基于 SOC 职业分类
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。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/benjam3n/reasoningtool --skill la-limitation-analysis命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
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.
| name | la - Limitation Analysis |
| description | Systematically identify limitations across multiple dimensions, |
| output | {"format":"prose"} |
Input: $ARGUMENTS
Before executing, identify which interpretation matches the user's input:
Interpretation 1 — System/product limitations: The user wants to identify weaknesses, constraints, and bottlenecks in a system, product, or tool they are building or using. Interpretation 2 — Method/approach limitations: The user wants to assess the boundaries and blind spots of a particular method, framework, or analytical approach. Interpretation 3 — Personal/team limitations: The user wants to honestly evaluate capacity constraints, skill gaps, or resource limitations affecting their ability to execute.
If ambiguous, ask: "I can help with system/product limitations, method/approach limitations, or personal/team limitations — which fits?" If clear from context, proceed with the matching interpretation.
Systematically identify limitations across multiple dimensions, assess their impact, and prioritize which to address.
Key insight: Most systems have many limitations, but only a few matter enough to fix. This procedure separates identification from prioritization to avoid premature filtering.
Default: 2x. Parse depth from $ARGUMENTS if specified (e.g., "/la 4x [input]").
| Depth | Min Limitations Found | Min Categories Checked | Min Severity Assessments | Min Mitigation Plans |
|---|---|---|---|---|
| 1x | 5 | 2 | 3 | 1 |
| 2x | 8 | 3 | 5 | 2 |
| 4x | 12 | 5 | 8 | 3 |
| 8x | 18 | 7 | 12 | 5 |
| 16x | 25 | 10 | 18 | 7 |
These are floors. Go deeper where insight is dense. Compress where it's not.
Clearly state what system/method/process you're analyzing. Include: purpose, current state, context of use.
List ALL limitations you can think of without filtering. Use the analysis_questions.enumerate prompts. Don't worry about categorization or priority yet. Aim for completeness over precision.
For each limitation, assign a category from limitation_categories. Mark whether it's INHERENT (can't be fixed) or FIXABLE. Note if it's a TRADEOFF (fixing it would break something else).
Rate impact: CRITICAL / HIGH / MEDIUM / LOW / NEGLIGIBLE
CRITICAL: Blocks core use case, causes harm HIGH: Significantly degrades value MEDIUM: Noticeable but workable LOW: Minor inconvenience NEGLIGIBLE: Theoretical only
Rate effort: TRIVIAL / LOW / MEDIUM / HIGH / MASSIVE
TRIVIAL: < 1 hour, no dependencies LOW: < 1 day, minimal dependencies MEDIUM: Days to weeks, some coordination HIGH: Weeks to months, significant resources MASSIVE: Months+, major restructuring
Create priority matrix:
DO FIRST: TRIVIAL/LOW effort + HIGH/CRITICAL impact DO SECOND: MEDIUM/HIGH effort + HIGH/CRITICAL impact MAYBE: TRIVIAL/LOW effort + LOW/MEDIUM impact AVOID: MEDIUM/HIGH effort + LOW/NEGLIGIBLE impact ACCEPT: INHERENT limitations (can't fix, work around)
From DO FIRST, identify the single most impactful fix. Ask: "If we could only fix ONE thing, what would it be?"
For limitations we won't fix, document: