⏳ This skill is pending AI review.

Scores will appear once the review pipeline completes.

version unknown

openclaw-terse

@bluebirdback⭐ 1 stars

Make an OpenClaw agent concise and low-fluff by tightening persona files and reply rules. Use when an agent is too verbose, rambly, repetitive, overly explanatory, or when the user asks to make replies shorter, simpler, more direct, less chatty, or better behaved on GPT-5.4.

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

—/10

// RATINGS

⭐GitHub Stars
⭐ 1 on GitHubGitHub ↗

New / niche

🟢ProSkills Score
—
📍

Not yet listed on ClawHub or SkillsMP

// README

openclaw-direct-gpt54

中文说明

Make GPT-5.4 in OpenClaw reply shorter, clearer, and more direct.

For OpenClaw

Use this prompt:

Install and apply the latest version of this skill from https://github.com/BlueBirdBack/openclaw-direct-gpt54. Back up my current SOUL.md and USER.md first. Merge changes; do not replace my identity, safety, or operational rules.

This skill works by tightening:

  • SOUL.md
  • USER.md
  • RESPONSE_PROTOCOL.md

It is prompt-file guidance, not a plugin or runtime guardrail. If GPT-5.4 still leaks "If you want, I can..." after this, you may also need a separate runtime fix.

Update this skill

Use the same prompt again:

Install and apply the latest version of this skill from https://github.com/BlueBirdBack/openclaw-direct-gpt54. Back up my current SOUL.md and USER.md first. Merge changes; do not replace my identity, safety, or operational rules.

Rules that matter

  • answer first
  • default short
  • expand only when needed
  • remove praise, recap, and prompt-echo
  • never ask permission for directly implied low-risk internal bookkeeping after the main task; do it, then report it
  • if you created a durable artifact that obviously belongs in an index or tracker, update that index or tracker before replying
  • ask only for destructive, external/public, or genuinely ambiguous follow-up
  • stop when the answer is done

Concrete behavior target

Bad:

Created docs/project-x.md. If you want, I can add it to Projects.md.

Good:

Created docs/project-x.md and linked it in Projects.md.

Patch safely

  • merge, don’t replace
  • keep stronger local safety and operational rules
  • keep the target agent’s own name, identity, and voice
  • keep backups so rollback is easy

License

MIT

// HOW IT'S BUILT

KEY FILES

skills/openclaw-terse/SKILL.mdREADME.md

// REPO STATS

1 stars

// SHARE

Share on XShare on LinkedIn