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 dot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 | dot |
| description | Procedure for tracking outcomes that take months or years to manifest. |
| output | {"format":"prose"} |
Input: $ARGUMENTS
Some outcomes can't be verified immediately: investment returns (years), career moves (months to years), relationship building (months), health interventions (weeks to months), skill development (months), behavior change sustainability (months).
This procedure provides structure for tracking early indicators while waiting for final outcomes, maintaining accountability over long timeframes, connecting actions to delayed results, and adjusting course before final outcome is known.
OUTCOME DEFINITION:
Final outcome: [what]
Expected timeline: [when]
Success criterion: [specific, measurable]
Failure criterion: [specific, measurable]
Expected trajectory: [shape of progress over time]
Leading indicators are observable signals that predict the final outcome before it arrives:
| Indicator | Observable When | Predicts Success If | Predicts Failure If |
|---|---|---|---|
| [indicator 1] | [timeframe] | [what pattern means good] | [what pattern means bad] |
| [indicator 2] | [timeframe] | ||
| [indicator 3] | [timeframe] |
Good leading indicator qualities:
Examples by domain:
| Domain | Final Outcome | Leading Indicators |
|---|---|---|
| Investment | ROI at year 5 | Revenue growth rate, customer retention, unit economics |
| Career | Promotion in 2 years | Scope of work, visibility, sponsor relationship |
| Health | Weight at 6 months | Weekly weigh-ins, adherence to plan, energy levels |
| Skill | Competence at 1 year | Practice frequency, performance on sub-skills, feedback quality |
| Business | Market share at year 3 | Customer acquisition cost trend, NPS, retention |
Create a minimal but consistent tracking system:
TRACKING CADENCE:
Daily: [what to log, if anything]
Weekly: [what to review]
Monthly: [what to assess]
Quarterly: [what to evaluate deeply]
At endpoint: [final assessment]
Tracking method: [journal, spreadsheet, app, etc.]
Visualization: [graph, dashboard, etc.]
Rules:
When should you change course BEFORE the final outcome?
| Trigger | Condition | Action |
|---|---|---|
| Leading indicator alarm | [indicator] is [threshold] for [duration] | [specific response] |
| Trajectory deviation | Progress < [X%] of expected at [time] | [reassess / adjust / abandon] |
| External change | [conditions changed] that affect the outcome | [re-evaluate assumptions] |
| New information | Learned something that changes the calculus | [integrate and decide] |
The hardest part of delayed tracking: remembering what you did and connecting it to results.
Action log format:
Date: [when]
Action: [what you did]
Rationale: [why you did it]
Expected effect: [what you thought would happen]
Expected timeline: [when you'd see the effect]
At each review, connect:
| Failure Mode | Symptom | Prevention |
|---|---|---|
| Tracking abandonment | Stop logging after enthusiasm fades | Minimum viable tracking, calendar reminders |
| Metric fixation | Optimizing indicator instead of outcome | Rotate which indicators you focus on |
| Attribution error | Crediting/blaming wrong actions | Track multiple indicators, not just one |
| Survivorship bias | Only tracking successes | Track failures and abandonments too |
| Premature judgment | Concluding too early | Define minimum evaluation period upfront |
DELAYED OUTCOME TRACKING:
Outcome: [what you're tracking]
Timeline: [start] → [expected end]
Current status: [on track / ahead / behind / uncertain]
Leading indicators:
| Indicator | Trend | Signal |
|-----------|-------|--------|
| [indicator] | [improving/stable/declining] | [success/warning/failure] |
Actions taken: [N actions logged]
Actions with visible effects: [N]
Effective actions: [which ones worked]
Ineffective actions: [which ones didn't]
Course corrections needed: [Y/N]
If yes: [what to change and why]
Next review: [date]