20-understand-goal-150
[20] UNDERSTAND. Achieve complete clarity on goals, expectations, and success criteria. Use when starting new tasks, when requirements seem unclear, when scope is ambiguous, or anytime you need full understanding of what success looks like. Triggers on "clarify goal", "understand requirements", "what exactly needed", "define success", or when facing unclear expectations.
Best use case
20-understand-goal-150 is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
[20] UNDERSTAND. Achieve complete clarity on goals, expectations, and success criteria. Use when starting new tasks, when requirements seem unclear, when scope is ambiguous, or anytime you need full understanding of what success looks like. Triggers on "clarify goal", "understand requirements", "what exactly needed", "define success", or when facing unclear expectations.
Teams using 20-understand-goal-150 should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/20-understand-goal-150/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How 20-understand-goal-150 Compares
| Feature / Agent | 20-understand-goal-150 | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
[20] UNDERSTAND. Achieve complete clarity on goals, expectations, and success criteria. Use when starting new tasks, when requirements seem unclear, when scope is ambiguous, or anytime you need full understanding of what success looks like. Triggers on "clarify goal", "understand requirements", "what exactly needed", "define success", or when facing unclear expectations.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Understand-Goal 150 Protocol **Core Principle:** Achieve complete clarity, not just confirm understanding. Know the WHAT, WHY, and HOW of success before acting. ## What This Skill Does When you invoke this skill, you're ensuring: - **Full understanding** of what needs to be done - **Clear success criteria** — how you'll know it's done right - **Known constraints** — what limits apply - **Hidden expectations** surfaced and addressed ## The Clarity Framework | Dimension | What to Clarify | |-----------|-----------------| | **Goal** | What needs to be achieved? Why does it matter? | | **Scope** | What's included? What's explicitly excluded? | | **Format** | What does the output look like? | | **Constraints** | What limits apply? (time, resources, quality) | | **Success** | How will we know it's done right? | | **Risks** | What could make this fail? | ## The 150% Clarity Rule - **100% Core:** Clear on the goal and expected result - **50% Enhancement:** Clear on constraints, hidden requirements, and edge cases ## When to Use This Skill **Universal trigger:** Any situation where clarity is needed. **Specific triggers:** - Starting new tasks or projects - Requirements seem vague or ambiguous - Multiple interpretations possible - Scope keeps shifting - Expectations unclear - Before major effort investment - When you realize mid-work you're not sure what's needed **Key insight:** This skill applies whenever clarity is lacking, not just at the start. ## Execution Protocol ### Step 1: UNDERSTAND THE CORE Identify the fundamental goal: - What is actually needed? - Why is this needed? (the real reason) - What problem does this solve? ### Step 2: DEFINE SUCCESS Establish clear success criteria: - What does "done" look like? - How will we measure success? - What's the minimum acceptable outcome? - What's the ideal outcome? ### Step 3: MAP CONSTRAINTS Identify all limitations: - Time constraints - Resource limits - Quality requirements - Format specifications - Dependencies ### Step 4: SURFACE HIDDEN EXPECTATIONS Probe for unstated requirements: - What's assumed but not said? - What would cause disappointment? - What must NOT happen? - Who else cares about this? ### Step 5: CONFIRM CLARITY Validate your understanding: - Restate in your own words - Present your understanding of success - Get explicit confirmation - Document the agreement ## Clarity Questions Ask to achieve clarity: **About the Goal:** - "What's the core objective here?" - "Why is this important?" - "What problem are we solving?" **About Success:** - "What does success look like?" - "How will we know it's done right?" - "What's acceptable vs ideal?" **About Constraints:** - "What limits apply?" - "Any hard deadlines?" - "What resources are available?" **About Hidden Requirements:** - "What should definitely NOT happen?" - "What would cause disappointment?" - "What am I missing?" ## Output Format When using Goal-Clarity 150: ``` 🎯 **Goal-Clarity 150 Achieved** **Goal Understood:** [What needs to be done and why] **Success Criteria:** - ✅ Done when: [measurable outcome] - 🎯 Ideal: [best case result] - ⚠️ Minimum: [acceptable baseline] **Constraints Identified:** - [Time/resource/quality limits] **Hidden Requirements Surfaced:** - [Unstated expectations now explicit] **Confirmed Understanding:** [Summary in your own words] Ready to proceed with clarity. ``` ## Operational Rules 1. **CLARITY BEFORE ACTION:** Don't act without understanding 2. **ASK, DON'T ASSUME:** Questions > assumptions 3. **SURFACE THE HIDDEN:** Find what's not being said 4. **DEFINE SUCCESS:** Know what "done right" looks like 5. **CONFIRM EXPLICITLY:** Get clear agreement 6. **REVISIT WHEN NEEDED:** Clarity can erode; refresh it ## Examples ### ❌ Low Clarity (Dangerous) ``` User: "Make the app faster" AI: [Starts optimizing database queries] Result: Optimized wrong thing; user meant UI responsiveness ``` ### ✅ High Clarity (Safe) ``` User: "Make the app faster" AI: "🎯 Goal-Clarity 150 To ensure I focus on the right thing: **Understanding:** You want the app to be faster. **Clarifying questions:** - What feels slow right now? (page loads? transitions? API calls?) - How fast should it feel? (instant? < 2 seconds?) - Are there specific pages/features to prioritize? - What's causing the most frustration? **Once I understand:** - Success = [specific metric improvement] - Focus = [specific areas] - Constraints = [time/effort limits] What aspects feel slowest to you?" ``` ### ✅ Mid-Work Clarity Check ``` AI: "I've been working on this for a while and want to check: 🎯 Goal-Clarity Check **My understanding:** Building user dashboard with stats **Success I'm aiming for:** Clean UI, real-time data, mobile-friendly **Questions that emerged:** - Should it auto-refresh or manual refresh? - Any specific charts/graphs needed? - Does it need export functionality? Want to confirm before I continue." ``` ## Failure Modes & Recovery | Failure | Detection | Recovery | |---------|-----------|----------| | **Acting on assumptions** | Working without confirmed clarity | Stop, ask clarifying questions | | **Partial clarity** | Some aspects still vague | Probe specific unclear areas | | **Scope drift** | Work expanding beyond original goal | Return to clarity, reconfirm scope | | **Hidden requirements emerge late** | Surprise expectations mid-work | Surface them, adjust or discuss | ## Relationship to Other Skills | Skill | Focus | |-------|-------| | **deep-think-150** | Quality of thinking | | **max-quality-150** | Quality of execution | | **goal-clarity-150** | Quality of understanding | Use together: **Clarity** on what to do → **Think** deeply about how → **Execute** with max quality. ## Session Log Entry (MANDATORY) After completing this skill, write to `.sessions/SESSION_[date]-[name].md`: ``` ### [HH:MM] Understand-Goal 150 Complete **Action:** Clarified goals and constraints **Result:** <clarity achieved/confirmed> **Artifacts:** <updated docs/plans> ``` --- **Remember:** Clarity is not a one-time event. Goals can shift, requirements can change, understanding can be incomplete. Use this skill whenever you need to be sure you're solving the right problem the right way.
Related Skills
23-understand-ask-ai-150
[23] UNDERSTAND. Consult external AI models when internal sources are exhausted. Build quality prompts using Prompt150 formula (Context + Query + Method + Style). Use when Loop150 exhausts internal sources, need real-world precedents, confidence <75%, or require reasoning from specialized AI models.
22-understand-deep-150
[22] UNDERSTAND. Deep research from all sources — internal (code, git, logs) AND external (web, docs, best practices). Use when choosing libraries, investigating solutions, understanding legal/technical questions, comparing approaches, or anytime you need comprehensive knowledge from both project context and world knowledge. Triggers on "research", "investigate", "find best approach", "what do others do", "compare options", or complex questions requiring multiple sources.
21-understand-research-150
[21] UNDERSTAND. Deep research workflow for this project using 150% scope (100% core + 50% boundary), evidence-based reasoning, and structured investigation notes. Use when the task requires investigation, root-cause analysis, or mapping unknown areas. Always maintain a research log file that captures findings, hypotheses, and next branches; use web.run when external verification is needed.
tech-blog
Generates comprehensive technical blog posts, offering detailed explanations of system internals, architecture, and implementation, either through source code analysis or document-driven research.
ontopo
An AI agent skill to search for Israeli restaurants, check table availability, view menus, and retrieve booking links via the Ontopo platform, acting as an unofficial interface to its data.
whisper-transcribe
Transcribes audio and video files to text using OpenAI's Whisper CLI, enhanced with contextual grounding from local markdown files for improved accuracy.
grail-miner
This skill assists in setting up, managing, and optimizing Grail miners on Bittensor Subnet 81, handling tasks like environment configuration, R2 storage, model checkpoint management, and performance tuning.
lets-go-rss
A lightweight, full-platform RSS subscription manager that aggregates content from YouTube, Vimeo, Behance, Twitter/X, and Chinese platforms like Bilibili, Weibo, and Douyin, featuring deduplication and AI smart classification.
ux
This AI agent skill provides comprehensive guidance for creating professional and insightful User Experience (UX) designs, covering user research, information architecture, interaction design, visual guidance, and usability evaluation. It aims to produce actionable, user-centered solutions that avoid generic AI aesthetics.
modal-deployment
Run Python code in the cloud with serverless containers, GPUs, and autoscaling using Modal. This skill enables agents to generate code for deploying ML models, running batch jobs, serving APIs, and scaling compute-intensive workloads.
vly-money
Generate crypto payment links for supported tokens and networks, manage access to X402 payment-protected content, and provide direct access to the vly.money wallet interface.
thor-skills
An entry point and router for AI agents to manage various THOR-related cybersecurity tasks, including running scans, analyzing logs, troubleshooting, and maintenance.