agentleFS
Sign inStart free
DITlieDDITlieD/ELAI-archive/.agents/skills/prompt-transform/SKILL.md

prompt-transform

Skill24 starsChanged 2 months agoMITView on GitHub

Reformats user prompts before implementation. Triggers on any task implying code changes, implementation, multi-step work, or starting/resuming a plan phase. This includes "start phase X", "implement X", "continue X", any plan phase execution request, AND bug reports phrased as questions ("doesn't work", "isn't saving", "is X wired", "broken", "why does X", "fix this"). Diagnostic phrasing does not exempt from protocol.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    If session_id is provided, the agent reads the context package from workflow/sessions/{session_id}/context-package.md (written by …

    line 20
  2. Distinctive:

    Wait for confirmation. Do not proceed until the user approves.

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Prompt transformation

Trigger: any task implying code changes, implementation, multi-step work, or starting/resuming a plan phase. Bug reports count even when phrased as questions — trigger verbs include: "doesn't", "isn't", "broken", "wired", "fix", "why does", "why doesn't", "does X save/persist/work". If the answer requires reading the codebase to find out whether something is wired or correct, it is a code-change task and triggers this skill. Skip: messages starting with !. Pure yes/no replies. Purely informational questions where the answer comes from training or documentation, not from reading the codebase. Tie-breaker: if unsure whether the task is informational or implementation, treat it as implementation. Over-spawning context-compiler is cheap; skipping it is expensive (re-do).

  1. Spawn the prompt-engineer agent (.Codex/agents/prompt-engineer.md) with:
    • task: the raw task description
    • session_id: the current session ID (if in a plan resume or phase start flow) If session_id is provided, the agent reads the context package from workflow/sessions/{session_id}/context-package.md (written by context-compiler). Do NOT pass the context package content inline — the agent reads it directly to save main model tokens. For ad-hoc tasks without a session, omit session_id and pass context inline as before.
  2. Show result. Ask: "Reformatted. Approve or edit:"
  3. Wait for confirmation. Do not proceed until the user approves.

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