Skip to content
Back to skills

Oneshot

ASecurity

Run the complete APEX workflow from analysis through runtime proof. Use when the user invokes $oneshot with a request.

  • 3 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added September 5, 2026
securitycode-reviewgit

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned September 22, 2026

npx -y skills add twikus/claude-configuration --skill oneshot --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Oneshot?

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

Security grade badge for Oneshot
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/twikus-oneshot/badge)](https://www.skillsdirectory.com/skills/twikus-oneshot)

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: oneshot
description: Run the complete APEX workflow from analysis through runtime proof. Use when the user invokes $oneshot with a request.
disable-model-invocation: true
argument-hint: "[-a|auto] <request>"
---

Run these skills in order, passing each result to the next:

1. `$analyze`
2. `$plan`
3. `$implement`
4. `$code-review`
5. `$verify`

The `$plan` result is the source of truth. Do not skip, combine, or reorder stages.

With `-a` or `auto`, do not pause for confirmation. Resolve facts, make safe reversible decisions, and record assumptions in the plan and, when authorized, on the issue. Fix review or verification failures, then rerun every affected downstream stage.

Close a GitHub issue created in this run only after `$verify` reports PASS for every acceptance criterion. Preserve `$verify`'s evidence: show every screenshot inline. Comment with the outcome and commit SHA when one exists, follow the repository's GitHub attribution rules, then close the issue and read it back as `CLOSED`. Leave it open when verification is `BLOCKED — NOT PROVEN`.

Without autonomous mode, pause only for a material decision or authorization. Stop only after verification passes and any issue created in this run is closed, or progress requires unavailable access, credentials, external authorization, or an irreversible decision.

Files in this skill

  • SKILL.md1.9 KB
  • agents/openai.yaml328 B
  • assets/codex-icon.svg322 B

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…