dse120071750/m8m-harness-builder / skills/m8m/m8m-harness-builder/templates
__SKILL_NAME__
VerifiedM8M 3.1 product skill whose closed native source compiles into a displayable, executable milestone workflow.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.1 KB |
| asset.output.schema.json | config | 578 B |
| codebase-launcher.py | script | 17.6 KB |
| milestone/assemble.py | script | 8.3 KB |
| milestone/gem.md | markdown | 3.2 KB |
| milestone/judge_input.schema.json | config | 1.3 KB |
| milestone/judge_output.schema.json | config | 589 B |
| milestone/judge_test_tool.py | script | 1.4 KB |
| milestone/judge_tool.py | script | 1.1 KB |
| milestone/test_assemble.py | script | 1.1 KB |
| product-SKILL.md | markdown | 2.1 KB |
| run.py | script | 2.2 KB |
| step/draft.schema.json | config | 257 B |
| step/input.schema.json | config | 245 B |
| step/output.schema.json | config | 237 B |
| step/test_tool.py | script | 683 B |
| step/tool.py | script | 955 B |
step/tool.py
View on GitHub"""BUILD_REQUIRED FlowStep scaffold: __STEP_ID__.
Return a dict that matches output.schema.json. Do not write the envelope.
If this step needs a model, return:
{"_flowstep": "NEED_MODEL", "model": "completion", "model_request": {...}}
The driver will stop, the agent writes draft.json from that request, and
advance is called again. This function then receives `draft` and must return
the typed payload.
This generated file is deliberately non-runnable. Implement the public
contracts, replace the generated test, and remove both BUILD_REQUIRED
declarations before asking the builder to validate or install the harness.
"""
from __future__ import annotations
from typing import Any
MODEL = "none"
M8M_BUILD_STATUS = "BUILD_REQUIRED"
M8M_RUNNABLE = False
def run(input_data: dict[str, Any], draft: dict[str, Any] | None = None, **_: Any) -> dict[str, Any]:
raise NotImplementedError("__STEP_ID__ is a generated stub; implement this tool")
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 |