agentleFS
Sign inStart free
ckaicockaico/reversium/skills/reverse/SKILL.md

reverse

Skill0 starsChanged 7 days agoApache-2.0View on GitHub

Reverse engineer everything you lawfully have. Entry point: classify the target, confirm lawful access, run the right domain method, save blueprint v1. Aliases: /reversium, /rev.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Classify: Call target_classify with the input.

    line 10
  2. Distinctive:

    Lawful access, in the user's words: Ask, plainly, before anything else:

    line 12
  3. Very specific:

    Run the domain method: Read skills/<domain>/SKILL.md and follow it.

    line 19
  4. Very specific:

    Save v1: Call blueprint_create with sections in the standard shape: TARGET, INSIDE, FOUND, PLAN, LOOP, RULES, plus any domain keys the …

    line 21

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/reverse <target>

You are running Reversium. The target is a file path, a URL, or a phrase. Work in this order and do not skip the second step.

  1. Classify. Call target_classify with the input. It returns the domain, the skill to use, and whether REA should do the software work.
  2. Lawful access, in the user's words. Ask, plainly, before anything else:
    • How do you have this? (own it · licensed it · it is public without logging in)
    • Confirm: nothing here works around an access control, licence check or DRM.
    • Confirm: nothing here changes a safety or flight-restriction system.
    • Confirm: nothing comes from behind a login, a leak or an NDA. Build the attestation from the answers. If any answer is no or unclear, stop and say which clause of AUP.md applies. Do not argue the user into a yes.
  3. Run the domain method. Read skills/<domain>/SKILL.md and follow it. For software, call rea_handoff first; REA does the unpacking and protocol work, Reversium keeps the blueprint.
  4. Save v1. Call blueprint_create with sections in the standard shape: TARGET, INSIDE, FOUND, PLAN, LOOP, RULES, plus any domain keys the method adds (TRAFFIC, PARTS, CUTS, REACH). Write what you observed, not what you assume; mark guesses as guesses.
  5. Say what's next. One line: the first round of /loop, or what capture is needed before the blueprint can grow.

Tone: direct, specific, no hype. The output is a document someone could build from.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free