agentleFS
Sign inStart free
jtarorehjtaroreh/agystack/skills/in-your-own-words/SKILL.md

in-your-own-words

Skill128 starsChanged 2 days agoMITView on GitHub

Playback structure to verify understanding of user intent. Restates goals and problems clearly before proposing or executing implementations.

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify alignment on user intent and requirements before executing complex tasks.

    line 8
  2. Distinctive:

    Use the following explicit structure:

    line 15
  3. Distinctive:

    Follow these principles when playing back intent:

    line 33
  4. Distinctive:

    Use plain declarative prose.

    line 35
  5. Distinctive:

    Do not echo the user prompt verbatim.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “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

In Your Own Words

Verify alignment on user intent and requirements before executing complex tasks. Playback the core objectives in your own words to prevent misunderstandings and misaligned effort.

Playback Structure

Structure intent playbacks cleanly. Goals and problems are stated clearly before proposing or executing implementations. Use the following explicit structure:

  1. Goal. State the intended outcome from the perspective of the user or consumer.
  2. Problem. Define the defect, friction, or technical limitation being resolved.
  3. Scope and non-goals. Clarify the boundaries of what will and will not change.
  4. Proposed implementation. Outline the specific sequence of edits and verification steps.

When to Use

Apply this playback structure in the following situations:

  • Starting a multi-phase or cross-cutting feature request.
  • Receiving complex instructions with multiple competing requirements.
  • Taking over a task from another agent or session transcript.
  • Resolving ambiguous user feedback or architectural forks.

Execution Rules

Follow these principles when playing back intent:

  • Use plain declarative prose.
  • Do not echo the user prompt verbatim.
  • Identify unstated assumptions and surface them explicitly.
  • Request confirmation only when genuine product decisions cannot be resolved through empirical probes.

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.

Reviews can't be read right now.

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