clarify-intent
Skill1 starsChanged 8 days agoMITView on GitHub
Use when the task has unclear requirements, unknown domain terms or no acceptance criteria. Clarifies the intent and the domain language before you write code.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- ZadAnthony/meta-workflowtheir own version, first seen Oct 11, 2026
- Hugo-DDT/clarify-intenttheir own version, first seen Sep 18, 2026
- irfanannaafi19/Clarify-Intenttheir own version, first seen Aug 28, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- Hugo-DDT/clarify-intent★ 26same name
- irfanannaafi19/Clarify-Intent★ 1same name
- ZadAnthony/meta-workflow★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- apply-architectureSkill
- bootstrapSkill
- code-reviewSkill
- map-workSkill
- plan-workSkill
- releaseSkill
- tdd-loopSkill
- triageSkill
- write-adrSkill
- write-prSkill
- writing-checkSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use before you implement a non-trivial change.
- Distinctive: line 12
If the feature has a plan, read its open questions and requirements.
- Distinctive: line 18
Ask the questions. Do not assume answers.
- Distinctive: line 20
Only after the intent is clear, proceed to design or implementation.
- Distinctive: line 35
If you cannot start subagents, do the steps one at a time in the order of this skill.
- Distinctive: line 39
Do not start coding while important questions remain open.
- Distinctive: line 40
Prefer fewer, higher-value questions.
- Distinctive: line 41
Update or create a glossary entry if a new domain term appears.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Clarify intent
Use before you implement a non-trivial change.
Force clarification of requirements and domain language.
If the feature has a plan, read its open questions and requirements. Record each decision that you clarify in the plan. Do not invent answers. See feature plans.
Steps
- Restate the request in your own words.
- List open questions about behavior, edge cases, and constraints.
- Ask the questions. Do not assume answers.
- Capture domain terms. Prefer the language of the problem. See architecture/domain-languages.md.
- Only after the intent is clear, proceed to design or implementation.
Subagents
If you can start subagents, use them to answer the open questions that the repository can answer. Do steps 1 and 2 yourself. Then read the code and the docs at the same time, the code in one subagent and the docs in another subagent. Give each subagent a brief that is complete without your context:
- The request, as you restated it in step 1.
- The open questions from step 2.
- What to read: the code, or the docs, for example the README, the ADRs and the glossary.
- What to report: for each question, the answer with its file path and line, or "not found". The domain terms that it finds.
- A word limit, for example 400 words.
- This line: "Report to me only. Do not change files, ask the owner, post, approve or merge."
Then collect the reports. Read each answer at its file path and line yourself. If the code and the docs disagree, keep the question open. Do steps 3 to 5 yourself. Ask only the questions that are still open.
If you cannot start subagents, do the steps one at a time in the order of this skill. Before step 3, read the code and then the docs to answer the questions that they can answer.
Rules
- Do not start coding while important questions remain open.
- Prefer fewer, higher-value questions.
- Update or create a glossary entry if a new domain term appears.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.