CtrlK
BlogDocsLog inGet started
Tessl Logo

overall-planning

触发:当你需要在多个目标、利益方或相互制约的指标之间做动态平衡时调用;常见信号包括 trade-offs、目标冲突、系统性约束、优化一项会伤害另一项。 English: Trigger when several important goals must be advanced together and optimizing one dimension can damage another. Use this skill to map the key relationships, avoid one-sided decisions, and balance the system as a whole.

64

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/overall-planning/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 body is well-structured and actionable with concrete output templates and useful tables, making it an effective instruction-only skill. Main weakness is conciseness — material is repeated across sections and could be consolidated — and the dangling original-texts.md reference.

Suggestions

Consolidate the overlapping content between 何时使用, 方法流程, and the two tables to remove repetition and tighten token usage.

Either add the missing references/original-texts.md bundle file or remove the reference to it so signaled paths all resolve.

Trim the recurring 片面性 framing and Mao quote citations that restate the same point already made in 核心原则.

DimensionReasoningScore

Conciseness

Mostly efficient but repeats itself: 何时使用 restates step framing, the tables restate the 步骤 content, and the 片面性 theme is belabored across multiple sections; some tightening would reduce tokens without losing clarity.

3 / 5

Actionability

As an instruction-only skill it has no code (not penalized), and the 操作规程 supplies concrete fill-in output templates, explicit checks, and warning indicators that give directly usable guidance with only minor gaps.

4 / 5

Workflow Clarity

A clear six-step method followed by a five-step 操作规程 with checkpoints (片面性检查, 系统影响检查, 失衡预警指标); no formal validate→fix→retry loop, but the task is non-destructive reasoning so that is appropriate.

4 / 5

Progressive Disclosure

Well-organized with clear section headers and a single clearly-signaled reference to original-texts.md; the referenced file does not exist in the bundle, a minor gap that keeps it below 5.

4 / 5

Total

15

/

20

Passed

Description

83%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 strong: bilingual, explicit trigger guidance, and clear distinguishability from sibling skills. Specificity could be sharpened with more enumerated concrete actions, but it capably conveys both purpose and trigger conditions.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions — 'map the key relationships, avoid one-sided decisions, and balance the system as a whole' — but the actions remain somewhat abstract rather than a comprehensive enumerated list.

4 / 5

Completeness

Explicitly answers both 'what' (map relationships, avoid one-sided decisions, balance the system) and 'when' with concrete trigger phrases in both languages.

5 / 5

Trigger Term Quality

Provides explicit natural trigger signals ('trade-offs、目标冲突、系统性约束、优化一项会伤害另一项') that users would plausibly say, with good synonym coverage, though a few common phrasings are missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (dynamic balancing of competing goals) and is explicitly distinguished from concentrate-forces via the 不适用场景 section, with only minor overlap risk against general planning skills.

4 / 5

Total

17

/

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
HughYau/qiushi-skill
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.