Discover Research skills, compare source repositories and read the instructions for each workflow.
Design questions that elicit authentic insight and story material. Core skill for walk-and-talk guides and interviews. Draws from oral history, UX research, clean language, and motivational interviewing traditi...
Capture screenshots of aiandi.dev for visual verification. Puppeteer-based, outputs to /tmp. Foundation for the design-loop skill.
Prepare synthesis guidance for the-art. NOT an outline. Provides thematic guidance, narrative intent, and evidence library that enables synthesis instead of expansion.
Process walk recordings into usable research material. Transcription workflow, insight extraction, integration with pipeline. Use after WALK stage recording.
Multi-persona documentation review that catches quality failures AND signal mismatches. Produces prioritized edits, not assessment. Quality before signals.
Blog post review for authentic voice. Kill the slop. Keep the soul. Use before publishing blog posts or when a draft 'feels AI-generated'.
Question template for Journey stories ('How I learned X'). Arc: Challenge → Struggle → Discovery → Integration → Wisdom. Use with question-design skill.
Question template for Methodology stories ('Here's how to do X'). Arc: Problem → Experimentation → Discovery → Refinement → Teaching. Use with question-design skill.
Iterative visual design fine-tuning. Implement, capture, see with vision, assess, refine, repeat. The recursive loop where craft meets sight.
Expressing Robbie's authentic voice for AI and I blog. The voice teaches by demonstration, trusts through expectation, flows between poles without announcing shifts, and finds joy in structure clicking into pla...
Create talking guides for insight elicitation during physical walks. Use when you need human insight that benefits from embodied cognition, reflective thinking, or extraction of tacit knowledge. Triggers: 'walk...
Question template for Evolution stories ('X changed from A to B'). Arc: Origin State → Pressure → Transition → New State → Reflection. Use with question-design skill.
Synthesis of scried material with voice into unified teaching. The alchemical marriage of Sol (synthesis guidance) and Luna (fluid voice) to create the Philosopher's Stone (transmuted content).
Fact-check and verify technical accuracy of blog articles. Code examples, links, claims, dates. Use at TECHNICAL stage of blog pipeline.
Chat-based goal classification (habit/distance/speed/race) with constraint clarification. Use during onboarding or when user wants to update their running goals through conversation with weekly commitment disco...
Converts run telemetry into insights, recovery recommendations, and next-session nudges.
Converts run telemetry and user notes into structured reflections with confidence scores. Use after runs to capture qualitative feedback and generate next-step guidance with safety checks for pain or abnormal h...
Detects unsafe spikes in training load and emits SafetyFlags with conservative adjustments.
Recomputes upcoming workouts based on recent runs, feedback, and safety limits.
Classifies pre-run readiness (proceed/modify/skip) using recent load, recovery, and self-reported signals.
Detects unsafe training load spikes (>20-30% week-over-week) and emits safety flags. Use in nightly background jobs or when reviewing weekly training volume with conservative adjustment recommendations.
Entry point for Codex-discoverable skills used by the Run-Smart AI coach.
Generates route specifications with distance and elevation constraints. Use when user asks for route suggestions, wants to explore new running paths, or needs safer surface recommendations for upcoming workouts...
Recomputes upcoming workouts based on recent runs and user feedback. Use when recent performance deviates from plan, user provides negative feedback, or recovery signals indicate adjustment needed with determin...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.