菜单
Generate comprehensive lists by systematically covering all dimensions. Ensures nothing is missed through structured enumeration.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Route any input through a branching question tree to narrow down the optimal response strategy before writing. Two stages — PERCEIVE (classify input) then ACT (select response). Covers all prompt types.
Generate exhaustive guesses about user input using ALL search methods with coverage tracking. Guessing is SEARCH through possibility space. Tracks space created vs space covered to ensure comprehensive exploration.
Systematically evaluate and select from a set of guesses, options, or possibilities. Combines ARAW analysis with prioritization to determine which guesses are strong, weak, actionable, or eliminable.
Extract hidden assumptions from any content. Surfaces what must be true for claims to hold, enabling deeper analysis.
Sub-orchestrator for analytical requests. Routes to decomposition, systems analysis, comparison, risk assessment, or synthesis based on what kind of analysis is needed.
Assume Right - Deep recursive rightness search. For every claim, assume it's right — find what must follow, then assume THOSE implications are right too. Recurse until bedrock. Track every claim found.
| name | se - Space Enumeration |
| description | Generate comprehensive lists by systematically covering all dimensions. Ensures nothing is missed through structured enumeration. |
| output | {"format":"table"} |
Input: $ARGUMENTS
Before executing, identify which interpretation matches the user's input:
Interpretation 1 — Generate a comprehensive list: The user wants to systematically enumerate all options, types, or instances within a defined space — nothing should be missed. Interpretation 2 — Map a problem space: The user wants to understand the full landscape of a topic — not necessarily listing every item, but seeing the structure and boundaries of what exists. Interpretation 3 — Find what's missing: The user already has a partial list or understanding and suspects there are blind spots — they want to discover what they have not yet considered.
If ambiguous, ask: "I can help with generating a comprehensive list, mapping the full structure of a space, or finding what you're missing from a partial view — which fits?" If clear from context, proceed with the matching interpretation.
Generate a comprehensive list by systematically covering all dimensions of a problem space. This ensures nothing is missed.
Prerequisites:
/dd if unknown)Before enumeration, specify the desired granularity:
| Level | Description | When to Use |
|---|---|---|
| EXHAUSTIVE | Every combination | Small spaces (<100), formal specs |
| REPRESENTATIVE | Key examples per dimension | Medium spaces (100-1000) |
| TOP-N | Most important N items | Large spaces, quick overview |
| DIMENSION-ONLY | Just list dimensions and values | Very large spaces, framework |
Default: 2x. Parse depth from $ARGUMENTS if specified (e.g., "/se 4x [input]").
| Depth | Min Items Generated | Min Dimensions Covered | Min Edge Cases | Min Completeness Checks |
|---|---|---|---|---|
| 1x | 10 | 3 | 2 | 1 |
| 2x | 20 | 5 | 4 | 2 |
| 4x | 35 | 7 | 6 | 3 |
| 8x | 55 | 9 | 10 | 5 |
| 16x | 80 | 12 | 15 | 7 |
These are floors. Go deeper where insight is dense. Compress where it's not.
List the dimensions you'll enumerate across:
DIMENSIONS FOR: [topic]
1. [Dimension 1]: [value1, value2, value3, ...]
2. [Dimension 2]: [value1, value2, value3, ...]
3. [Dimension 3]: [value1, value2, value3, ...]
TOTAL SPACE: [N1] × [N2] × [N3] = [Total] combinations
GRANULARITY: [EXHAUSTIVE / REPRESENTATIVE / TOP-N / DIMENSION-ONLY]
NOVELTY CHECK: For each dimension, is this a standard textbook category or derived from the specific context? If you cannot point to a feature of the input that generated a dimension, you are reproducing a cached taxonomy.
Based on granularity and space size:
| Space Size | Strategy |
|---|---|
| < 50 | Full Cartesian product |
| 50-500 | Dimension-by-dimension with pruning |
| 500-5000 | Representative sampling per dimension |
| > 5000 | Hierarchical (top-level dimensions, then drill down) |
For EXHAUSTIVE on small spaces, enumerate all combinations:
FULL ENUMERATION: [topic]
| # | Dim1 | Dim2 | Dim3 | Description |
|---|------|------|------|-------------|
| 1 | v1 | v1 | v1 | [what this combination means] |
| 2 | v1 | v1 | v2 | [what this combination means] |
| 3 | v1 | v2 | v1 | [what this combination means] |
...
Pruning: Mark combinations that don't make sense as N/A:
| 4 | v1 | v2 | v2 | N/A - [reason this combination is invalid] |
For REPRESENTATIVE on medium spaces:
DIMENSION-BY-DIMENSION: [topic]
## Dimension 1: [name]
For each value, list key items:
### [Value 1]
- [Item 1.1]
- [Item 1.2]
- [Item 1.3]
### [Value 2]
- [Item 2.1]
- [Item 2.2]
[Continue for all dimensions]
For TOP-N on large spaces:
HIERARCHICAL ENUMERATION: [topic]
## Level 1: [Primary Dimension]
### [Category 1]
Top items:
1. [Most important]
2. [Second most]
3. [Third most]
### [Category 2]
Top items:
1. [Most important]
...
## Level 2: Drill-down on [specific area]
[More detailed enumeration of one branch]
After initial enumeration, check for items that span dimensions:
CROSS-DIMENSIONAL ITEMS:
- [Item X] spans [Dim1:value] AND [Dim2:value] - classify under: [primary]
- [Item Y] doesn't fit any dimension - add to "Other" category
Verify no dimension is under-represented:
COVERAGE CHECK:
| Dimension | Values | Items per Value | Gap? |
|-----------|--------|-----------------|------|
| [Dim 1] | 5 | 3, 4, 2, 5, 3 | No |
| [Dim 2] | 3 | 8, 2, 1 | Yes - [value 3] under-covered |
ACTION: Add items for [Dim 2, value 3]
Choose organization by:
COMPREHENSIVE LIST: [topic]
Organization: [chosen method]
[Organized list with clear structure]
---
METADATA:
- Total items: [N]
- Dimensions covered: [list]
- Granularity: [level]
- Gaps identified: [any]
- Items in "Other": [N]
Input: Enumerate all types of requirements for a software project
TOTAL: 5 × 4 × 4 = 80 combinations GRANULARITY: REPRESENTATIVE
Dimension-by-dimension with representative items
All dimensions covered. No major gaps.
[Organized list as shown above]
Before completing:
After enumeration:
/mv to verify MECE-ness/de if items have dependencies/to if items need sequencing