delivery-workshop
Instructional design patterns for hands-on developer workshops: intensive practice, collaborative problem-solving, peer learning, facilitated labs, and…
Skill by caraya
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/caraya-delivery-workshop
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/delivery-workshop
What's inside
- Skill name
delivery-workshop- Description
- Instructional design patterns for hands-on developer workshops: intensive practice, collaborative problem-solving, peer learning, facilitated labs, and coaching. Trigger phrases: workshop, hands-on, lab, practice-driven, collaborative learning, coached practice, small groups.
- License
- MIT
- Instructions
- 267 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Delivery — Workshop This skill adapts instructional design principles for intensive, hands-on developer workshops. It covers facilitated lab environments, peer learning dynamics, coaching strategies, collaborative problem-solving, and creating productive constraints that drive learning through doing. ## Features - **Scaffolded Practice**: Guided labs progressing from worked examples to independent challenges - **Collaborative Problem-Solving**: Pair and group work with intentional peer roles - **Coaching & Circulation**: Facilitator moves through room, asks questions, unblocks without solving - **Real-Time Feedback**: Immediate debugging support, code review on-the-fly - **Lab Stations or Breakout Teams**: Differentiated difficulty or specialization - **Reflection & Debrief**: Group processing after practice, surfacing learning ## When To Use - Designing 2-4 hour intensive practice sessions - Building peer programming or pairing-based learning - Creating capstone projects with facilitation - Designing hackathons, code retreats, or sprint-style learning - Facilitating open lab hours with coaching ## Guidelines ### Lab Design - [ ] **Clear problem statement**: Learners understand what they're trying to achieve - [ ] **Starter template or skeleton code**: Reduces setup friction, focuses on core learning - [ ] **Graduated complexity**: Easy win (20-30%), medium challenge (40-60%), extension (80%+) - [ ] **Acceptance criteria**: "You've succeeded when..." - [ ] **Hints available, not solutions**: Hint cards, scaffolded docs, not full code - [ ] **Estimated time**: "This section should take ~20 min" (learners self-pace within bounds) - [ ] **Checkpoints**: "Stop here; we'll debrief together" at natural breaks - [ ] **Success is visible**: Running tests, working feature, or artifact to demo ### Pair Programming Structure **Optimal pairing**: - Mix skill levels intentionally (novice + intermediate > homogeneous) - Define roles: **driver** (types) and **navigator** (directs, reviews) - Rotate every 10-15 minutes (timer helps) - Both roles critical to learning **Role clarity**: - **Driver**: Writes code, asks for direction, types suggestions from navigator - **Navigator**: Reads code, spots issues, looks ahead, asks clarifying questions - Avoid: Driver ignoring navigator; navigator dictating verbatim **Facilitation**: - [ ] Introduce roles; explain why pairing accelerates learning - [ ] Watch for dominance: "Navigator, what should happen next?" - [ ] Support quieter partners: "Driver, can you explain your approach to your navigator?" - [ ] Normalize struggle: "Disagreement is good—it surfaces assumptions" - [ ] Debrief: "What did you learn from your partner's approach?" ### Coaching & Circulation **Ask, don't tell**: - ❌ "You need to add a null check here" - ✅ "What could go wrong if the input is null?" **Diagnostic questions**: - "What's the error message telling you?" - "What did you expect to happen? What happened instead?" - "Walk me through your approach step by step" - "What have you tried so far?" - "Is there a simpler test case you could try first?" **Unblocking strategies** (in order): 1. Clarifying question (helps them find the path) 2. Hint: "Have you considered...?" or "What if you tried...?" 3. Pointed resource: "Check the section on X in the docs" 4. Demonstration (show the concept, not the full solution) 5. Code snippet + explanation (last resort; ensure they understand before moving on) **Circulation pattern**: - [ ] Systematically visit every pair/group - [ ] Start with pairs showing visible struggle - [ ] Check in with confident pairs to prevent complacency - [ ] Notice and interrupt unproductive patterns early (thrashing, passivity) - [ ] Spend 2-5 min per pair, then move on ### Peer Learning Dynamics **Structured peer feedback** (after practice): - [ ] Pair review: "Compare your solutions; what's different?" - [ ] Rotation review: Solution posted; others annotate with feedback sticky notes - [ ] Fishbowl: One pair codes while others watch, then discuss approach **Psychological safety in peer work**: - [ ] Normalize mistakes: "Great—you found a common edge case" - [ ] Celebrate different approaches: "You both solved it; show both methods" - [ ] Frame feedback as curious: "I'd expect this to fail; did it?" - [ ] Facilitator models: "Here's code I wrote; it has a bug—can you spot it?" **Preventing dominance**: - [ ] Enforce driver/navigator role rotation (timer) - [ ] Interrupt code hogging: "Navigator, take the driver role" - [ ] Group size: pairs are ideal; groups of 3+ require active facilitation - [ ] Assign roles explicitly: "A is driver; B is navigator; you'll swap at X" ### Lab Checkpoints & Debrief **Checkpoint design**: - After ~15-20 min of independent work, pause for group debrief - Show 2-3 representative solutions (working, partially working, alternative approach) - Discuss tradeoffs, common errors, and "why this matters" - Reset: "Clear this and try the next section" **Debrief structure** (5-10 min): 1. **Show & Tell** (2-3 min): One or two pairs demo their solution 2. **Compare** (2-3 min): "How is your approach different? Both valid?" 3. **Reflect** (2-3 min): "What was hard? What surprised you?" 4. **Connect** (1-2 min): "How does this relate to production code you'll write?" **Group problem-solving debrief**: - Start with a failing test or bug introduced by the facilitator - Pairs/groups debug collaboratively; share findings - Reveal the solution incrementally (not all at once)
From caraya/agent-skills, MIT.
More from caraya/agent-skills
- 0.592score
design-system
caraya
Organise and maintain a consistent design system through contracts, discovery, reuse and verification.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
dev
caraya
Development workflows for the playwright-cli repository.
SkillAFreshness: A★ 1Claude Code +9 - 0.497score
delivery-self-paced
caraya
Instructional design patterns for self-paced developer education: motivation maintenance, progress tracking, chunking for independent study, asynchronous…
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
delivery-classroom
caraya
Instructional design patterns for synchronous classroom delivery of developer education: lecture + live coding, pacing, group dynamics, real-time feedback…
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
debugging-methodology
caraya
General debugging skill for investigative workflow, error interpretation, and common debugging patterns across languages.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
debugging-pedagogy
caraya
Explicit debugging instruction for developers: five-stage framework, hypothesis testing, tools, and common error patterns.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
accessibility-core
caraya
Accessibility skill for WCAG 2.1 AA compliance, keyboard navigation, ARIA labels, focus management, meaningful empty and error states, responsive design, and…
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
accessibility-react
caraya
React-specific accessibility skill for WCAG 2.1 AA compliance, keyboard navigation, ARIA patterns, focus management, meaningful empty and error states…
SkillCFreshness: C★ 1Claude Code +9 - 0.429score
go-formatting
caraya
Go formatting skill for gofmt, goimports, and IDE configuration.
SkillDFreshness: D★ 1Claude Code +9 - 0.429score
devrel-integration
caraya
Integrating instructional design with developer relations: developer journey, segmentation, DDMU, and community learning pathways.
SkillDFreshness: D★ 1Claude Code +9 - 0.429score
evaluation-iteration
caraya
Evaluation approaches and iterative development for learning products: pilot plans, SAM cycles, Kirkpatrick, and friction logging.
SkillDFreshness: D★ 1Claude Code +9 - 0.429score
go-core
caraya
Go skill for API design, interface boundaries, concurrency safety, and idiomatic error handling.
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 2, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/caraya/agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from caraya
- 0.592score
design-system
caraya
Organise and maintain a consistent design system through contracts, discovery, reuse and verification.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
dev
caraya
Development workflows for the playwright-cli repository.
SkillAFreshness: A★ 1Claude Code +9 - 0.497score
delivery-classroom
caraya
Instructional design patterns for synchronous classroom delivery of developer education: lecture + live coding, pacing, group dynamics, real-time feedback…
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
delivery-self-paced
caraya
Instructional design patterns for self-paced developer education: motivation maintenance, progress tracking, chunking for independent study, asynchronous…
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
debugging-methodology
caraya
General debugging skill for investigative workflow, error interpretation, and common debugging patterns across languages.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
debugging-pedagogy
caraya
Explicit debugging instruction for developers: five-stage framework, hypothesis testing, tools, and common error patterns.
SkillCFreshness: C★ 1Claude Code +9
Cite this page
delivery-workshop skill. Agent Mart. https://agentmart.dev/skills/caraya-delivery-workshop (last updated 2026-10-24)