orchestrate-reference
Skill9 starsChanged 22 days agoMITView on GitHub
Reference library for Orchestrate - ready-to-paste Claude Code prompts (kickoff, iteration, audit, freeze), the engineering playbook principles with case studies, the AI judge preparation notes, the release checklist, the community kit CLI, past-winner patterns, and rubric history. Read on demand; do not read top to bottom.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/orchestrate.mdcCursor rule
- llms.txtllms.txt
- orchestrate-buildSkill
- orchestrate-interviewSkill
- orchestrate-packageSkill
- orchestrate-scoreSkill
- orchestrateSkill
- orchestrate-submitSkill
- orchestrate-test-fixSkill
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 8
Read the file you need. The other skills point here.
≈ “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
Orchestrate Reference
Read the file you need. The other skills point here.
| Need | File |
| Paste-ready prompts for Claude Code: kickoff, iteration protocol, targeted audit, final freeze | references/prompt-templates.md |
| Why a change counts, blast radius, counterfactuals, ceilings, rejection logs, auditing the audit | references/playbook-principles.md |
| Judge's topics, praise, criticism, model answers, traps | references/judge-prep.md |
| Release gate with proof lines | references/release-checklist.md |
| Loop patterns: agent loop, plan-build-review, change-record, prompt relay, verify-before-trust, per-row safety | references/loop-patterns.md, references/loop.md |
| What top finishers did | references/winning-approaches.md |
| Rubric and history of past rounds | references/orchestrate-context.md |
| Community CLI (evaluate, experiment, score, mentor) | references/kit-repo.md, references/loop-kit-readme.md, references/faq.md |
Iteration change-record format
CHANGE / REQUIREMENT / CLAIM / METRIC / BASELINE / RESULT / BLAST RADIUS / COUNTERFACTUAL / VERDICT (SHIP or REJECT).
Caution
Figures in these files come from past rounds and user reports. Re-verify against the current challenge before quoting any of them. Do not state a number from here as your own result.
Goal mode
This skill is a lookup library, so it has no completion goal of its own. Use the goal conditions in the phase skills instead.
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.