with intent-based migration', with only minor overlap risk against a generic update 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
skill_md_line_count	SKILL.md is long (504 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: nanocoai/nanoclaw
Path: .claude/skills/migrate-nanoclaw/SKILL.md
Commit: ad8837c

Reviewed: 4 days 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.