CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

frontend-architecture

主仓库前端的窗口模型和聊天 surface 的不变式——Electron 多窗口怎么判断、chat.html 被两种宿主共用、手机模式怎么排除、启动时序、react-neko-chat 的 full / compact、static/ 搬目录。改 static/、templates/、frontend/react-neko-chat/、main_routers/pages_router.py,或者排查「网页正常、桌面端不对」之前读。

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

93%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.

An exemplary architecture-invariants skill: lean, dense with exact identifiers and executable checks, with validation checkpoints embedded in the risky rules and an excellent condition-based references index. The only gap is the absence of an enumerated checklist for the static/ migration reference points.

DimensionReasoningScore

Conciseness

The body states 「这里只补那些文档没有、读代码也不容易看出来的部分」 and delivers exactly that: 13 dense invariant rules with exact identifiers, flags, and issue references, no padding and no explanation of concepts Claude already knows. Every token earns its place.

5 / 5

Actionability

Gives copy-ready executable guidance throughout: the exact gate expression `window.__NEKO_MULTI_WINDOW__ === true && /^\/chat(?:_full)?(?:\/|$)/.test(location.pathname)`, exact classes and flags (`body.neko-electron-runtime`, `lanlan-pet-mode`, `electron-chat-window`), the required attribute `data-compact-hit-region="true"`, and concrete commands (`npm run build`, `getComputedStyle`, `getBoundingClientRect`, `elementFromPoint`). As an instruction-only skill its guidance is fully actionable.

5 / 5

Workflow Clarity

Not a linear pipeline but a rule compendium, and the risky rules do carry explicit checkpoints: 「要分别验证三条路径」 (rule 8), 「要跑读它的 Python 测试」 (rule 9), and 「改前改后各量一次」 (rule 12). It falls short of 5 because there is no end-to-end sequence and the static/ migration checklist (rule 13) only gestures at 「四种写法的测试断言」 without enumerating where they live.

4 / 5

Progressive Disclosure

The body keeps only the highest-frequency gotchas inline, delegates base facts to existing docs (`.agent/rules/neko-guide.md`, `docs/frontend/...`), and routes details to five one-level-deep reference files — all verified present in references/ — via a 「references 索引」 table that states exactly when to read each file. Clear overview, well-signaled navigation, appropriate split.

5 / 5

Total

19

/

20

Passed

Description

87%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 highly specific, well-triggered description: it names concrete topics and file paths, gives an explicit read-before trigger including a natural troubleshooting symptom, and occupies a distinct niche. The only minor weakness is that capabilities are framed as topic areas rather than actions.

DimensionReasoningScore

Specificity

Enumerates six concrete, distinct topics (Electron 多窗口怎么判断、chat.html 被两种宿主共用、手机模式怎么排除、启动时序、full / compact、static/ 搬目录), giving comprehensive coverage of the domain, but they are stated as topics/invariants rather than concrete actions, so they fall a notch below the 5 anchor.

4 / 5

Completeness

Explicitly answers both what (the enumerated window-model and chat-surface invariants) and when with concrete trigger phrases: 「改 static/、templates/、frontend/react-neko-chat/、main_routers/pages_router.py,或者排查『网页正常、桌面端不对』之前读」. The when-clause is specific and symptom-based, not merely present, so it is not the 4 anchor.

5 / 5

Trigger Term Quality

Includes concrete file paths users would touch (static/、templates/、frontend/react-neko-chat/、main_routers/pages_router.py) and the very natural symptom phrase 「网页正常、桌面端不对」, but a few natural synonyms (e.g. 桌宠窗口、Electron 窗口) are only implicit, matching 'good keyword coverage; a few natural terms missing'.

4 / 5

Distinctiveness Conflict Risk

Scoped to this repository's specific frontend window model (react-neko-chat, chat.html, pages_router.py), giving a clear niche with distinct file-path and symptom triggers and minimal conflict risk with any generic skill.

5 / 5

Total

18

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Project-N-E-K-O/N.E.K.O

Path

.agent/skills/frontend-architecture/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.