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).
Best use case
task-pack is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
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).
Teams using task-pack 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/task-pack/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How task-pack Compares
| Feature / Agent | task-pack | 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?
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).
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.
SKILL.md Source
# Task Pack Workflow A task pack is a self-contained directory describing one decompilation task. It is backend-agnostic: the same pack works with any agent or a browser chat. ## Generate a task pack Use `python tools/ai_task.py` with the mode that matches the target: - `python tools/ai_task.py unit src/gamecode/crate.c` - `python tools/ai_task.py function MoveCrate` - `python tools/ai_task.py decompme path/to/export.zip` The pack is written to `.ai/tasks/<timestamp>-<target>/` and contains `task.json` (the canonical, machine-readable task), `prompt.md`, `context.md`, `verify.sh`, `verify.ps1`, and `notes.md`. Inspect `task.json` for the resolved unit, `allowed_edit_files`, `forbidden_edit_files`, and `verify_commands`. ## Run a task pack - Browser ChatGPT / any agent without a local CLI: `python tools/ai_run.py --backend print .ai/tasks/<task>` and paste the output. - Local GitHub Copilot: `python tools/ai_run.py --backend copilot .ai/tasks/<task>`. - Best-effort local CLIs: `--backend codex|claude|aider|gemini` (each falls back to printing the prompt when the CLI is not on PATH). ## Rules - Work on one function at a time; keep edits inside `allowed_edit_files`. - Never edit the generated files listed in `forbidden_edit_files`. - No inline asm; never start an interactive `objdiff-cli diff` session. - Stop or mark blocked after 4 build/measure cycles without improvement, then record the blocker in the pack's `notes.md`. ## References - Read [references/backends.md](references/backends.md) for backend selection and browser usage. - Read [references/verification.md](references/verification.md) for verifying a task pack.
Related Skills
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.
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.
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.
You are a professional Chief Marketing Officer. Your task is to help a user start and grow their social media presence organically through a series of questions and generate a growthplan.md blueprint.
Follow these instructions:
tasks-acset
Google Tasks management via TasksACSet. Transforms task operations into GF(3)-typed Interactions, routes to triadic queues, detects saturation for task-zero-as-condensed-state.
performing-packet-injection-attack
Crafts and injects custom network packets using Scapy, hping3, and Nemesis during authorized security assessments to test firewall rules, IDS detection, protocol handling, and network stack resilience against malformed and spoofed traffic.
performing-network-packet-capture-analysis
Perform forensic analysis of network packet captures (PCAP/PCAPNG) using Wireshark, tshark, and tcpdump to reconstruct network communications, extract transferred files, identify malicious traffic, and establish evidence of data exfiltration or command-and-control activity.