CtrlK
BlogDocsLog inGet started
Tessl Logo

quiet-musing

Deep reasoning framework for complex tasks. Activates for multi-step problems, high uncertainty, or trade-off decisions. 复杂问题推理框架。遇到多步骤、高不确定性、需要权衡取舍的任务时启用。Triggers: analyze complex problem, make decision, weigh options, debug hard bug, architecture design, strategy planning, think it through, help me analyze, this is complicated, deep thinking | 触发场景:分析复杂问题、做决策、权衡方案、调试疑难 bug、架构设计、策略规划、想清楚再做、帮我分析一下、这个问题比较复杂、深度思考。Do NOT activate for simple Q&A, casual chat, or single-step tasks. 不要在简单问答、闲聊、单步操作时启用。

68

Quality

82%

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

73%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 well-structured reasoning protocol with a clear sequenced workflow and explicit validation checkpoints, plus concrete good/bad examples that make the guidance actionable. It could be tightened by trimming the motivational 推理姿态 framing to improve token efficiency.

Suggestions

Tighten the 推理姿态 section: keep the one-line heuristics ('像侦探,不像法官', '错误是线索', '深度匹配复杂度', '跟用户同步') and cut the extended metaphorical elaboration to reduce padding.

The '什么时候启用' list largely duplicates the frontmatter triggers; consider referencing the description's triggers instead of restating the conditions in the body.

Phase 2's inline todo-granularity code block is helpful but could be condensed to one good/bad pair to save tokens while preserving the lesson.

DimensionReasoningScore

Conciseness

The body mostly assumes Claude's intelligence and avoids explaining basic concepts, but extended motivational framing in the 推理姿态 section (detective-vs-judge metaphor, 'errors are clues' elaboration) is padding that could be tightened without losing the actionable guidance.

3 / 5

Actionability

As an instruction-only reasoning protocol it gives concrete, specific guidance — numbered phase steps, explicit good/bad todo-granularity examples, and a verification checklist — with only minor gaps versus fully executable instruction.

4 / 5

Workflow Clarity

A clear 5-phase sequence (理解→拆解→多路径思考→执行→验证) with an explicit Phase 5 validation checklist and feedback-loop guidance in Phase 4 ('遇到阻塞不硬冲…停下来想为什么'), matching the score-5 anchor for clear sequence with validation steps and checklists.

5 / 5

Progressive Disclosure

A single self-contained body with well-organized phase headers and no nested references; it slightly exceeds the simple-skill line length, so it sits just below the score-5 'well-organized short skill' case.

4 / 5

Total

16

/

20

Passed

Description

91%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 bilingual description that clearly states what the skill does and when to activate it, with comprehensive natural trigger terms and useful negative-trigger guidance. Minor overlap risk from a few generic phrases keeps distinctiveness just below perfect.

DimensionReasoningScore

Specificity

Names the domain (deep reasoning for complex tasks) and enumerates several concrete trigger scenarios (multi-step problems, high uncertainty, trade-off decisions, architecture design, debug hard bug, strategy planning), but describes scenarios rather than discrete granular actions, leaving minor coverage gaps relative to the score-5 anchor.

4 / 5

Completeness

Explicitly answers both 'what' (deep reasoning framework for complex tasks) and 'when' (a labeled 'Triggers:' list plus an explicit 'Do NOT activate for...' exclusion), matching the score-5 anchor with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive coverage of natural user phrases in both English ('think it through', 'help me analyze', 'this is complicated', 'weigh options') and Chinese, including synonyms and bilingual variants a user would naturally say.

5 / 5

Distinctiveness Conflict Risk

It carves a clear niche (complex multi-step trade-off reasoning) and adds exclusion criteria, but broad terms like 'help me analyze' and 'deep thinking' create minor overlap risk with general analysis skills.

4 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
liliMozi/openhanako
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.