agent-orchestration
Orchestrate one Crash WOC unit or one function with Copilot using the repo-local helper scripts, prompt entry points, and a one-writer-at-a-time workflow.
Best use case
agent-orchestration is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Orchestrate one Crash WOC unit or one function with Copilot using the repo-local helper scripts, prompt entry points, and a one-writer-at-a-time workflow.
Teams using agent-orchestration should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/agent-orchestration/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How agent-orchestration Compares
| Feature / Agent | agent-orchestration | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Orchestrate one Crash WOC unit or one function with Copilot using the repo-local helper scripts, prompt entry points, and a one-writer-at-a-time workflow.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# Agent Orchestration ## Purpose Use this skill when the task is larger than a one-off lookup but should still stay tightly scoped to one file or one function. ## Entry Points - `python tools/ai_orchestrate.py --unit <unit-or-path>` - `python tools/ai_orchestrate.py --function <symbol-or-address>` - `.github/prompts/orchestrate-unit.prompt.md` - `.github/prompts/match-function.prompt.md` - `.github/prompts/reverse-engineer.prompt.md` ## Operating Rules - Use read-only helper scripts and read-only exploration freely. - Keep exactly one active code-writing flow at a time. - Keep one active function selected at all times for decomp edits. - Prefer `ai_lookup_symbol.py`, `ai_lookup_unit.py`, `ai_context.py`, `ai_match_plan.py`, and `ai_ghidra.py` over ad hoc repo-wide searching. - Never use interactive `objdiff-cli diff` sessions in automated loops. ## Suggested Unit Workflow 1. Run `python tools/ai_orchestrate.py --unit <unit-or-path> --no-launch --print-prompt`. 2. Review the chosen next function and the generated helper commands. 3. Launch Copilot with the same command without `--no-launch` when ready. 4. Re-run `python tools/ai_match_plan.py <unit-or-path>` after each measurable change. 5. If a function stalls for 4 build/measure cycles, note the blocker and move on. ## Suggested Function Workflow 1. Run `python tools/ai_orchestrate.py --function <symbol-or-address> --no-launch --print-prompt`. 2. Refresh lookup and context with `ai_lookup_symbol.py` and `ai_context.py`. 3. Use `ai_ghidra.py` if the original-side context is still unclear. 4. Edit only the target function, then build only the owning object. ## References - Read [../match-workflow/SKILL.md](../match-workflow/SKILL.md) for the matching loop. - Read [../ghidra-workflow/SKILL.md](../ghidra-workflow/SKILL.md) for Ghidra CLI usage.
Related Skills
task-pack
Generate and run provider-neutral decompilation task packs in crashwoc-decomp. Use when an agent should turn a unit, function, or decomp.me bundle into a self-contained task pack and run it against any backend (print, copilot, codex, claude, aider, or gemini).
symbol-lookup
Lookup symbols, addresses, units, and match metadata in crashwoc-decomp. Use when Codex needs to map a function or global to config/GCBE7D/symbols.txt, split ownership, build/GCBE7D/report.json, or fallback DWARF lines.
split-maintenance
Maintain config/GCBE7D/splits.txt and its generated companions. Use when Codex needs to add or replace unit ranges, import split data from the backup file, seed split ownership, or reason about normalized unit names like ai_1.c and GBA_1.c.
project-onboarding
Onboard Codex to crashwoc-decomp. Use when working in this repository and Codex needs the project layout, build and verification commands, generated-file rules, helper tooling, or the standard workflow for Crash Bandicoot: The Wrath of Cortex GameCube decompilation.
match-workflow
Drive symbol-to-verification matching work in crashwoc-decomp. Use when Codex needs to take a symbol or unit from lookup through context gathering, narrow local builds, and final regression checks.
ghidra-workflow
Query the local Crash WOC Ghidra project through analyzeHeadless.bat for function lookup, decompilation, disassembly, and datatype inspection.
build-triage
Diagnose build failures, progress regressions, and single-object compile problems in crashwoc-decomp. Use when Codex needs to narrow a failing target, inspect report data, or summarize changes from ninja changes.
decomp-match
Autonomous matching-decompilation workflow for Crash WOC GameCube units. Use when the agent needs to decomp-match functions in a C source file.
container-orchestration
Docker and Kubernetes patterns. Triggers on: Dockerfile, docker-compose, kubernetes, k8s, helm, pod, deployment, service, ingress, container, image.
cfn-loop-orchestration-v2
CFN Loop coordination and orchestration - gate checks, validation, consensus, Product Owner decisions. Use when orchestrating multi-agent workflows, managing iteration cycles, or coordinating Loop 2/Loop 3 dependencies.
CFN Docker Loop Orchestration Skill
**Purpose:** Orchestrate container-based CFN Loop execution with agent spawning, loop management, consensus collection, and product owner decision flow.
infrastructure-orchestration
Python CLI and menu orchestration for pipeline runs — project slug validation, interactive picker, PipelineRunner wrapping PipelineExecutor, per-stage logs, secure pipeline wrapper. Use when extending run.sh behavior, fixing menu/CLI routing, or testing discovery helpers.