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

Pipelines

ASecurity

Gate for whole-pipeline skills that run an entire workflow end-to-end (examples from this author's setup: paint/genjutsu, impeccable, image-to-code, gsd-autonomous, gsd-quick…; classify your own via check-skills). Open it yourself only for end-to-end requests ('처음부터 끝까지', '전체 다 해줘'); a narrow task belongs in its domain gate. Single-select: the user picks exactly ONE pipeline.

3 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgobash

Security Analysis

A100/100

Scanned 9/22/2026

$npx -y skills add devrudals/master-of --skill pipelines --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pipelines?

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

Security grade badge for Pipelines
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/devrudals-pipelines/badge)](https://www.skillsdirectory.com/skills/devrudals-pipelines)

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: "pipelines"
description: "Gate for whole-pipeline skills that run an entire workflow end-to-end (examples from this author's setup: paint/genjutsu, impeccable, image-to-code, gsd-autonomous, gsd-quick…; classify your own via check-skills). Open it yourself only for end-to-end requests ('처음부터 끝까지', '전체 다 해줘'); a narrow task belongs in its domain gate. Single-select: the user picks exactly ONE pipeline."
allowed-tools: Read, Bash
---

# pipelines

Reads `~/.claude/masterof/gates/pipelines.txt` (the pre-rendered index for
this gate — NOT registry.json, which is ~16k tokens to Read). Uses
the same lookup mechanics as the Activation Protocol in `../../SKILL.md`
(read registry, try to match the request first), with one structural
difference:

## Single-select, not multi-select

Every entry here is a complete, self-contained workflow (a full design
pipeline, a full GSD phase-execution mode, an image-to-code conversion) — the
kind of thing where running two at once doesn't compose, it conflicts. So:

1. Read the `"pipelines"` array.
2. Try to match the user's request to exactly one entry first — if confident,
   say so directly ("이 작업엔 `<name>` 파이프라인을 쓸게요") and `Read` its
   `path`. No list.
3. If more than one pipeline plausibly fits (e.g. both `gsd-quick` and
   `gsd-mvp-phase` could handle a small feature), or the user asks what's
   available: print the list and ask the user to pick **one**. Never
   activate two pipelines for the same request — if the task genuinely needs
   more than one, that's a sign it should be broken into separate requests,
   not run as two pipelines at once.
4. `Read` only the chosen entry's `path`, confirm, then proceed.

Scope: one-shot, in-context only, same as every other gate.

## Adding to the roster

`check-skills` routes new pipeline-shaped skills here — see its Step 1
for the "does this run one complete pipeline end-to-end, or does it support a
task" test used to decide `pipelines` vs a domain category. Append
`{name, description, path}` to `"pipelines"` in `registry.json`.

Attribution

devrudalsdevrudals
View sourceSee grades on GitHubMore from devrudals →
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', ...

698461 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 →