CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/migrate-nanoclaw/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

This is a highly actionable, well-sequenced skill: exact commands, verbatim sub-agent prompts, validation checkpoints, and rollback paths cover even the destructive steps. Its weaknesses are the monolithic single-file layout with ~120 lines of template/example content that belongs in a reference file, and some duplicated guidance (absolute-path rule, reset rationale).

Suggestions

Move the migration-guide template and the standard/non-standard example entries out of section 1.7 into a reference file (e.g. references/guide-template.md) and link to it, keeping only the structure skeleton and detail-level rules inline.

State the absolute-path worktree rule once (Principles) and reference it from 2.3/2.2.8 instead of restating it three times, and drop 2.8's closing paragraph that re-explains the reset already performed in its step 4.

Consider a short phase-map at the top (Phase 0 refresh → Phase 1 extract → Phase 2 upgrade) so a fresh session can orient before the detail.

DimensionReasoningScore

Conciseness

The body is command-dense and assumes competence — no space is wasted explaining git, worktrees, or pnpm. Minor over-explanation and real duplication exist (the absolute-path rule is stated in Principles, 2.3, and 2.8; 2.8's closing paragraph restates the already-executed reset --hard step), matching anchor 4 ("efficient; minor instances of over-explanation that could be trimmed") rather than anchor 3, since the padding is a small fraction of genuinely load-bearing content.

4 / 5

Actionability

Nearly every step ships copy-paste-ready commands (git worktree add, backup branch/tag creation, symlink and service-restart recipes, the upgrade-marker tsx invocation) plus verbatim sub-agent prompts and two complete example guide entries with real code snippets. This matches anchor 5 ("fully executable; copy-paste ready; specific examples cover the common cases").

5 / 5

Workflow Clarity

Phases 0–2 with numbered sub-steps form a coherent sequence, and validation is explicit throughout: clean-tree preflight, guide read-back verification, the new-changes hash guard, build/test in the worktree, optional live test, and post-upgrade build before the required tripwire stamp. Destructive operations (git reset --hard, worktree remove --force) are wrapped in backup tags and rollback instructions, matching anchor 5 ("clear sequence with explicit validation steps; feedback loops for error recovery").

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), so all ~500 lines live inline in SKILL.md; the guide template plus the two example guide entries (~120 lines) and the tier-conditions text clearly belong in a separate reference file. The one external reference (.claude/skills/migrate-nanoclaw/diagnostics.md) is one level deep but cannot be verified here and is only surfaced at the very end. This matches anchor 3 ("some structure; content that should be separate is inline") better than anchor 4, despite good section headers.

3 / 5

Total

17

/

20

Passed

Description

70%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.

The description is concrete, third-person, and distinctive, accurately summarizing the extract-guide-then-reapply workflow. Its one real weakness is the complete absence of a 'when to use this' trigger clause, which caps completeness and leaves users without explicit invocation guidance.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user wants to upgrade a customized NanoClaw fork to upstream, or when git merge with upstream produces conflicts."

Include natural synonym phrasings users would actually say — "update my fork", "sync with upstream", "pull upstream changes" — to improve trigger-term coverage.

Optionally mention the safety rails (backup branch/tag, worktree validation, rollback) to round out coverage of what the skill does.

DimensionReasoningScore

Specificity

"Extracts user customizations from a fork, generates a replayable migration guide, and upgrades to upstream by reapplying customizations on a clean base" lists several concrete, verb-led actions covering the skill's lifecycle. It stops short of anchor 5's comprehensive coverage — supporting capabilities like conflict detection, validation, or rollback are not mentioned — so anchor 4 ("several specific actions; minor gaps") is the closest fit.

4 / 5

Completeness

The 'what' is clear and detailed across two sentences, but there is no 'Use when...' clause or equivalent explicit trigger guidance — e.g. nothing like "Use when upstream NanoClaw ships updates and your fork has conflicts". Per the judging guideline, a missing explicit trigger clause caps completeness at 3, which is exactly this case: clear 'what', absent 'when'.

3 / 5

Trigger Term Quality

Strong domain keywords a user would plausibly say: "fork", "customizations", "upstream", "migration guide", "merge-based upgrades". Common natural variations like "update my fork", "sync with upstream", or "pull upstream changes" are absent, matching anchor 4 ("good keyword coverage; a few natural terms missing") rather than anchor 5's synonym-and-variation completeness.

4 / 5

Distinctiveness Conflict Risk

The fork/customization/upstream-reapply framing carves out a clear niche that few other skills would occupy, and its triggers (fork divergence, merge conflicts on upgrade) are distinct. Anchor 5 ("clear niche with distinct triggers; minimal conflict risk") fits; there is no meaningful overlap with generic git or document skills.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

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.