跳到正文
cccskills
免费在 GitHub 公开

outcome-roadmap

Transform an output-focused roadmap (feature list) into an outcome-focused one. Rewrites initiatives as outcome statements reflecting user and business impact. Use when a roadmap lists features instead of results, when making a roadmap more strategic, or when communicating what success looks like vs what will be built.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md5.1 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Outcome Roadmap — from features to results

Converts a feature-focused roadmap into an outcome-focused one.

Core principle: Teams build features, but customers and businesses care about outcomes. An outcome roadmap communicates WHAT CHANGES, not what gets built.


The transformation formula

For every initiative on the roadmap, apply:

Enable [customer segment] to [desired customer outcome] so that [business impact]

Examples:

Output (old)Outcome (new)
Q2: Build advanced search filtersQ2: Enable customers to find products 50% faster through intuitive discovery
Q2: AI recommendationsQ2: Increase average order value 20% through personalised recommendations
Q3: Dashboard redesignQ3: Help operators monitor all systems with 80% less time spent on dashboards
Q3: SSO integrationQ3: Remove auth friction for enterprise admins so we can close 3+ enterprise deals
Q4: Mobile appQ4: Enable users to complete core workflows on mobile so 7-day retention increases from 20% to 35%

How to apply

Step 1 — Read the existing roadmap

If the user provides a roadmap file, read it. If they describe it verbally, extract the initiative list.

For each initiative, ask internally:

  • What feature / project is planned?
  • Why are we building it? What changes for customers or the business?
  • What metric will improve, and by how much?
  • Is there a better, different way to achieve the same outcome?

Step 2 — Rewrite each initiative as an outcome

For each item in the roadmap:

  1. Identify the output: What feature or project is planned?
  2. Uncover the outcome: Why are we building it? Keep asking "So what?" until you reach real customer or business value.
  3. Rewrite: Use the formula above. Include a metric if possible.

"So what?" chain example:

  • "We're adding search filters" → So what?
  • "Users can narrow results" → So what?
  • "Users find what they're looking for faster" → So what?
  • "Users convert at higher rates because they find products before abandoning" ✅ That's the outcome.

Step 3 — Group by strategic theme (optional)

If the roadmap has 5+ items, group related outcomes into themes:

  • Retention (outcomes that reduce churn)
  • Acquisition (outcomes that improve conversion)
  • Monetisation (outcomes that increase revenue per user)
  • Ops efficiency (outcomes that reduce internal cost/time)

Step 4 — Output format

## Outcome Roadmap — <Product> <Quarter/Year>

### Strategic context
<1–2 sentences on what the team is optimising for this period>

### Q<N> Outcomes

| Initiative | Outcome Statement | Primary Metric | Target |
|------------|------------------|----------------|--------|
| <original feature name> | Enable [segment] to [outcome] so that [business impact] | <metric> | <target> |

### What we're NOT doing this quarter (and why)
- <deprioritised initiative>: <reason — not enough signal / too early / wrong priority>

### Key assumptions
- <assumption this roadmap depends on — if it's wrong, the outcomes change>

Step 5 — Validate

Before presenting, check:

  • Every outcome has a measurable component (%, number, ratio, frequency)
  • "So what?" has been applied to every item — no pure feature descriptions remain
  • At least one "Not doing" item is stated — otherwise scope is unbounded
  • Outcomes align with stated OKRs or strategic goals in PROJECT.md

Anti-patterns

❌ "We will build X" — that's an output, not an outcome.

❌ "Improve UX" — unmeasurable. Rewrite as: "Reduce time to complete checkout from 4min to 90sec".

❌ Outcome without a metric — if you can't measure it, you can't know if you achieved it.

❌ Outcomes that require building a specific solution — "Enable users to access features via mobile app" locks the solution. Better: "Enable users to complete core workflows on any device".


Integration with pm agent

When the pm agent receives a feature list without a PRD:

  1. Check if the list looks like outputs (feature names) or outcomes (result statements)
  2. If outputs → apply this skill to transform before decomposing into tasks
  3. Pass the outcome statements into the PLAN doc as the "Why" for each task group

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

great_cto's own committed aesthetic — the instrument panel. Dark five-step surface ladder, exactly one accent, two faces divided by MEANING (Geist speaks, Geist Mono is machine-truth), tabular numerals, and a dash that is not a nought. Twelve checkable rules measured from packages/board and greatcto.systems, not designed for this file. Use when building or extending any great_cto surface — the board, the site, a report, a share page.

中文简介正在准备中。当前显示原文说明。

avelikiy/great_cto1052026年10月23日 更新

Catalogue of known SDLC anti-patterns that great_cto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).

中文简介正在准备中。当前显示原文说明。

avelikiy/great_cto1052026年10月23日 更新

anydesign

免费

Analyze images, websites, and Figma files to extract their design and generate a `design.md` with token system, component inventory, and reconstruction notes. Use this skill whenever the user wants to understand, document, replicate, or audit the design of something visual: a screenshot, a URL, a Figma link, a Pinterest reference, a mockup, a competitor's site, a component, a dashboard, a landing page. Also when they ask 'extract the design system from X', 'document the style of Y', 'analyze this visually', 'convert this image into tokens', 'help me replicate this design', 'what palette does this site use', 'how is this built'. Also for single elements: 'copy this navbar', 'recreate this illustration', 'give me a prompt to regenerate this graphic' — element mode outputs a focused element.md, with token-grounded image-model prompts when the element is visual art. If the user brings any visual source and wants to understand it at a design level — this skill should activate.

中文简介正在准备中。当前显示原文说明。

avelikiy/great_cto1052026年10月23日 更新

Shared review framework that every domain reviewer (pci, oracle, gov, edtech, healthcare, mlops, etc.) MUST follow. Defines the output artifact (TM-{slug}.md), mandatory sections, severity scale, verdict format, the workflow scaffold (when-invoked, Step-0 read-inputs, HANDOFF), and the "domain heuristic vs generic check" boundary. Eliminates duplication across the ~30 reviewer prompts.

中文简介正在准备中。当前显示原文说明。

avelikiy/great_cto1052026年10月23日 更新

Structured idea generation + multi-LLM debate for the product-owner stage. Diverge (generate genuinely different bets), debate (a 4-persona panel on 4 models argues over 2 rounds), converge (synthesize a recommendation). Used by product-owner before architect; available to architect for design-space exploration.

中文简介正在准备中。当前显示原文说明。

avelikiy/great_cto1052026年10月23日 更新

Run the great_cto controlled Codex lifecycle with controller-owned writes, verifier evidence, human gates and optional artifact release.

中文简介正在准备中。当前显示原文说明。

avelikiy/great_cto1052026年10月23日 更新

查看 avelikiy 的全部技能

报告此技能的问题