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

72%

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

77%Weight 40%Scale 1-3

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

The content is highly actionable with concrete commands, code, and sub-agent prompts, and the phased workflow is clearly sequenced with validation and rollback checkpoints; its main weakness is verbosity and a monolithic structure that could offload detail into reference files.

Suggestions

Tighten the tier-conditions prose and consolidate repeated safety/rollback commentary to reduce length without losing the validation checkpoints.

Move the large inline migration-guide template (1.7) and the Phase 2 swap/live-test procedures into reference files referenced one level deep, leaving SKILL.md as an overview — this would also improve progressive_disclosure.

Keep the executable command blocks and sub-agent prompts intact — they are the strongest, most copy-paste-ready part of the skill.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and actionable but runs ~500 lines with repeated safety rationale, prose-heavy tier descriptions, and embedded sub-agent prompts that could be tightened; it does not pad with basic concepts Claude already knows, so it is above a 1 but not the lean 3.	2 / 3
Actionability	Provides fully executable bash/git commands, exact file paths, complete code snippets, and copy-paste-ready sub-agent prompts — matching the anchor for fully executable, copy-paste-ready guidance.	3 / 3
Workflow Clarity	Phases are explicitly sequenced (0 through 2.9) with validation checkpoints (1.7 guide verification, 2.6 build/test), error-recovery feedback loops ('If build fails... Fix only issues caused by the migration'), and rollback/backups before destructive ops like git reset --hard.	3 / 3
Progressive Disclosure	Sections are clearly labeled and the trailing diagnostics.md reference is one level deep, but the skill is a largely monolithic ~500-line wall of text with no bundle files — large content that could be split out (guide template, tier logic, Phase 2 swap procedure) lives inline, so it does not reach the well-split 3.	2 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 clearly distinguishable, listing multiple concrete actions in a distinct niche, but it omits an explicit 'Use when...' trigger and leans on internal jargon rather than natural user-facing terms.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases a user would actually say (e.g. 'Use when upgrading or migrating a forked NanoClaw install to upstream, or when merge-based upgrades hit conflicts').

Soften internal jargon ('intent-based migration', 'replayable migration guide') with user-facing equivalents so trigger terms match how users describe the problem.

Keep the concrete action list as-is — it is the strongest part of the description.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Extracts user customizations from a fork', 'generates a replayable migration guide', 'upgrades to upstream by reapplying customizations on a clean base' — matching the anchor that lists several specific concrete actions.	3 / 3
Completeness	It clearly answers 'what does this do' but provides no explicit 'when should Claude use it' trigger; per the judging guidelines a missing 'Use when...' clause caps completeness at 2.	2 / 3
Trigger Term Quality	Uses relevant domain keywords ('fork', 'upstream', 'merge-based upgrades') but relies on internal/technical jargon and lacks the natural terms a user would say ('migrate/upgrade my NanoClaw fork'); no explicit 'Use when...' trigger list with common variations, so it stops short of a 3.	2 / 3
Distinctiveness Conflict Risk	The intent-based fork-to-upstream migration niche is distinct from other skills and unlikely to trigger for the wrong skill, matching the clear-niche anchor.	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
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: 641963c

Reviewed: 6 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.