Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Opening A Pr

ASecurity

Prepare and, only when explicitly requested, publish a reviewed branch as a ready pull request with verified scope and evidence.

2 stars
0 votes
0 copies
0 views
Added 10/1/2026
ai-agentsperformance

Security Analysis

A100/100

Scanned 10/6/2026

$npx -y skills add williamwue/oh-my-stack --skill opening-a-pr --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Opening A Pr?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Opening A Pr
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/williamwue-opening-a-pr/badge)](https://www.skillsdirectory.com/skills/williamwue-opening-a-pr)

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

Download with Pro
Files
SKILL.md
---
name: opening-a-pr
description: "Prepare and, only when explicitly requested, publish a reviewed branch as a ready pull request with verified scope and evidence."
disable-model-invocation: true
---

# Opening a Pull Request

Use this workflow only when the user explicitly asks to create or publish a pull
request. Finishing another workflow does not imply publication authority.

1. Resolve the repository, remote, base branch, current branch, and forge from
   current state. Stop if the destination is ambiguous or the branch contains
   unrelated work that cannot be separated safely.
2. Inspect the complete diff and commit range. Confirm that generated files,
   third-party notices, and provenance records are included when applicable.
3. Run the relevant clean checks and record exact outcomes. A prior child report
   or stale run is not release evidence.
4. Shape small ordered commits without rewriting shared history unless the user
   explicitly authorized it. Never discard unrelated changes.
5. Write a concise conventional title and a body with `Why`, `What changed`,
   `Scope`, optional `Tradeoffs`, `Blast Radius`, and `Verification`. Use section
   headings when the repository template or host calls for them. Keep the
   problem and approach brief, list only meaningful changes, and name scope
   boundaries when they affect review. Verification names actual commands and
   outcomes; performance claims link the sample, spread, and limiter evidence
   and keep one primary number in the body. Follow the repository template and
   the user's writing requirements. Apply `technical-writing`
   and `unslop` without changing technical meaning.
6. Prefer a host-owned pull-request tool for operations it owns. Use the
   resolved forge for unsupported operations and follow the host's association
   requirements so created or updated requests remain attached to the task.
   Tool availability does not grant publication authority.
   Show the resolved destination and intended public change immediately before
   the external operation. Create a ready pull request, not a draft, using the
   available forge integration.
7. Read the created pull request back from the forge. Report its URL, base and
   head branches, readiness, and any verification boundary. Creating it does not
   authorize merging or continuous monitoring.

If pull-request creation is unavailable, produce the exact title, body,
destination, and pending command or operation, then report that publication did
not occur. Never claim a URL that was not returned by the forge.

Attribution

williamwuewilliamwue
View sourceSee grades on GitHubMore from williamwue →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →