CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

migrate-from-v1

Finish migrating a NanoClaw v1 install into v2. Run after `bash migrate-v2.sh` completes. Seeds the owner, migrates legacy memory, reconciles container configs, and helps port custom v1 code. Triggers on "migrate from v1", "finish migration", "v1 migration".

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

96%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.

An exemplary operational skill body: dense, executable, and install-specific, with a well-sequenced phase workflow, explicit validation and feedback loops, safety principles (read-only v1, show-before-write, credential masking), and a defined recovery point. The only structural weakness is that everything lives inline in SKILL.md with no reference files for the lookup-style material.

DimensionReasoningScore

Conciseness

Every section carries install-specific knowledge Claude cannot infer (handoff.json structure, user-ID formats per channel, exact helper names, service-label derivation); there is no generic concept explanation or padded prose, matching anchor 5's "every token earns its place" rather than anchor 4's trimmable over-explanation.

5 / 5

Actionability

Fully executable guidance throughout: ready-to-run SQL queries, a complete idempotent TypeScript snippet with init/migrations/cleanup, concrete bash commands (git remote check, service restart via derived unit/label), exact file paths, and a when-to-use step table — copy-paste ready and covering the common cases, matching anchor 5.

5 / 5

Workflow Clarity

Clear preflight gate, phased sequence (0–4) with explicit validation (smoke test via AskUserQuestion, "don't proceed to deeper work on a broken router", diagnose-and-re-test feedback loop, deferred-failure re-visit) and a "When done" checklist with a verify step; handoff.json is an explicit recovery point. Validation is present for the batch/destructive operations, so the workflow-clarity cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist; sections are well-organized, and the one external delegation ("Run `/migrate-memory`") is clearly signaled at one level. But at ~220 lines with no reference files, lookup-style content (per-channel user-ID formats, the setup-steps table, access-policy options) is inlined — anchor 4's "good structure, minor organization gaps" fits better than anchor 5's appropriately-split content, and the under-50-line simple-skill exception does not apply.

4 / 5

Total

19

/

20

Passed

Description

87%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.

A strong description: third-person, concise, with a clear what/when structure and an explicit trigger clause. The only weaknesses are minor coverage gaps (routing/triage work unmentioned) and a few missing trigger synonyms such as "port to v2" or "v2 migration".

Suggestions

Add trigger synonyms like "port to v2", "v2 migration", or "NanoClaw migration" to the Triggers-on clause so users phrasing it from the v2 side also match.

Mention the routing smoke-test / failed-step triage work in the action list so the description reflects all major phases, not just the four porting actions.

"helps port custom v1 code" is softer than the other verbs — "ports custom v1 skills and flags non-portable source" would be more concrete.

DimensionReasoningScore

Specificity

"Seeds the owner, migrates legacy memory, reconciles container configs, and helps port custom v1 code" names four domain-specific concrete actions, but the routing/triage phase in the body is unmentioned and "helps port" is slightly soft — anchor 4's minor gaps in coverage fits better than anchor 5's comprehensive coverage.

4 / 5

Completeness

Explicitly answers both: the "what" (four concrete migration actions) and the "when" twice — "Run after `bash migrate-v2.sh` completes" plus a dedicated "Triggers on ..." clause with concrete trigger phrases, matching the anchor-5 example structure exactly.

5 / 5

Trigger Term Quality

"migrate from v1", "finish migration", "v1 migration" are natural phrases a user would say, but common variants like "port to v2", "v2 migration", or "NanoClaw migration" are missing — good keyword coverage with a few natural terms absent, so not 5.

4 / 5

Distinctiveness Conflict Risk

"Finish migrating a NanoClaw v1 install into v2" carves a clear niche with version-specific trigger phrases; no other skill would plausibly match "migrate from v1" / "v1 migration", so conflict risk is minimal.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

nanocoai/nanoclaw

Path

.claude/skills/migrate-from-v1/SKILL.md

Reviewed

Table of Contents

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.