discovery-clarify-project
Skill1 starsChanged 53 days agoMITView on GitHub
Cross-domain / Research methodology and experiment design — Review the current Microsoft Discovery project's purpose, expected outcomes, and task list, then surface up to 5 targeted clarifying questions to the user via `/askQuestion` about ambiguities, gaps, or concerns before any work begins. Goal is to give the user a chance to reconsider scope, assumptions, or approach before kickoff. USE FOR: 'clarify this project', 'ask me clarifying questions before we start', 'review the project and challenge assumptions', 'pre-flight the project plan', 'what's ambiguous about this project'. DO NOT USE FOR: executing tasks, generating a plan from scratch, or reviewing completed work.
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- alphafold-structure-provenanceSkill
- biochemical-identifier-crosswalkSkill
- biocyc-network-contextSkill
- brenda-enzyme-dataSkill
- build-research-paperSkill
- chat-session-experimentalSkill
- discovery-add-agentsSkill
- discovery-dashboardSkill
- discovery-design-tasksSkill
- discovery-project-storySkill
- discovery-token-usageSkill
- engine-chat-experimentalSkill
- osti-literature-searchSkill
- sabio-rk-kineticsSkill
- scientific-database-accessSkill
- scientific-evidence-qcSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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 44
Identify ambiguities and concerns: Look specifically for:
- Distinctive: line 58
Prefer questions that could cause course correction over questions that only add detail.
- Distinctive: line 60
Do NOT ask questions whose answers are already explicit in the project purpose, outcomes, or task list.
- Distinctive: line 62
Do NOT ask stylistic or formatting questions.
- Distinctive: line 63
If the project is fully clear and you have zero concerns, say so plainly and ask nothing.
≈ “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
discovery-clarify-project
Pre-flight a Microsoft Discovery project by surfacing clarifying questions before any task is executed. This is a lightweight sanity check that gives the user one final opportunity to reconsider scope, assumptions, or approach.
When to run
The user asks you to review, clarify, pre-flight, or challenge the current project before getting started. Typical trigger phrases:
- "clarify this project"
- "ask me clarifying questions before we begin"
- "review the project and flag anything ambiguous"
- "any concerns before we start?"
What to do
- Read the project context. Load the current Discovery project's:
- Purpose / problem statement
- Expected outcomes / success criteria
- Task list (planned steps, deliverables, or subtasks)
- Identify ambiguities and concerns. Look specifically for:
- Undefined success criteria or vague outcomes
- Missing constraints (time, budget, data access, tools)
- Task steps that assume prerequisites not listed in the project
- Conflicts between stated purpose and the task list
- Scope that appears too large, too small, or off-target
- Unstated dependencies on other people, systems, or data
- Ambiguous ownership or handoff points
- Surface up to 5 questions via
/askQuestion. Rules:- Maximum 5 questions. Fewer is better if the project is clear.
- Each question must be specific and actionable — the user should be able to answer it in one or two sentences and have that answer change what you do next.
- Prefer questions that could cause course correction over questions that only add detail.
- Do NOT ask questions whose answers are already explicit in the project purpose, outcomes, or task list.
- Do NOT ask stylistic or formatting questions.
- If the project is fully clear and you have zero concerns, say so plainly and ask nothing.
- Do not start work. This skill only clarifies. Wait for the user's answers before proceeding to execution.
Output format
Brief lead-in (1–2 sentences) naming what you reviewed and how many
questions you have, then the /askQuestion calls. Nothing else.
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.