Collaborative coding with enforced micro-steps and user-paced control.
npx skills add https://github.com/notque/vexjoy-agent --skill pair-programming
Collaborative coding through the Announce-Show-Wait-Apply-Verify micro-step protocol. The user controls pace, sees every planned change as a diff, and confirms before any file is modified. Works with any domain agent as executor.
This skill runs in the main session (not context: fork) because every step requires an interactive user gate — forking would execute autonomously and break the confirmation protocol.
Maintain step count, current speed setting, and remaining plan throughout the session so you can display "Step N of ~M" with each announcement. The user needs this orientation to stay engaged with the collaborative flow.
For each step in the plan, execute this 5-step protocol:
1. Announce — Describe the next change in 1-2 sentences: what will change and why. Keep announcements brief (1-2 sentences) before showing code immediately because the user came to code together, not to read an essay. Long explanations break flow and reduce collaborative momentum.
2. Show — Display the planned code as a diff or code block. The current step size limit (default 15 lines, max 50 lines) exists because users cannot make informed decisions about changes they have not seen. Every change gets shown—even trivial ones, which are fast to approve—so you and the user stay synchronized. Never exceed the limit: split large changes into sub-steps instead.
3. Wait — Stop and let the user respond with a control command. Do not proceed until you receive an explicit command—assuming the user will say "ok" and applying preemptively turns this into autonomous mode with a running commentary, violating the micro-step protocol.
| Command | Action |
|---------|--------|
| ok / yes / y | Apply current step, proceed to next |
| no / n | Skip this step, propose alternative approach |
| faster | Double step size (max 50 lines) |
| slower | Halve step size (min 5 lines) |
| skip | Skip current step entirely, move to next |
| plan | Show remaining steps overview |
| done | End pair session, run final verification |
4. Apply — Execute the change only after receiving ok/yes/y. Never apply changes without explicit confirmation—doing so turns collaborative pair programming into autonomous mode with a running commentary.
5. Verify — Run relevant checks (lint, type check, test) and report results in one sentence. Catching errors immediately keeps the codebase green and prevents error accumulation across steps, ensuring every change is validated before moving forward.
If a step exceeds the current size limit, split it into sub-steps (Step 3a, 3b, 3c). Announce the split: "This change is ~40 lines. I will split it into 3 sub-steps." This splitting exists because the user must be able to approve or reject individual logical changes—bundling multiple logical changes into one step to avoid splitting defeats the purpose of the micro-step protocol.
Sessions start at 15 lines per step, balancing progress with reviewability. Apply speed changes immediately when the user requests them and acknowledge the new setting because ignoring pace signals breaks trust and the user's sense of control. The user must feel they are the one steering the session.
| Setting | Lines Per Step | Trigger |
|---------|---------------|---------|
| Slowest | 5 | Multiple slower commands |
| Slow | 7 | slower from default |
| Default | 15 | Session start |
| Fast | 30 | faster from default |
| Fastest | 50 | Multiple faster commands (hard cap) |
When the user says faster or slower, acknowledge the change: "Speed adjusted to ~N lines per step."
When the user says done or all steps are complete: run final verification (lint, type check, full test suite), show a summary (steps completed, steps skipped, files modified), and report verification results. This end-of-session gate ensures the codebase is left in a valid state.
Standard Session — User says: "Pair program a function that parses CSV lines in Go"
ok — apply — verifyok — apply — verifySpeed Adjustment — User says faster after Step 2
slower later, drop to ~15Session End — User says done after Step 4 of 6
go vet, go test ./...Cause: User wants speed, not collaboration.
Solution: Acknowledge the preference and offer to switch. Say: "Would you like to switch to autonomous mode? I can implement the remaining steps without confirmation." If they accept, drop the micro-step protocol and implement normally.
Cause: Applied change introduces a lint error, type error, or test failure.
Solution: Announce the fix as the next micro-step. Show the fix diff, wait for confirmation, apply, re-verify. Do not silently fix verification failures regardless of cause—silent fixes violate the protocol.
Cause: A logical change requires more lines than the current limit.
Solution: Split into sub-steps (Step 3a, 3b, 3c). Each sub-step stays within the limit. Announce the split: "This change is ~40 lines. I will split it into 3 sub-steps."
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take notque/pair-programming from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.