Skip to content
Back to skills

Anti Bottleneck

ASecurity

Load this skill BEFORE asking the user for confirmation, approval, next steps, or choices that can be resolved through verification, repo context, or reasonable defaults. Also load when you are unsure how to proceed and might otherwise stop early.

  • 6 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added October 12, 2026
ai-agentsgit

Works with

  • claude code
  • cli

Security analysis

A100/100

Scanned October 12, 2026

npx -y skills add yoshpy-dev/ralph --skill anti-bottleneck --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Anti Bottleneck?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Anti Bottleneck
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/yoshpy-dev-anti-bottleneck/badge)](https://www.skillsdirectory.com/skills/yoshpy-dev-anti-bottleneck)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: anti-bottleneck
description: Load this skill BEFORE asking the user for confirmation, approval, next steps, or choices that can be resolved through verification, repo context, or reasonable defaults. Also load when you are unsure how to proceed and might otherwise stop early.
user-invocable: false
---
Human attention is the scarcest resource in the harness.

Before asking the user anything, check whether you can:
- inspect the codebase
- inspect plans or docs
- run tests or verification scripts
- gather logs or screenshots
- use a focused subagent
- choose a reasonable default and document it

Escalate only for:
- irreversible destructive actions
- external approvals that are genuinely required
- missing credentials or secrets
- product or design judgments that cannot be grounded in the repo or evidence

When stuck:
1. reduce scope
2. gather evidence
3. update the plan
4. try a different verifier or reviewer
5. present the best grounded answer you can

## CLI execution modes

This skill runs under both Claude Code and Codex. The execution mode follows
the conventions in AGENTS.md and `.codex/AGENTS.override.md`.

| Aspect | Claude Code | Codex |
|--------|-------------|-------|
| Skill invocation | `/skill-name` slash command | `$skill-name` mention or the `/skills` menu (avoid the `/skill-name` form — it collides with built-ins) |
| Skill body path | `.claude/skills/<name>/SKILL.md` | `.agents/skills/<name>/SKILL.md` |
| Subagent mechanism | `Task(subagent_type=...)` when a policy delegates | `.codex/agents/` custom agents when a policy delegates |
| Structured prompts | `AskUserQuestion` | Numbered options printed to stdout, awaiting a digit reply |
| Artifacts | `docs/reports/`, `docs/plans/`, `docs/specs/` (shared) | Same (CLI-agnostic) |

The drift check (`./scripts/check-skill-sync.sh`) cross-checks both bodies and
invocation metadata — editing only one side will fail CI.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.