huashu-skill-updater

检查并更新花叔系 skills。当用户说「检查skill更新」「更新花叔的skill」「skill是不是最新的」时触发；当会话中用到任何花叔系 skill（huashu-* / nuwa / darwin / freud / seedance / tramstop / dukou 等），且其安装目录里的 .huashu-skill-meta.json 的 last_checked 距今超过 30 天（或 git 安装的超过 30 天未 fetch）时，也应主动触发一次检查。

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./huashu-skill-updater/SKILL.md

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.

The content is actionable and well-structured, externalizing implementation detail to a real script while keeping the SKILL.md as a clear overview with concrete commands and a sensible workflow. It could improve by replacing placeholder update commands with fuller examples and tightening a few explanatory asides.

Suggestions

Replace the <名字> placeholders in the update commands with a concrete worked example for one skill so the update path is fully copy-paste ready.

Tighten or remove incidental commentary like '方便接 cron' and the opening rationale sentence to push conciseness toward fully lean.

Make the pre-overwrite validation an explicit step in the numbered workflow rather than a conditional sentence, to strengthen the feedback-loop clarity.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes competence, with concrete commands and a tight metadata spec; only minor asides ('方便接 cron', the opening rationale sentence) could be trimmed, so it sits above the midpoint but not at fully lean.	4 / 5
Actionability	Provides several copy-paste-ready commands (check_updates.py invocations, git pull --ff-only, cron line), but the update path uses <名字> placeholders requiring substitution and conditional guidance, leaving minor gaps versus fully executable coverage.	4 / 5
Workflow Clarity	Clear sequenced workflow (full check -> mark-checked -> git vs copy update -> metadata -> cron) with a confirmation gate before the destructive overwrite, plus exit-code feedback; not a 5 because the validation is a confirm step rather than an explicit validate-fix-retry loop.	4 / 5
Progressive Disclosure	Well-organized into clear sections with the bulk detection logic appropriately externalized to scripts/check_updates.py (a real referenced file) rather than inlined; minor gaps (the inline agent-rules list is slightly long) keep it just below the pristine one-level-deep reference ideal.	4 / 5
	Total	16 / 20 Passed

Description

82%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 well-constructed: it states the purpose, gives concrete natural-language triggers, and adds a precise proactive-trigger condition tied to metadata freshness. Its only weakness is moderate specificity — it names check/update but not the full range of supporting operations.

Dimension	Reasoning	Score
Specificity	Names the domain ('检查并更新花叔系 skills') with two concrete actions (检查/更新) and lists specific skill identifiers, but does not enumerate the full set of operations the skill performs, so it stays at the 1-2 concrete actions anchor rather than comprehensive coverage.	3 / 5
Completeness	Explicitly answers both what (检查并更新花叔系 skills) and when, with concrete trigger phrases and an explicit proactive trigger condition based on the 30-day last_checked rule.	5 / 5
Trigger Term Quality	Provides three natural user utterances ('检查skill更新'、'更新花叔的skill'、'skill是不是最新的') plus a proactive condition, giving good keyword coverage, but lacks synonyms and extensions that would make it comprehensive.	4 / 5
Distinctiveness Conflict Risk	Targets a clearly defined niche (花叔系 skills, enumerating huashu-* / nuwa / darwin / etc.) with distinct triggers, making conflict with unrelated skills minimal.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alchaincyf/huashu-skills
Path: huashu-skill-updater/SKILL.md
Commit: 49a55ba

Reviewed: 3 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.