sn-update

Update SenseNova Skills (the sn-* bundle) inside an OpenClaw or hermes-agent install. ALWAYS use this skill when the user says any of: "update SenseNova skills", "update SN skills", "更新 sensenova skills", "更新 sn skills", "刷新 sn-*", "升级 sn-* skills", or names a specific sn-* skill to update (e.g. "更新 sn-ppt-standard", "refresh sn-image-base"). Default scope is the whole sn-* bundle; if the user names specific skills, update ONLY those.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

75%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 dense, well-sequenced instruction skill that assumes competence and bakes in validation for a destructive batch operation. It is solid across all dimensions but leaves minor gaps: a few steps are high-level English rather than literal commands, and there is no explicit post-install verification.

Suggestions

Add an explicit post-install verification step (e.g., confirm the copied SKILL.md parses and .sn-version matches the upstream subtree SHA) before reporting success, since install overwrites existing skills.

Promote the high-level English steps to literal commands where feasible — e.g., give the sparse-checkout set command and the backup-retention prune command (ls/sort/tail | xargs rm) so they are copy-paste ready.

Tighten the partial-clone caveat (lines 64-69) to the essential warning that --filter=blob:none only stays small with --no-checkout plus sparse-checkout, trimming the explanatory aside.

Dimension	Reasoning	Score
Conciseness	Mostly lean and imperative with terse tables and bullets that assume git/YAML competence; the partial-clone blob:none caveat is a touch verbose but earns its place by preventing a real misunderstanding, so it sits just below the score-5 anchor.	4 / 5
Actionability	Provides concrete commands (git log -1 --format=%H, git describe --tags --abbrev=0, --filter=blob:none --no-checkout) and exact paths/formats, but several steps (sparse-checkout re-apply, backup retention prune, move-into-bucket) are given as precise English rather than copy-paste commands.	4 / 5
Workflow Clarity	Clear sequenced sections (scope → target → sync → compare → install → retention → report) with explicit validation (error-and-stop on missing upstream, backup-before-overwrite, retention pruning, separate error reporting); the gap is no explicit post-install integrity/load check, relevant for a destructive overwrite.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections separated by horizontal rules with easy navigation and no nested or buried references; at ~130 lines with no bundle files it has good structure but does not meet the score-5 anchor's one-level-deep reference split.	4 / 5
	Total	16 / 20 Passed

Description

90%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 that explicitly covers what and when with a comprehensive bilingual set of natural trigger phrases and a clearly distinct niche. The only soft spot is specificity, which lists one core action rather than several.

Dimension	Reasoning	Score
Specificity	Names the domain concretely ('Update SenseNova Skills (the sn-* bundle) inside an OpenClaw or hermes-agent install') with one clear action (update/refresh) plus behavioral scoping, but does not list several distinct actions like the score-4 anchor requires.	3 / 5
Completeness	Explicitly answers both what ('Update SenseNova Skills ... inside an OpenClaw or hermes-agent install') and when ('ALWAYS use this skill when the user says any of: ...') with concrete trigger phrases, plus scope clarification.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage in both English and Chinese ('update SenseNova skills', 'update SN skills', '更新 sensenova skills', '刷新 sn-', '升级 sn- skills') including synonyms and concrete skill-name examples, matching the comprehensive-synonyms anchor.	5 / 5
Distinctiveness Conflict Risk	Clear niche (sn-* skill updates in specific agent installs) with highly distinct triggers (sn-*, SenseNova, named skills) that would not naturally fire for unrelated skills, giving minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: OpenSenseNova/SenseNova-Skills
Path: skills/sn-update/SKILL.md
Commit: 61b60bb

Reviewed: 8 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.