pmx-canvas
Copilot instructions30 starsChanged 9 days agoMITView on GitHub
Before changing anything a person sees (styles, chrome, node renderers, Home, edges), follow the Design section of AGENTS.md: build to the drawings in docs/design/ per the guide and build plan in docs/design.md. This repo ships an agent-facing skill pipeline under .agents/skills/, .claude/skills/, and .opencode/skills/. After solving non-obvious issues, consider logging to .learnings/ using the self-improvement skill format. Promote broadly reusable patterns into CLAUDE.md, AGENTS.md, or this file when they should guide future sessions.
Where files are headingNew Copilot instructions files have more rules about branches and pull requests, and fewer about code style.
Of the Copilot instructions files we read, the 2,336 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- control-session-orchestratorSkill
- data-analysisSkill
- doc-coauthoringSkill
- frontend-designSkill
- json-render-codegenSkill
- json-render-coreSkill
- json-render-inkSkill
- json-render-mcpSkill
- json-render-reactSkill
- json-render-shadcnSkill
- playwright-cliSkill
- pmx-canvas-orchestrationSkill
- pmx-canvasSkill
- pmx-canvas-testingSkill
- published-consumer-e2eSkill
- tufte-vizSkill
- web-artifacts-builderSkill
- web-design-guidelinesSkill
The file
We split this copilot-instructions.md into the rules it gives an agent
5 rules. About 0 are common, 0 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 5
Before changing anything a person sees (styles, chrome, node renderers, Home, edges), follow the Design section of AGENTS.md: build to the …
- Very specific: line 13
Use skill-pipeline to classify coding tasks and route them through the right depth.
- Very specific: line 15
Use learning-aggregator and eval-creator for cross-session improvement loops.
- Very specific: line 16
Use the *-ci variants for headless CI workflows only.
- Very specific: line 20
After solving non-obvious issues, consider logging to .learnings/ using the self-improvement skill format.
≈ “Common” is an estimate: at least 1 in 5 of the 3,779 Copilot instructions 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
Copilot Instructions
Design
Before changing anything a person sees (styles, chrome, node renderers, Home, edges), follow the
Design section of AGENTS.md: build to the drawings in docs/design/ per the guide and build
plan in docs/design.md.
Agent Skill Pipeline
This repo ships an agent-facing skill pipeline under .agents/skills/, .claude/skills/, and .opencode/skills/.
- Use
skill-pipelineto classify coding tasks and route them through the right depth. - For larger implementation work, prefer the pipeline of
plan-interview,intent-framed-agent,context-surfing,verify-gate,simplify-and-harden, andself-improvement. - Use
learning-aggregatorandeval-creatorfor cross-session improvement loops. - Use the
*-civariants for headless CI workflows only.
Learnings
After solving non-obvious issues, consider logging to .learnings/ using the self-improvement skill format.
- Corrections and best practices:
.learnings/LEARNINGS.md - Failures and debugging outcomes:
.learnings/ERRORS.md - Missing capabilities:
.learnings/FEATURE_REQUESTS.md
Promote broadly reusable patterns into CLAUDE.md, AGENTS.md, or this file when they should guide future sessions.
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.