try-works/role-model / .agents/skills/recursive-mode
recursive-mode
UnverifiedRepository workflow orchestration skill for staged implementation, locked artifacts, late-phase receipts, and durable memory maintenance. Use when executing recursive-mode runs, resuming a run, locking a phase, or verifying locks.
scripts/recursive-training-extract.py
View on GitHub#!/usr/bin/env python3
"""
Companion extractor for recursive-training prompt evaluation.
The training scripts build extraction prompts and hand them to this script.
The default extractor skips cleanly when no extractor implementation is wired.
"""
from __future__ import annotations
import argparse
import sys
from pathlib import Path
def main() -> int:
parser = argparse.ArgumentParser(description="Companion extractor for recursive-training")
parser.add_argument("--repo-root", required=True, help="Repository root path")
parser.add_argument("--prompt-file", required=True, help="Path to the prompt file to evaluate")
args = parser.parse_args()
prompt_path = Path(args.prompt_file).resolve()
if not prompt_path.exists():
print("ERROR: Prompt file not found for recursive-training extraction.", file=sys.stderr)
return 1
print(
"Training extractor is not available for recursive-training in this environment.",
file=sys.stderr,
)
return 2
if __name__ == "__main__":
raise SystemExit(main())
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: 466k | Updated | Claude CodeCodex | Verified | 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: 466k | 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: 319k | 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: 319k | Updated | Claude CodeCodex | Verified | Install |