Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Prepare Fabric Pr

ASecurity

Prepare or update a Fabric pull request by proving the changeset-or-skip decision, validation evidence, DCO sign-off, and public-safe PR metadata. Use before the first push, after later revisions, or when asked to create or update a PR. Do not use to review an unrelated PR or authorize relay.

3 stars
0 votes
0 copies
1 views
Added 9/20/2026
ai-agentsgit

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add Fabric-Pro/fabric-oss --skill prepare-fabric-pr --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Prepare Fabric Pr?

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

Security grade badge for Prepare Fabric Pr
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fabric-pro-prepare-fabric-pr/badge)](https://www.skillsdirectory.com/skills/fabric-pro-prepare-fabric-pr)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: prepare-fabric-pr
description: Prepare or update a Fabric pull request by proving the changeset-or-skip decision, validation evidence, DCO sign-off, and public-safe PR metadata. Use before the first push, after later revisions, or when asked to create or update a PR. Do not use to review an unrelated PR or authorize relay.
---

# Prepare a Fabric pull request

Produce a reviewable PR whose release decision is explicit and whose public
metadata contains no private identifiers.

## Before pushing

1. Read the root `AGENTS.md` sections on public repository hygiene and
   changesets, plus `packages/fabric-app/README.md`.
2. Fetch the target branch and inspect the complete diff from its merge base.
   Preserve unrelated working-tree changes.
3. Classify the release impact:
   - Production-shipping or user-visible behavior requires a changeset,
     normally `"fabric-app": patch`.
   - Docs-only, CI-only, Markdown-only, or pure changeset changes are normally
     eligible for `skip-changeset`.
   - A different change may skip only when it has no deployable or
     user-visible effect; state that reason explicitly.
4. For an impacting change, run Changesets with `--output` against the target
   branch and inspect the JSON. Require `.releases | length > 0`; exit code zero
   with an empty release list is a failed release decision.
5. For a skip-eligible change, do not create a meaningless changeset. Record
   the no-impact reason for the PR and plan to apply `skip-changeset` once the
   PR exists.
6. Run validation proportional to the diff and record exact commands and
   results. A skipped, unavailable, timed-out, or sandbox-blocked check is
   unverified, not passing.
7. Inspect all public text—branch, commits, changeset headline/body, and PR
   draft—for real organizations, people, deployments, hostnames, internal URLs,
   or private ticket prose. Replace them with synthetic descriptions.
8. Commit only when authorized. Use `git commit -s`; never add AI attribution.

## Create or update the PR

Creating or updating a PR is an external mutation. Do it only when the user's
request authorizes it.

- Use the repository PR template.
- Explain behavior, release decision, and verification without claiming checks
  that did not run.
- After creating a skip-eligible PR, apply `skip-changeset` immediately and
  verify the stored label.
- After every later push, repeat the diff review, release decision, and
  Changesets JSON check. A previous result belongs to the old head.

Stop after the PR is created or updated unless the user explicitly authorized
landing. PR creation alone never authorizes relay, merge, or deployment.

Attribution

Fabric-ProFabric-Pro
View sourceMore from Fabric-Pro →
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

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 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', ...

695601 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →