channel-research-deployment
Skill15 starsChanged 49 days agoMITView on GitHub
Deploy interviews, surveys, and diary studies via messaging channels (Telegram, Slack, WhatsApp, Google Chat) with adaptive questioning and real-time analytics.
In this repository47 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- affinity-mappingSkill
- empathy-mappingSkill
- hmw-statementsSkill
- journey-mappingSkill
- jtbd-analysisSkill
- kappa-thematic-analysisSkill
- persona-creationSkill
- prioritization-matrixSkill
- research-synthesisSkill
- taxonomy-generatorSkill
- thematic-analysisSkill
- user-flow-mappingSkill
- design-system-auditSkill
- handoff-documentationSkill
- longitudinal-trackingSkill
- nps-analysisSkill
- regression-impactSkill
- repository-curationSkill
- research-retroSkill
- stakeholder-presentationSkill
- sus-umux-scoringSkill
- task-analysis-quantSkill
- ab-test-analysisSkill
- card-sortingSkill
- cognitive-walkthroughSkill
- concept-testingSkill
- design-critiqueSkill
- heuristic-evaluationSkill
- prototype-feedbackSkill
- tree-testingSkill
- usability-testingSkill
- workshop-facilitationSkill
- accessibility-auditSkill
- analytics-reviewSkill
- competitive-analysisSkill
- contextual-inquirySkill
- desk-researchSkill
- diary-studiesSkill
- field-studiesSkill
- interview-question-generatorSkill
- stakeholder-interviewsSkill
- survey-ai-detectionSkill
- survey-designSkill
- survey-generatorSkill
- user-interviewsSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 59
Use the intro message to set expectations and build trust
≈ “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
Channel Research Deployment
Capabilities
- Deploy research studies across Telegram, Slack, WhatsApp, and Google Chat
- Adaptive questioning with LLM-powered follow-up probes
- Real-time analytics dashboard (response rate, completion rate, per-question stats)
- Automatic nugget extraction from participant responses into the Atomic Research chain
- Conversation state machine: intro, questions, probing, wrap-up
- Configurable rate limiting between questions
- LLM-judged saturation detection to avoid over-probing
- Cross-deployment overview with progress tracking
Workflow
- Plan -- Define research goals, generate question set with adaptive rules
- Configure -- Set up channel instances and link to a project
- Deploy -- Create and activate a deployment across selected channels
- Collect -- Participants respond via messaging; adaptive probing deepens insights
- Monitor -- Real-time analytics show progress, response rates, and per-question stats
- Analyze -- Complete the deployment; synthesize findings into nuggets, insights, recommendations
Input
- Research goals and questions (text or generated via plan)
- Channel instance IDs (configured Telegram/Slack/WhatsApp/Google Chat connections)
- Deployment configuration (adaptive rules, rate limits, intro/outro messages)
- Project context (auto-loaded from context layers)
Output
- Deployment plan with question set and adaptive rules (JSON)
- Real-time analytics (response rate, completion rate, per-question breakdown)
- Nuggets with source attribution (participant, channel, deployment)
- Insights and recommendations synthesized from responses
- Full conversation transcripts per participant
Deployment Types
- Interview -- Semi-structured conversational interview via messaging
- Survey -- Structured question set with optional branching
- Diary Study -- Longitudinal prompts sent on a schedule over days/weeks
Best Practices
- 5-15 questions per interview deployment; 3-5 for diary studies
- Enable adaptive probing for interviews to capture deeper insights
- Set rate limits (30-60s between questions) to avoid overwhelming participants
- Use the intro message to set expectations and build trust
- Monitor per-question skip rates to identify confusing questions
- Complete deployments promptly to avoid participant fatigue
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.