CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

73

Quality

90%

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

88%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.

A well-engineered, actionable migration runbook with strong sequencing and validation despite destructive operations. The main improvement opportunity is offloading some inline reference material into bundle files for progressive disclosure.

Suggestions

Move the per-channel user-ID format table and the access-policy option list into a reference file (e.g. references/user-id-formats.md) to slim the body and improve progressive disclosure.

Tighten the Preflight rationale paragraph — the verbatim user message is essential, but the surrounding explanation of why not to run the script could be trimmed.

Consider extracting the owner-seeding and known-user-import SQL/TS snippets into a scripts/ helper so the body stays a high-level overview.

DimensionReasoningScore

Conciseness

Lean for a complex migration: concrete commands, code, and file paths with little concept explanation, though a few prose passages (e.g. the preflight rationale) could be tightened.

4 / 5

Actionability

Fully executable guidance throughout — real SQL queries, copy-paste TypeScript using named DB helpers, bash commands, and a setup-step table covering the common cases.

5 / 5

Workflow Clarity

Clear phased sequence (Preflight → Phase 0–4) with explicit validation checkpoints (smoke test in 0b, verify step at end) and feedback loops (diagnose from log and re-test; show-before-writing principle).

5 / 5

Progressive Disclosure

Well-organized into clearly signaled sections and phases, but the entire body is inline with no bundle files splitting out the larger reference material (user-ID formats, access-policy options).

4 / 5

Total

18

/

20

Passed

Description

92%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, specific description that names concrete actions, gives explicit run-order and trigger guidance, and occupies a clear niche. The only minor gap is trigger-term variety, which centers on synonymous phrasings.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Seeds the owner, migrates legacy memory, reconciles container configs, and helps port custom v1 code' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both what (finish v1→v2 migration with four named tasks) and when ('Run after `bash migrate-v2.sh` completes' plus concrete trigger phrases).

5 / 5

Trigger Term Quality

Triggers on 'migrate from v1', 'finish migration', 'v1 migration' — natural phrases a user would say, though they are near-synonyms with a few common variations missing.

4 / 5

Distinctiveness Conflict Risk

Targets a narrow, product-specific niche (NanoClaw v1→v2 finish-migration) with distinct triggers, making conflict with other skills minimal.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
nanocoai/nanoclaw
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.