DSH Plugins技能

unlazy

Leonxlnx/unlazy

unlazy is a tool for DeepSeek Harness. Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.

查看仓库

Stars: 3.2k
Forks: 219
Issues: 2
Update: 13 days

REVIEW SCORECARD

评测成绩单

8.5/10Excellent

detail.dimSecurity9.0

detail.dimQuality9.0

detail.dimContent7.0

detail.dimDeps7.0

detail.dimMaintenance9.0

✓ 无Risky检出 · 自动化扫描结果仅供参考，非官方背书

AI DEEP REVIEW

AI 深度评测

7.8/10Consider

A well-documented anti-laziness skill with runnable verification gates, but its unkeyed evidence binding and shell-execu

Code quality8

README documents a Node 16+ checker with no third-party runtime deps, a parser with explicit rejection rules, a lint script, and a versioned SHA-256 evidence fingerprint, indicating deliberate engineering, though no test suite or CI is mentioned.

Security7

The checker executes arbitrary shell code from CHECK: lines and the README itself admits evidence is unkeyed and forgeable by anyone who can edit the ledger, but it mitigates with an approval store outside the repo, a non-executing --status mode, and explicit PATH/shell warnings.

Utility8

It targets a real and commonly reported pain point (premature completion and underthinking in agentic coding work) with a concrete acceptance-ledger workflow rather than vague prompt advice.

Maintenance8

Last updated 2026-09-03 with an unreleased 2.1.0 change set and a CHANGELOG, and the repo is not archived, indicating active development, though the README notes no tagged GitHub release exists.

Docs8

The README covers install for multiple agents, a quick start, a full gate contract example, shell/PATH caveats, and links to references and templates, though the security section is visibly truncated mid-sentence.

Generated by AI after reading the project README, as a decision aid; neutral scores are given when information is thin. Not an official endorsement.

PROJECT README项目说明展开Collapse

正在读取 GitHub README...

INSTALL REFERENCE

安装参考

待结构检查

npx skills add Leonxlnx/unlazy

This command comes from an explicit install reference in the README and is provided for reference only — it is never auto-executed by a DSH host.

PROJECT TOPICS

项目标签

ai-agents claude claude-code llm productivity prompt-engineering skill

VALIDATION LADDER

验证进度

待结构检查

01市场发现Passed

02归类识别Passed

03结构检查Pending

04实机验证Pending

FAQ

Frequently Asked Questions

What is unlazy used for?

Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 resear

How popular is unlazy?

unlazy has 3,246 stars and 219 forks on GitHub, last updated 2026-09-03.

What license does unlazy use?

unlazy is distributed under the MIT license.

Is unlazy compatible with DeepSeek Harness?

unlazy is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.

CLASSIFICATION EVIDENCE