context-aware-questions
Skill11 starsChanged 6 days agoMITView on GitHub
Use when asked 'what am I missing?', reviewing an issue or draft before submission, or checking documentation completeness - detects requirement, spec, and doc gaps and generates prioritized actionable questions
In this repository31 other files it gives its agents.
- architecture-diagrammingSkill
- at-risk-detectionSkill
- build-faq-from-issuesSkill
- daily-planning-ritualSkill
- dependency-mappingSkill
- estimating-change-footprintSkill
- estimating-work-itemsSkill
- idea-to-designSkill
- issue-decompositionSkill
- markdown-formattingSkill
- mermaid-diagramsSkill
- prepare-meeting-agendaSkill
- project-analysisSkill
- project-planningSkill
- repairing-project-setupSkill
- requirement-elicitationSkill
- research-topic-summarizeSkill
- setting-up-a-projectSkill
- sgai-goalSkill
- stakeholder-trackingSkill
- stakeholder-updatesSkill
- summarize-conversation-threadSkill
- supervising-conductor-workspacesSkill
- supervising-paradev-workspacesSkill
- timeline-planningSkill
- triage-new-issuesSkill
- working-on-an-epicSkill
- working-on-an-issueSkill
- writing-product-specsSkill
- writing-user-storiesSkill
- writing-verification-plansSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. About 0 are common, 14 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈14
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 32
When asked "what am I missing?" or "what questions should I be asking?":
- Distinctive: line 36
Check README and documentation
- Distinctive: line 42
When asked to review a specific issue:
- Distinctive: line 50
When reviewing a draft (issue, PR, note) before submission:
- Distinctive: line 53
Check against standard templates and best practices
- Distinctive: line 58
When asked about documentation completeness:
- Distinctive: line 60
Read README.md and files in docs/
- Distinctive: line 67
Missing acceptance criteria: No checkboxes, no "done when" statement
- Distinctive: line 74
Missing README sections: No install, usage, or examples sections
- Distinctive: line 77
Missing license information: No LICENSE file or license section
- Distinctive: line 82
Missing architecture documentation: No system overview for complex projects
- Very specific: line 84
No project overview available: Run the project-analysis skill first to map the project structure
- Distinctive: line 124
Always prioritize by impact
- Distinctive: line 135
Check against industry standards
- Distinctive: line 136
Consider the project type (CLI needs different docs than library)
≈ “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
Context-Aware Question Generator Skill
Analyze project context to surface information gaps and generate prioritized, actionable questions.
When to Use
Activate when:
- User asks "what am I missing?" or "what questions should I be asking?"
- Reviewing issues before starting work
- Analyzing documentation completeness
- Preparing a draft (issue, PR, document) for submission
- During project planning or kickoff
Fetching Issues
Where issues are needed, fetch them with the gh CLI (must be installed and authenticated):
gh issue list --state open --json number,title,body,labels,assignees
gh issue view <n> --commentsAnalysis Modes
1. Project-Wide Review
When asked "what am I missing?" or "what questions should I be asking?":
- Fetch all open issues (see Fetching Issues)
- Analyze project structure
- Check README and documentation
- Analyze all gathered data for information gaps
- Generate prioritized questions
2. Issue Review
When asked to review a specific issue:
- Fetch the issue and all comments (see Fetching Issues)
- Analyze for missing requirements, unclear specs, and gaps
- Generate targeted questions for that issue
3. Draft Review
When reviewing a draft (issue, PR, note) before submission:
- Analyze the provided text for completeness
- Check against standard templates and best practices
- Suggest specific improvements
4. Documentation Gap Analysis
When asked about documentation completeness:
- Read README.md and files in docs/
- Analyze what the project contains
- Identify missing documentation by comparing project content to docs
Gap Detection Heuristics
Issue Analysis
- Missing acceptance criteria: No checkboxes, no "done when" statement
- Vague descriptions: Less than 100 characters, contains "unclear", "might", "maybe"
- Missing labels or assignees: Issue has no labels or no assignee
- Stale issues: Open more than 30 days with no activity
- Bug reports without reproduction steps: No "steps to reproduce" section
Documentation Analysis
- Missing README sections: No install, usage, or examples sections
- No dedicated docs/ directory: For projects with more than 10 files
- Short README: Less than 500 characters
- Missing license information: No LICENSE file or license section
- No inline documentation: Missing JSDoc/docstrings in key files
Project-Wide Analysis
- Conflicting descriptions across issues, README, and docs
- Missing architecture documentation: No system overview for complex projects
- Undocumented key files: Entry points without explaining comments
- No project overview available: Run the
project-analysisskill first to map the project structure
Output Structure
Questions are categorized and prioritized:
Categories
- requirements: Missing acceptance criteria, unclear specs, vague descriptions
- technical: Implementation questions, architecture decisions
- documentation: Missing docs, unclear README sections
- process: Workflow gaps, missing labels/assignees
- consistency: Conflicting information across sources
- architecture: High-level design questions
Priorities
- high: Blocking or critical gaps that need immediate attention
- medium: Important gaps that should be addressed soon
- low: Nice-to-have clarifications
Example Output
## Information Gaps Found
### High Priority (3)
1. [requirements] Issue #42 lacks acceptance criteria
- Context: "Add login feature" has no definition of done
- Suggested Action: Add checkboxes with acceptance criteria
2. [documentation] No API documentation found
- Context: Project has 15 endpoints but no API reference
- Suggested Action: Create docs/api.md with endpoint documentation
### Medium Priority (5)
...Best Practices
When Generating Questions
- Always prioritize by impact
- Group related questions together
- Provide actionable suggested actions
- Link to specific sources (issue number, file path)
When Reviewing Drafts
- Be constructive, not critical
- Suggest specific improvements with example text when helpful
- Acknowledge what's already good
When Analyzing Documentation
- Check against industry standards
- Consider the project type (CLI needs different docs than library)
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.

