agentleFS
MattieMattie/mattie_skills/skills/goal-check/SKILL.md

goal-check

Skill1 starsChanged 9 days agoMITView on GitHub

Give the human a compact reminder of the thread's longer-term goal, recent work, and the input needed next. Use when the user asks for a goal check, context reset, or quick orientation before continuing a task.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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. Distinctive:

    Keep the entire response succinct.

    line 26
  2. Very specific:

    If the longer-term goal is uncertain, give the best useful guess and append (unclear) or a more precise short qualifier.

    line 28
  3. Distinctive:

    Keep each table value on one line.

    line 33

≈ “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

Goal Check

Summarize the current thread for the human. Infer the longer-term goal from the whole thread (or half-dozen of turns or so, if a lot has happened) and the near-term work from the most recent one or two tasks.

Return exactly this structure:

## Goal Check!

Here's my understanding of this <thread or project>:

| Type | Summary |
| --- | --- |
| Long | <one-sentence summary of the longer-term goal> |
| Near | <one-sentence summary of the most recent one or two tasks> |
| Next | <what the agent needs from the human to progress> |

Keep the entire response succinct. Apply these rules:

  • If the longer-term goal is uncertain, give the best useful guess and append (unclear) or a more precise short qualifier.
  • In NEXT, bold each short, distinct response keyword in uppercase. If a choice is required then put each choice option in uppercase so that a single word can kick it in motion. If no human input is needed, mention that.
  • Keep each table value on one line. Escape/replace literal pipe characters in values so the Markdown table remains valid.
  • Include no preamble, explanation, bullets, code fence, closing, or other commentary outside the heading and table.
  • Assume that if this skill is given, the human or agent is not quite sure where things stand and it is your job to make sure their next turn is with clear context in plain language.

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.