ex

Solid

Analyze a complex problem with a fixed thinking skeleton; analysis only, no code changes.

Code & Development 37 stars 10 forks Updated 3 days ago MIT

Install

View on GitHub

Quality Score: 83/100

Stars 20%
53
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# ex — structured discussion skill Analyze complex problems with a fixed thinking skeleton. **Output analysis only; do not modify code.** ## Entry: complexity check When the question arrives, **first judge complexity**: - **Simple problem** → answer directly, **do not apply the methodology** (KISS) - **Complex problem** → run the full 6-step skeleton below Treat as complex if any of these holds: - Multiple candidate solutions need trade-off - Multiple hypotheses need verification - Spans multiple modules / systems / layers - The user explicitly asks for deep discussion ## Methodology skeleton (complex problems only) Run in order, **in one pass, without stopping to ask the user**: ``` 1. Problem study Clarify the problem itself through What / Why / How 2. Diverge Enumerate candidate hypotheses, solutions, perspectives 3. Converge Pick the top 1-3 4. Diverge again Deep-dive into the chosen ones (details, risks, edge cases) 5. Iterate-verify Verify key hypotheses via code search / web search / bash experiments 6. Summarize Conclude; use a comparison matrix when multiple options sit side by side ``` ### What / Why / How facets (cross-cutting) - **What**: what is the problem / solution, what is the boundary - **Why**: why does this problem exist, why pick this solution - **How**: how to implement / land / verify it ## Execution rules ### Run once, never interrupt the user - **Never call AskUserQuestion** - When information is missing → explic...

Details

Author
Surething-io
Repository
Surething-io/cockpit
Created
7 months ago
Last Updated
3 days ago
Language
TypeScript
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

deep-analysis

Runs a long, structured multi-step reasoning chain over the sequential-thinking MCP server, with branching, revision, and explicit hypothesis verification. Reserved for consequential, genuinely open problems whose answer cannot be reached by reading the code — an architecture decision with several defensible options, an unexplained performance bottleneck, technology selection, design trade-offs, or a migration and risk strategy. Because it is slow and token-heavy it is not for questions with one correct answer, factual or syntax lookups, summarizing or explaining existing code, a defect with an obvious cause, or applying a fix already chosen. Prefer /investigate for root-cause work on a reproducible defect, and /diverge when the need is a wide option space rather than one reasoned conclusion.

7 Updated 1 months ago
pfangueiro
AI & Automation Listed

analyze

Enter structured analysis mode for codebase exploration and requirements understanding. Use when exploring a new codebase, investigating a module, or understanding how a feature works.

4 Updated 2 weeks ago
alergyonthestage
Web & Frontend Listed

structured-analysis

Analyze a topic's background and future using structured analytic techniques drawn from intelligence tradecraft — genealogy, actor mapping, red team, STEEP, key assumptions check, scenario 2x2, second-order effects, and ACH/pre-mortem/what-if. Load when the user asks to unpack how something came to be, why an actor is moving now, what structural forces drive a situation, what might happen next, what could go wrong, or which of several competing readings holds. Not for quick factual lookups, generic SWOT-style strategy templates, or opinion pieces.

1 Updated 2 weeks ago
bushrabeg