ldilov/harness-forge / .agents/skills/complex-task-protocol
complex-task-protocol
VerifiedAuto-discoverable wrapper for `.hforge/library/skills/complex-task-protocol/SKILL.md`.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 952 B |
SKILL.md
View on GitHub---
name: complex-task-protocol
description: Auto-discoverable wrapper for `.hforge/library/skills/complex-task-protocol/SKILL.md`.
---
# Complex Task Protocol
## Activation
- trigger when a task is multi-step, risky, cross-module, orchestration-heavy, or likely to need verification and recovery discipline
- trigger when the task may benefit from a small number of bounded subagents for independent sidecar work
- trigger when reusable learning may need to be captured after complex work
## Use These Surfaces
- `.hforge/library/skills/complex-task-protocol/SKILL.md`
- `.hforge/runtime/agent-brief.md`
- `.hforge/generated/agent-command-catalog.json`
- `.hforge/runtime/recursive/language-capabilities.json`
## Operating Rule
Use the canonical skill under `.hforge/library/skills/` for execution. Treat this wrapper as a discovery entrypoint only. Activate the protocol by task complexity thresholds rather than by requiring a slash command.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |