Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Think — 问题解决与分析 — measured AI agent skill | DecimalAI

ellmos-ai/think

SkillScore73Maintained

Problem solving and analysis: Structured thinking processes for complex problems. Divide & Conquer, Root Cause Analysis, SWOT, Pareto, and decision heuristics.

by ellmos-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Research pack

decimalai skills pull ellmos-ai-think

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/ellmos-ai-think/SKILL.md

Raw file: /s/ellmos-ai-think/SKILL.md ↗ · machine-readable summary at /s/ellmos-ai-think.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3d ago

Yes — +9% lift+9% tokens0% turns73% of whole cases pass with skill (16/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-07	✗→✓	▲ Improved	23%	0%
case-16	✗→✓	▲ Improved	4%	0%
case-04	✓→✓	＝ Same ✓	2%	0%
case-05	✓→✓	＝ Same ✓	18%	0%
case-08	✓→✓	＝ Same ✓	16%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

ellmos-ai / skills

skills/utilities/think/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v6

Skill contents

SKILL.md

> 中文 — think 官方中文版本。

Think — 问题解决与分析

> 针对复杂问题的结构化思维过程

问题解决途径

1. Divide & Conquer（分治法）

Problem -> Sub-problems -> Solve individually -> Combine

2. Root Cause Analysis（根本原因分析）

Symptom -> Why? -> Why? -> Why? -> Root cause -> Solution

3. Constraint Relaxation（放宽约束）

Unsolvable problem -> Relax constraints -> Solve -> Re-apply constraints

4. Analogy Search（类比搜索）

New problem -> Similar known problem -> Adapt solution

分析方法

| 方法 | 应用 | |------|------| | SWOT | 优势 / 劣势 / 机会 / 威胁 | | 利弊分析 (Pro/Con) | 决策制定 | | Pareto | 80/20 优先级排序 | | Fishbone | 根本原因分析（石川图） |

决策启发式方法

不确定性下

1. 最坏的情况是什么？
2. 是否可逆？
3. 不采取行动的代价是什么？

复杂性下

1. 最简单的第一步是什么？
2. 专家会怎么做？
3. 80% 的解决方案会是什么？

变更日志

1.0.0 (2026-03-15)

从 BACH v3.8.0 移植

从 BACH v3.8.0 移植 | 独立版本

Want to see if ellmos-ai/think would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.