concentrate-forces

触发：当多个任务同时争夺时间、注意力、算力或预算，必须确定主攻方向并停止分散用力时调用；常见信号包括优先级过多、资源紧张、推进分散、需要决定先做什么。 English: Trigger when limited resources are being split across too many tasks and one main target must be chosen. Use this skill to concentrate effort, sequence work decisively, and finish a meaningful breakthrough before expanding.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/concentrate-forces/SKILL.md

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 a strong instruction-only skill: actionable operating procedure, clear sequenced workflow with validation gates, and good section organization. Its main weaknesses are verbosity from restating the same principle across several sections and a progressive-disclosure gap where the referenced original-texts.md file is missing.

Suggestions

Create the referenced original-texts.md in references/ (or remove the dangling "详细原著依据见 original-texts.md" pointer) so signaled references resolve to real files.

Consolidate the overlapping framings of the same principle (何时使用, 十大军事原则映射 table, 常见错误 table) to reduce repetition and trim token cost.

Move the detailed mapping/common-error tables into a reference file and keep SKILL.md as a lean overview pointing to them, improving both conciseness and progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and does not explain concepts Claude already knows, but it is long (~155 lines) and restates the core "concentrate on one, finish it, then move on" idea across multiple overlapping sections (何时使用, 方法流程, tables, 操作规程) that could be tightened.	2 / 3
Actionability	It gives concrete, executable guidance: a TodoWrite-based task matrix with specific impact/difficulty/dependency tags, explicit 首选/次选/末选 selection criteria, and a copy-paste-ready 🎯 declaration template with rules for mid-stream new requests.	3 / 3
Workflow Clarity	The six-step method (第一步–第六步) is clearly sequenced with explicit checkpoints — step 4 "验证完成", step 6 preparation checklist, and the "完成并验证后，才转向下一个目标" gate — providing the validation/feedback loops the rubric rewards.	3 / 3
Progressive Disclosure	The body is well-organized into clear sections rather than a wall of text, but it is a monolithic ~155-line file with no bundle files present, and it references "original-texts.md" ("详细原著依据见 original-texts.md") which does not exist in references/ — a clearly signaled but dangling reference.	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 bilingual, well-structured, and fully answers both what and when with explicit triggers, which is its main strength. It is somewhat held back by abstract action verbs and trigger terms that, while natural, are not as concrete or distinctive as they could be.

Suggestions

Replace abstract verbs with more concrete operations — e.g. name the specific deliverable ("output a task priority matrix and lock a single main target") instead of only "concentrate effort".

Add a couple more varied, concrete trigger phrasings a user would actually say (e.g. "too many things in flight", "spreading myself thin", "what should I do first") to broaden natural-term coverage.

Sharpen distinctiveness by contrasting with adjacent skills (e.g. note it is about choosing ONE main target, not general task listing or scheduling).

Dimension	Reasoning	Score
Specificity	The description names the domain and several actions ("concentrate effort, sequence work decisively, and finish a meaningful breakthrough"), but these are abstract strategic verbs rather than concrete operations, so it stops short of the multi-specific-action bar.	2 / 3
Completeness	It clearly answers both what ("concentrate effort, sequence work decisively, finish a meaningful breakthrough") and when (explicit "Trigger when limited resources are being split across too many tasks" plus listed common signals).	3 / 3
Trigger Term Quality	It enumerates natural signal phrases ("优先级过多、资源紧张、推进分散、需要决定先做什么"), but the domain is abstract and it lacks the crisp, varied noun-phrase coverage of a top-tier trigger set.	2 / 3
Distinctiveness Conflict Risk	The niche (concentrate on one main target under resource contention) is fairly specific, but task-prioritization is a crowded space and the triggers could overlap with sibling meta-skills, so it is not unmistakably distinct.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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: HughYau/qiushi-skill
Path: skills/concentrate-forces/SKILL.md
Commit: 6710791

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.