update-nanoclaw

Efficiently bring upstream NanoClaw updates into a customized install, with preview, selective cherry-pick, and low token usage.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/update-nanoclaw/SKILL.md

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.

The body is highly actionable and exceptionally well-sequenced with strong validation feedback loops for a risky git operation. Its weaknesses are conciseness (a redundant overview that restates the detailed steps) and progressive disclosure (a monolithic single file with references to non-existent bundle files).

Suggestions

Trim or remove the opening 'About'/'How it works' overview since it restates Steps 0-8, or compress it to a few pointer lines.

Move large peripheral sections (Known behavior changes, OneCLI upgrade details, the Step 7 hand-off narrative) into separate reference files and link to them one level deep.

Either add the referenced diagnostics.md and docs/onecli-upgrades.md to the bundle or remove the dangling references, since progressive disclosure is judged against the actual bundle structure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and action-oriented, but the opening 'About'/'How it works' overview (lines 6-49) largely duplicates the later Steps 0-8, and passages like Step 7's hand-off narrative and 'Known behavior changes' could be tightened, matching the score-2 anchor of mostly efficient with some unnecessary content.	2 / 3
Actionability	Dense with concrete, copy-paste-ready commands (git status --porcelain, git merge-base, git cherry-pick, pnpm run build, etc.), fully executable with specific examples rather than vague direction.	3 / 3
Workflow Clarity	Clearly sequenced Steps 0a through 8 with explicit validation checkpoints (Step 5 build/test, dry-run conflict preview, rebase abort after 3 rounds, build-fail fix loops), providing the feedback loops the rubric expects for destructive git operations.	3 / 3
Progressive Disclosure	The ~360-line body is a single monolithic file with good section structure, but content that could be split (Known behavior changes, OneCLI upgrade, detailed hand-off) is inline, and its only external references (diagnostics.md, docs/onecli-upgrades.md) point to files absent from the bundle, matching the score-2 anchor of some structure with content that should be separate kept inline.	2 / 3
	Total	10 / 12 Passed

Description

67%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.

The description is specific and clearly niche-scoped, naming concrete actions like preview and cherry-pick. Its main weakness is the absence of an explicit "Use when..." trigger clause and somewhat technical trigger terms that limit natural discoverability.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when you need to sync or pull upstream NanoClaw updates into your customized fork without losing local modifications.'

Broaden trigger terms with natural phrasings users would say (e.g. 'sync', 'pull upstream changes', 'update my fork') alongside 'cherry-pick' and 'preview'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "bring upstream NanoClaw updates", "preview", "selective cherry-pick", "low token usage" — comparable to the score-3 example listing several specific operations rather than a single vague one.	3 / 3
Completeness	Clearly states what the skill does but has no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	Includes some relevant terms ("upstream", "updates", "preview", "cherry-pick") but leans technical and omits common natural variations a user might say ("sync", "pull changes", "merge upstream"), matching the score-2 anchor of some relevant keywords but missing common variations.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche ("upstream NanoClaw updates into a customized install") with distinct, narrow triggers unlikely to overlap with other skills.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: nanocoai/nanoclaw
Path: .claude/skills/update-nanoclaw/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.