agentleFS
lalulalilalulali/vespyr/.agents/skills/shut-up/SKILL.md

shut-up

Skill11 starsChanged 11 days agoMITView on GitHub

One-shot silent execution mode — executes tasks directly with zero unsolicited critique, no conversational filler, and ultra-minimal output. Use when the user says "shut up and just do it", "no commentary, just execute", "minimal output", or invokes /shut-up with scope already locked.

  • Deletes or force-pushes

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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:

    When the requirements and scope are already locked, unsolicited Socratic feedback, multi-paragraph architectural rationale, and …

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

/shut-up — Silent Execution Mode

What this skill does

One-shot runtime context modifier that executes requests directly and silently with ultra-minimal output and zero conversational lecture.

When to use

  • "Shut up and just do it" / "no commentary, just execute"
  • "Minimal output" / "I don't want the lecture"
  • Any task where scope and requirements are already locked and further Socratic probing is friction, not value

When NOT to use

  • Scope is still open and the DNA 4 intent gate has not been passed — silence there is malpractice, not efficiency
  • A destructive or irreversible action is requested without confirmation (see the Destructive Safety Gate Exception below)
  • The user asked for a second opinion, a design critique, or a review

Why This Skill Exists

When the requirements and scope are already locked, unsolicited Socratic feedback, multi-paragraph architectural rationale, and pleasantries add friction. /shut-up switches the agent into an introverted, silent implementer mode.

Invariant Rules & Schema

  1. Runtime Context Only: /shut-up MUST NOT write flags or state to project-context.md or active-decisions.md.
  2. Ultra-Minimal Output — the schema contract. Output must contain ONLY:

    • Direct file edits (tool calls or diff blocks)
    • Exact shell command execution outputs
    • A single 1-line status summary

    Rules 2 and 3 used to be separate and said the same thing: the old Rule 2 was a compressed restatement of this list, missing only the shell-output line. One rule, stated once.

  3. Destructive Safety Gate Exception: If a requested command causes permanent data loss (e.g. rm -rf, DROP TABLE, uncommitted git wipe), the agent is permitted a single 1-line confirmation prompt before proceeding. This is why the frontmatter declares a question tool — the one harness that reads allowed-tools restricts the skill to what it declares, so a rule permitting a prompt is unenforceable under a declaration that forbids one. /round-table declared it; this skill did not, while being the only one of the two whose rules actually require asking.
  4. The session-write still runs, and it DOES touch project-context.md. Rule 1 forbids writing flags or state; session-write writes an activity line and refreshes Phase / Blockers / footer via syncProjectContext. Those overlap on one file, so — the global rule wins. Run it. Rule 1 is about kind of write, not file: /shut-up does not record itself as a mode or a flag. An earlier version of this rule claimed the two did not overlap at all. They do, and a claim that a mechanism does not touch a file it touches is worse than no rule.

Response Template

[File tool edits or command executions]

Done: <Single 1-line summary of changes made>.

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.