菜单
Design path to readiness using Stage-Gate, Technology Roadmapping, and milestone planning methods.
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
| name | maturation-pathway-design |
| description | Design path to readiness using Stage-Gate, Technology Roadmapping, and milestone planning methods. |
| dependencies | {"tactics":["multi-dimensional-readiness-scan","staged-gate-evaluation"],"sops":["dimension-assessment","feasibility-synthesis"]} |
Purpose: Given a candidate that is not yet ready, design a concrete pathway to bring it to implementation readiness. Uses Stage-Gate processes to define decision points, Technology Roadmapping to sequence development activities, and milestone planning to create actionable checkpoints.
When to use:
| Metric | Target |
|---|---|
| Stage gates defined | >= 3 |
| Milestones per stage | >= 2 |
| Resource estimates per stage | 1 per stage |
| Key | Type | Description |
|---|---|---|
| candidate | object | The candidate needing maturation |
| current_readiness | object | Starting maturity profile |
| target_readiness | object | Required maturity for implementation |
| stages[] | array | Defined maturation stages |
| gates[] | array | Decision gates between stages |
| milestones[] | array | Checkpoints within stages |
| roadmap | object | Complete maturation roadmap |
| Tactic | When |
|---|---|
| staged-gate-evaluation | To define and evaluate gates along the maturation path |
| multi-dimensional-readiness-scan | To assess readiness at each stage |
| SOP | Purpose |
|---|---|
| gate-criteria-definition | Define criteria for each gate |
| gate-judgment | Evaluate readiness at each gate |
| dimension-assessment | Assess dimension readiness at checkpoints |
| feasibility-synthesis | Synthesize pathway into overall feasibility view |
maturation_pathway:
candidate: <name>
current_readiness: <overall score>
target_readiness: <required score>
gap_dimensions: [{dimension, current, target, gap}]
stages:
- stage: 1
name: <stage name>
objective: <what this stage achieves>
milestones: [{name, criteria, target_date}]
resources: {time, cost, personnel}
gate:
criteria: [...]
pass_threshold: <condition>
total_timeline: <duration>
total_cost: <estimate>
critical_path: [<stage dependencies>]
risk_factors: [{risk, mitigation, stage_affected}]
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use |
|---|---|
| multi-dimensional-readiness-scan | Assess readiness across multiple dimensions, synthesize into radar visualization, and identify bottleneck dimensions. |
| staged-gate-evaluation | Define gate criteria for each stage, evaluate candidates at each gate, and render go/kill/recycle decisions with evidence. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| dimension-assessment | Score a single readiness dimension for a candidate with evidence and gap analysis. |
| feasibility-synthesis | Synthesize all assessments into a feasibility matrix, recommendation, and risk summary. |
Append research process and results to the current Phase's context file. Each append MUST contain >=500 lines of markdown covering both process and results. Use this skill at plan-designated checkpoint points — typically after each strategy completes or at key decision nodes within a research Phase.
Create a new context file for a research Phase. Called once at Phase start to initialize the file that subsequent context-checkpoint calls will append to. Use this skill whenever a new research Phase begins and a fresh context file is needed.
The optimizer brain for the ladder-foundry pretraining loop. Runs the two-level nested batch loop, delegates gating to gate_eval, attributes a failing batch to one weight (attribute-first), and recovers from disk after compaction. Control flow is fully scripted; only the backprop attribution is a judgment call.
Loss-2 judge (codex role). Over one topic's 6 shuffled research-design samples, pairwise-rank by quality using the D1–D5 standard. Emit the pairwise log; the harness computes the order and the ladder verdicts. Judge quality difference, never against academic standards.
Loss-1 judge (codex role). Given one sample's de-identified dialogue and its PolicyCard, decide axis-by-axis whether the user-simulator enacted the card's per-axis pressure. Judge enactment of the card, never whether the research is good.
Closing skill for the research-executor, loaded as the last step of formated-specs. Summarize the design just produced into one research-result JSON fenced block in your reply. Do not execute the research.