migrate-from-openclaw

Migrate from OpenClaw to NanoClaw v2. Detects an existing OpenClaw installation, extracts identity, channel credentials, scheduled tasks, and other config, then guides interactive migration. Triggers on "migrate from openclaw", "openclaw migration", "import from openclaw".

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

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.

A thorough, highly actionable migration guide with a well-sequenced phased workflow and real validation. Its main weaknesses are some restated verbosity and, more seriously, references to bundle files that do not exist, leaving parts of the disclosure model unresolvable.

Suggestions

Add the missing bundle files to the skill (REMOVE.md, MIGRATE_CRONS.md, and scripts/init-first-agent.ts) or inline the delegated content — Phase 5 currently cannot be executed because its task-model detail lives only in the absent MIGRATE_CRONS.md.

Tighten the credential-routing guidance to a single authoritative statement and reduce the Phase 8 summary to a terse checklist to remove redundancy.

Verify every path cited as ${CLAUDE_SKILL_DIR}/... or a bundled script resolves to a file actually shipped in the bundle.

Dimension	Reasoning	Score
Conciseness	Most of the body is concrete, product-specific guidance Claude would not already know, but credential routing is restated across the conformance section, Phase 3 plugins, and Phase 4, and the closing summary verbose-restates each migrated item rather than serving as a terse checklist — it could be tightened.	2 / 3
Actionability	It provides copy-paste-ready commands (pnpm exec tsx, ncl, onecli secrets, cp) with real flags and concrete field mappings (e.g. '--platform-id <channel>:<dm-id>', auth-profiles.json key paths), fully executable rather than pseudocode.	3 / 3
Workflow Clarity	A clear Phase 0–8 sequence with an explicit validation checkpoint in Phase 8 (copy + run vitest) and a feedback loop via migration-state.md re-read before each phase, plus 'show proposed edits before applying' confirmation gates on destructive/batch steps.	3 / 3
Progressive Disclosure	The phase structure and bundled scripts are well organized, but referenced bundle files are broken: REMOVE.md, MIGRATE_CRONS.md, and scripts/init-first-agent.ts are cited as skill resources yet are absent from the actual scripts/ bundle, and Phase 5 delegates its entire detail to the missing MIGRATE_CRONS.md.	2 / 3
	Total	10 / 12 Passed

Description

100%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.

A strong description: third-person voice, concrete enumerated actions, and an explicit trigger clause covering both purpose and activation. It is concise without fluff and occupies a clear niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Detects an existing OpenClaw installation, extracts identity, channel credentials, scheduled tasks, and other config, then guides interactive migration' — matching the anchor for enumerating specific actions rather than vague language.	3 / 3
Completeness	It states what the skill does (detect, extract, guide migration) and provides explicit 'Triggers on ...' guidance for when to use it, satisfying both the what and the when with an explicit trigger clause.	3 / 3
Trigger Term Quality	The triggers 'migrate from openclaw', 'openclaw migration', and 'import from openclaw' are natural phrases a user would say when needing this skill, giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The OpenClaw-to-NanoClaw v2 migration niche with product-specific triggers is clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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 (535 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	14 / 16 Passed

Repository: nanocoai/nanoclaw
Path: .claude/skills/migrate-from-openclaw/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.