askme

Solid

Explore intent with Verbalized Sampling before planning. Use when the task is ambiguous, you need maximum clarifying questions, or you want collaborative or adversarial mode via `/askme`.

AI & Automation 33 stars 0 forks Updated yesterday Apache-2.0

Install

View on GitHub

Quality Score: 83/100

Stars 20%
51
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Ask Me Command Before proceeding to ask planning questions, you must *proactively and critically* execute both Verbalized Sampling (VS) and exploration: - For Verbalized Sampling, sample multiple intent hypotheses, assign each an explicit probability weight (0 to 1 scale), and identify the specific observation or scenario that would falsify each before selecting a direction. Expand hypothesis depth as ambiguity, risk, or architectural surface grows; keep it concise when scope is truly narrow. Explore meaningful edge cases until additional cases stop changing the decision; broaden sampling if no clear leader emerges. Surface decision points early with concrete options and trade-offs. Synthesize surviving hypotheses into one consolidated direction before responding. Output should stay compact and decision-oriented: intent summary, assumptions, and focused questions. Do not proceed on non-trivial changes without visible VS. **Required VS Output Format:** ``` 1. [Weight: 0.42] hypothesis here - Falsifier: [observation or scenario that would invalidate this] 2. [Weight: 0.28] hypothesis here - Falsifier: [observation or scenario that would invalidate this] ``` - For exploration, deliberately seek out unconventional, underexplored, and edge-case possibilities relating to the user's objective, drawing on both the provided context and plausible but non-obvious requirements. Include at least 3 edge cases (at least 5 if architectural), and stop expanding once additional ca...

Details

Author
OutlineDriven
Repository
OutlineDriven/odin-claude-plugin
Created
8 months ago
Last Updated
yesterday
Language
Python
License
Apache-2.0

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category