CtrlK
BlogDocsLog inGet started
Tessl Logo

login-manager

平台登录态管理。约定各平台登录流程(强制有头手动登录)、探活规则、中央 cookie+UA 存储路径约定。仅管 4 个平台(douyin/kuaishou/bilibili/xhs-browse)。

60

Quality

72%

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 ./crews/main/skills/login-manager/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with a well-sequenced, validation-rich workflow, but it carries notable inline redundancy and a large rationale/原理 block that could be offloaded to reference files for better progressive disclosure and token economy.

Suggestions

Move the detailed '背后的原理' internals (per-platform cookie fields, pong endpoints, HTML login-wall detection regex) into a separate reference file (e.g. references/internals.md) and keep SKILL.md as a concise overview that links to it.

De-duplicate the repeated cautionary statements (no-cookie-import, no-retry, fail-first concurrency) — state each once in the most relevant section rather than restating across 用法/注意事项/原理.

DimensionReasoningScore

Conciseness

The body is mostly efficient and uses tables/commands tightly, but the '背后的原理' section re-explains a lot of operational rationale and repeated cautions (e.g. the no-cookie-import and fail-first points are stated multiple times across sections), so it could be tightened — it sits above the verbose anchor but below the lean 'every token earns its place' level.

2 / 3

Actionability

It provides concrete, copy-paste-ready commands (camoufox-cli open, login-manager --platform), a real exit-code table mapping each code to an agent action, and references the actual scripts/export-and-verify.ts, matching the 'fully executable code/commands; copy-paste ready' anchor.

3 / 3

Workflow Clarity

A clear 3-step sequence with explicit validation checkpoints (two-tier 探活 verify before commit, exit codes 0/1/2, '不重试' feedback policy, session retention on failure), satisfying the 'clear sequence with explicit validation steps and feedback loops for error recovery' anchor.

3 / 3

Progressive Disclosure

Structure is reasonable (用法 / 注意事项 / 原理) with a real one-level-deep reference to scripts/export-and-verify.ts and _shared/check-session.ts, but the body inlines a large amount of '原理' detail (cookie field lists, pong endpoints, HTML login-wall detection) that could live in a separate reference file, so it is 'some structure but content that should be separate is inline' rather than the cleanly-split 3-anchor.

2 / 3

Total

10

/

12

Passed

Description

67%

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 well-scoped to a clear niche (four named platforms), but it lacks an explicit 'use when' trigger clause and only has partial coverage of natural trigger terms.

Suggestions

Add an explicit 'Use when ...' clause, e.g. '当需要为 douyin/bilibili/kuaishou/xhs-browse 完成或排查登录、刷新失效登录态、落盘 cookie+UA 时使用' to satisfy the completeness 'when' requirement.

Include more natural user-facing trigger terms (登录、扫码登录、登录失效/过期、重登、cookie 掉线) alongside the technical terms to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Names several concrete actions: 登录流程(强制有头手动登录)、探活规则、中央 cookie+UA 存储路径约定, matching the 'lists multiple specific concrete actions' anchor rather than the single-domain anchor at 2.

3 / 3

Completeness

It clearly states 'what' (平台登录态管理 + the specific conventions it governs) but there is no 'Use when...' / 'when to use' clause — the 'when' is only implied by naming the four platforms, which per the guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

It uses domain terms like '登录态' and platform keys (douyin/kuaishou/bilibili/xhs-browse), which a user needing login management might say, but it lacks the common colloquial variations a user would naturally say (e.g. '登录', '扫码登录', 'cookie 失效', '重登'), so it is only 'some relevant keywords' rather than full coverage.

2 / 3

Distinctiveness Conflict Risk

It explicitly scopes to only four named platforms and states other platforms are NOT handled here, giving it a clear niche unlikely to trigger for the wrong skill — matching the 'clear niche with distinct triggers' anchor.

3 / 3

Total

10

/

12

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
TeamWiseFlow/xiaobei
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.