Skip to content

charlieviettq/awesome-agent-skill / .claude/skills/autoskill

autoskill

Verified

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.

scripts/autoskill.py

View on GitHub
"""Unified CLI for the autoskill skill.

Subcommands:
  run      — detect workflows and draft proposed skills
  doctor   — verify screenpipe + LM Studio + config + skills dir
  promote  — move an approved proposal into scientific-skills/
"""

import argparse
import sys


def main(argv=None):
    parser = argparse.ArgumentParser(prog="autoskill", description=__doc__,
                                     formatter_class=argparse.RawDescriptionHelpFormatter)
    parser.add_argument("command", choices=["run", "doctor", "promote"],
                        help="subcommand to run")
    parser.add_argument("rest", nargs=argparse.REMAINDER,
                        help="arguments forwarded to the subcommand")
    args = parser.parse_args(argv)

    if args.command == "run":
        import run as _run
        return _run.main(args.rest)
    if args.command == "doctor":
        import doctor as _doctor
        return _doctor.main(args.rest)
    if args.command == "promote":
        import promote as _promote
        return _promote.main(args.rest)
    raise AssertionError(f"unreachable: {args.command!r}")


if __name__ == "__main__":
    sys.exit(main())
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall