What it does
Systematically clarify intent, challenge assumptions, resolve contradictions, and align goals, constraints, risks, and success criteria.
- Connects Instruction files the AI reads
- Account or key Not confirmed yet (README not read yet)
- Category Automation and agents
For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/inference1-clarify-intent-and-establish-shared-understanding)Similar Skills
Same kind of work, ordered like the Skills list
| This one clarify-intent-and-establish-shared-understanding | skills | nacos | anatomy | leon | |
|---|---|---|---|---|---|
| Maker | Inference1 | vercel-labs | alibaba | wheresryan22 | leon-ai |
| Skills | 1 | 1 | 1 | 1 | 1 |
| GitHub stars | 205 | 39,908 | 33,528 | 27,996 | 17,693 |
| Last code change | Oct 31, 2026 | Nov 17, 2026 | Nov 18, 2026 | Oct 19, 2026 | Nov 13, 2026 |
| License | Apache-2.0 | MIT | Apache-2.0 | MIT | MIT |
1 skills (instruction sets) by Inference1 that an AI reads and follows · not an MCP server
How a Skill differs from MCP
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Works with
Claude CodeCodexCursorGemini CLIGitHub Copilot
From the maker’s README and the folders in the repo
Install
Is it safe?
- Who made it
GitHub account Inference1 (person), 6 years old
- Use and upkeep
★ 205 stars, few users so far · code last changed Oct 31, 2026
- Any scripts?
No, plain text files the AI reads and follows
- Uses the internet?
No scripts, so it does not go online by itself
- Changes machine-wide settings?
No hooks or writes to machine settings found
Checked automatically from the repo files at commit d423115 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
First: which AI do you use?
Pick your app and this page shows only how to install it there
Option 1Upload to claude.ai (web and app)
Uploading to claude.ai would fail: the description is over 200 characters (1658). Use "Let the AI install it" instead
Option 1Let Claude Code install it
Copy this sentence and paste it into a Claude Code chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Restart Claude Code, then type /clarify-intent-and-establish-shared-understanding or ask for a matching task and Claude picks it up
Checked against official docs Nov 12, 2026 · Source: code.claude.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
The maker’s recommended way
Install Node.js (if you don’t have it)
Already installed? Check first · Open Terminal, type this command and press Enter
node -v- A version number such as v26.13.1 = installed, skip this step
- "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
How to open Terminal
Mac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed
Open the Node.js download page ↗
When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v
Install once; it works for everything that needs Node.js
Checking the commands · copy buttons appear once they pass
Copied from the maker’s README; it downloads and runs the maker’s code
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.claude/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Restart Claude Code, then type /clarify-intent-and-establish-shared-understanding or ask for a matching task and Claude picks it up
ChatGPT desktop app
The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills
Option 1Let ChatGPT install it
Open Codex in the ChatGPT desktop app and paste this sentence into the chat
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Option 2Put the folder there yourself
Put the clarify-intent-and-establish-shared-understanding folder at ~/.agents/skills/clarify-intent-and-establish-shared-understanding
~ is your home folder ($HOME)
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
After installing
- ChatGPT desktop app: open Skills in the sidebar to see that the skill is there
- To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
- Codex picks up newly installed skills by itself; if one does not show up, restart Codex
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
ChatGPT on the web and mobile
Skills you install yourself do not work here; only skills that come with a plugin from the directory
To use this skill with ChatGPT, use the ChatGPT desktop app as above
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Option 1Let Codex install it
Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Restart Codex, then ask for a matching task; Codex lists the skill
Option 1Let Cursor install it
Copy this sentence and paste it into a Cursor chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
In Cursor’s Agent chat, type / and pick clarify-intent-and-establish-shared-understanding
Checked against official docs Nov 12, 2026 · Source: cursor.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.cursor/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
In Cursor’s Agent chat, type / and pick clarify-intent-and-establish-shared-understanding
Option 1Let the AI install it
For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com
For Terminal users
Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.
Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026
View the original SKILL.md
The text below comes from the maker’s repo, not from PopNx MCP
5,584 characters · Open the full file on GitHub
---
name: clarify-intent-and-establish-shared-understanding
description: Whether you're thinking or getting things done, be clear, specific, and methodical. Grounded in first principles, rigorously examine and refine a user's task, decision, plan, goal, strategy, proposal, or idea through structured, progressively deeper questioning, in order to bridge the gap between the User and the Agent. Use when the user explicitly requests grilling, challenge, pressure-testing, cross-examination, red-team review, pre-mortem analysis, or a decision audit. The goal is to uncover unclear objectives, hidden assumptions, contradictions, weak evidence, missing information, overlooked constraints, dependencies, risks, trade-offs, failure modes, and misalignment between intended outcomes and real-world results. Begin by establishing a shared understanding of the user's actual intent, plans, goals, rules, constraints, and success criteria. Ask focused, high-leverage questions rather than broad or repetitive ones. Adapt each question based on previous answers, probing deeper where uncertainty, unsupported assumptions, or strategic weaknesses remain. Regularly summarize the current understanding of the user's precise intent and position to confirm alignment, expose misunderstandings, and refine the problem or goal definition. Distinguish facts, assumptions, hypotheses, and unknowns. Challenge reasoning rigorously while remaining constructive, respectful, and solution-oriented. Continue until the reasoning is internally coherent, evidence-aware, constraint-conscious, risk-assessed, and translated into a clearer, more actionable goal, decision, or plan. Ultimately, achieving the super-alignment between the User and the Agent.
---
**Simplicity** should be pursued to the greatest extent possible without compromising essential details, accuracy, or conceptual integrity.
**Interrogate the user systematically until both sides share a precise, complete understanding of the intent, problem, goal, task, constraints, priorities, assumptions, and desired outcomes**.
Construct and navigate an implicit decision tree. Resolve foundational choices before dependent ones, identify hidden assumptions, detect contradictions, and revisit previous conclusions when new information changes the **decision landscape**.
**Proceed through the decision tree iteratively, one round at a time**. At each round, define the frontier as the set of decisions whose prerequisites have already been resolved; in other words, it consists of the questions that can be asked without making assumptions about information that has not yet been provided. Present all questions on the current frontier within a single round, number them sequentially, and provide a recommended answer for each question. Do not proceed to the next round until the user has responded to the questions presented in the current round.
Format a round like so:
```
❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
➡️ <your recommended answer>
---
❓ **Q2** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
➡️ <your recommended answer>
```
In each round, the user's answers reshape the decision tree: resolved decisions extend the frontier and unlock questions that depend on them. Recompute the frontier accordingly and then present the next round of questions. Any question whose answer depends on another unresolved question in the current round should be deferred to a subsequent round.
Do not combine independent questions. Each question should:
- target a specific unresolved decision or ambiguity;
- briefly explain why the answer affects the outcome;
- provide a clearly labeled recommended option when sufficient context exists;
- preserve user agency by making clear that the final choice belongs to the user.
You may use any and all available tools, network proxies, agents, and search resources.
Do not ask for information that can be reliably obtained from available context, current working directory, code repositories, files, tools, connected sources, or other authorized inputs. **Retrieve or verify such information directly when possible**. Reserve questions for human judgment, preferences, priorities, acceptable risks, subjective trade-offs, or unavailable facts.
**Continuously restate and refine the emerging understanding**. Identify ambiguities, contradictions, unresolved dependencies, missing success criteria, and differences between stated requests and likely underlying goals.
Continuously maintain a shared mental model by:
- summarize the current understanding when meaningful progress is made;
- separate confirmed facts, assumptions, interpretations, and open decisions;
- highlight ambiguity, conflicting requirements, missing constraints, and unclear evaluation criteria;
- check whether the inferred objective matches the user's actual intent.
**Do not execute, implement, modify, submit, publish, or finalize any consequential output until**:
1. the relevant decisions, dependencies, and constraints have been resolved;
2. the desired outcome and measurable success criteria are explicit;
3. major assumptions and trade-offs have been surfaced and accepted;
4. the user explicitly confirms that shared understanding has been reached.
**Maintain a balance between rigor and efficiency**. Be persistent enough to prevent avoidable misunderstandings, but avoid unnecessary interrogation. Prioritize clarity, alignment, and forward progress over exhaustive questioning.
Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
From GitHub
- GitHub stars
- 205
- Maker
- Inference1
- License
- Apache-2.0
- Last code change
- Oct 31, 2026
- SKILL.md files in the repo (including translated copies and templates)
- 1
- Topics
- agent-skill, deepseek-harness, dsh-plugin