CtrlK
BlogDocsLog inGet started
Tessl Logo

migrate-memory

Migrate legacy NanoClaw and Claude-native memory into the shared memory tree and provider-neutral standing instructions. Run after an update reports the shared-memory breaking change, or when a group still has .seed.md, legacy CLAUDE.md/CLAUDE.local.md, Claude auto-memory, or an unindexed imported-agent-memory.md. Triggers on "migrate memory", "legacy memory", "the agent forgot everything after the switch".

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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 detailed, highly actionable migration workflow with strong sequencing and validation for a destructive operation. Its main weaknesses are minor verbosity (a symlink concept explanation and repeated collision rules) and a monolithic structure with no progressive disclosure via reference files.

Suggestions

State the collision-safe numeric-suffix rename rule once near the top of section 3 and reference it from each file-type subsection instead of repeating it five times.

Remove or condense the 'A symlink is a pointer to another path...' explanation in 'Explain quarantined links plainly' — assume Claude knows what a symlink is and keep only the operator-facing message template and safety rule.

Move the operator-facing quarantine message template (the text block in section 3) into a referenced file such as references/quarantine-message.md so the main body stays a concise overview.

DimensionReasoningScore

Conciseness

Mostly lean and procedural with no padding, but the 'Explain quarantined links plainly' section explains what a symlink is ('A symlink is a pointer to another path, not the memory content itself') — a concept Claude already knows — and the collision-safe numeric-suffix rename rules are repeated across each file-type subsection rather than stated once.

2 / 3

Actionability

Highly executable: concrete commands (ncl groups list, ncl tasks pause/resume, ncl groups restart), specific lstat-equivalent checks (test -L/-f/-e), exact template paths, readlink usage, and per-file-type rename targets with collision handling.

3 / 3

Workflow Clarity

A clear 5-step sequence (Inventory, Prepare tree, Move legacy, Organize, Verify/rollback) with explicit validation checkpoints — operator approval before moves, 'stop for operator review' on bad path types, lstat re-inspection, a verify checklist, and a recorded rollback procedure for this destructive batch operation.

3 / 3

Progressive Disclosure

Well organized into numbered sections, but it is a monolithic ~244-line document with no external references; the operator messaging template and per-file-type move rules are inline content that, for a skill this complex, could be split into one-level-deep reference files. Not a 3 because there are no signaled references and the under-50-line exception does not apply.

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: concrete actions, explicit what-and-when guidance, natural trigger phrases, and a distinct niche with named legacy artifacts. Uses third person/imperative voice throughout with no over-claims.

DimensionReasoningScore

Specificity

Lists concrete actions with named sources and destinations: 'Migrate legacy NanoClaw and Claude-native memory into the shared memory tree and provider-neutral standing instructions', plus named artifacts like .seed.md, CLAUDE.md/CLAUDE.local.md, and imported-agent-memory.md.

3 / 3

Completeness

Clearly answers both what (migrate legacy memory into the shared tree and standing instructions) and when ('Run after an update reports the shared-memory breaking change, or when a group still has ...' and explicit 'Triggers on ...'). Not a 2 because explicit trigger guidance is present.

3 / 3

Trigger Term Quality

Natural user phrases are explicit: Triggers on "migrate memory", "legacy memory", "the agent forgot everything after the switch", plus 'Run after an update reports the shared-memory breaking change' — terms a user would naturally say.

3 / 3

Distinctiveness Conflict Risk

A narrow niche (NanoClaw/Claude legacy memory migration) with highly specific filenames and triggers makes conflict with other skills very unlikely.

3 / 3

Total

12

/

12

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.