菜单
Use when auditing or improving the proposal engine or any bid, tender, EOI, methodology, technical/financial proposal, or consulting product it produces.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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/peterbamuhigire/proposal-skills --skill kaizen-improvement-system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。
基于 SOC 职业分类
正在显示 SKILL.md
| name | kaizen-improvement-system |
| description | Use when auditing or improving the proposal engine or any bid, tender, EOI, methodology, technical/financial proposal, or consulting product it produces. |
| metadata | {"portable":true,"compatible_with":["claude-code","codex"]} |
Acknowledgement: Shared by Peter Bamuhigire, techguypeter.com, +256 784 464178.
| Artefact | Source/provider | Required? | Purpose | If absent |
|---|---|---|---|---|
| ToR/RFP, evaluation criteria, audience, proposal artefact, evidence register, compliance matrix, assumptions, and current score | Client brief and proposal project | yes | Set audit scope and evaluator bar | Stop or mark unassessed |
min(raw score, 65) and record blockers.| Artefact | Consumer | Acceptance condition |
|---|---|---|
| Capped audit, evaluator/evidence gap register, 95/100 plan, experiment result, and standardisation record | Proposal lead, reviewer, and release owner | Every finding has evidence, action, owner, acceptance proof, and re-audit date |
| Evidence | Consumer | Acceptance condition |
|---|---|---|
| Compliance matrix, evaluator score, red-team findings, source register, render review, and revision diff | Reviewer and release owner | Another reviewer can reproduce the decision and confirm the correction |
Read and search are required. Proposal audits are read-only by default; edits, submissions, or external communication require explicit authority and permission. Route current facts to Digital Research.
If the ToR, evaluation grid, evidence, source, render, or reviewer is unavailable, return a qualified result, mark the gap not assessed, and withhold submission readiness.
| Condition | Action | Failure or risk avoided |
|---|---|---|
| A value claim lacks evaluator-relevant proof | Narrow the claim or add evidence before release | Unsupported promise |
| A technical or financial envelope is required separately | Preserve the separation and re-check the submission package | Disqualification |
| A red-team finding remains unresolved | Block release or obtain a documented decision | Hidden compliance risk |
A persuasive narrative never substitutes for compliance or proof. Keep technical and financial envelopes separate when required. Expert advice must stay within verified competence and compliance boundaries.
Treat the first review as an initial analysis: show the raw findings but publish only
min(raw_score, 65), with missing evidence and mandatory blockers visible. Begin the
95/100 improvement cycle only after that baseline is frozen. Every action needs a
root cause, exact artefact or validator, owner, experiment, evaluator-facing measure,
guardrail, stop/rollback rule, acceptance proof, and re-audit date.
Run it at engine level (routes, templates, examples, validators, and handoffs) and
at product level (bid, EOI, methodology, technical/financial proposal, or report).
The product requires its own evaluator and evidence result.
If a draft scores well on narrative but fails two mandatory ToR requirements, keep the score capped, block release, repair the compliance matrix and evidence, then repeat the evaluator simulation.
digital-research-engine through the global engine-routing table and read its docs/continuous-improvement/portfolio-kaizen-standard-2026-08.md file; if it is unavailable, apply Degraded Mode and mark the portfolio comparison not assessed.skills/meta/ai-slop-audit/skills/strategy-positioning/critical-analysis-business-logic/