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

Forgecat Publish

ASecurity

Publish a profile to the registry, manage its versions, visibility and tags, and recover its source. Use when the user is ready to push, wants to unpublish or re-scope a profile, or lost the local source of one they own.

84 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentssecurity

Works with

cli

Security Analysis

A100/100

Scanned 9/23/2026

$npx -y skills add nota-america/forgecat-agent-profiles --skill forgecat-publish --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Forgecat Publish?

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

Security grade badge for Forgecat Publish
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/nota-america-forgecat-publish-fb3b606a/badge)](https://www.skillsdirectory.com/skills/nota-america-forgecat-publish-fb3b606a)

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: forgecat-publish
description: Publish a profile to the registry, manage its versions, visibility and tags, and recover its source. Use when the user is ready to push, wants to unpublish or re-scope a profile, or lost the local source of one they own.
---

# Publishing

## 1. push is the first real test

A local path can't be installed — the CLI answers *"Only registry sources are
supported."* So the first time anyone sees where the files actually land is
**after** publishing. Plan for that:

    push private → view → install it yourself → then flip to public

That way a wrong layout costs a version number, not a public release.

## 2. Before

    forgecat whoami                      # right account, right scope
    forgecat validate && forgecat plan   # schema clean, layout as intended

The scope in `name:` must be one the account owns.

## 3. push

    forgecat push --bump minor
    forgecat push --set-version 1.0.0
    forgecat push --visibility private --tags "skills,review"

**push assigns the version** — don't write one into `profile.yml` (deprecated and
ignored). `--visibility` is required to publish public non-interactively, `--tags`
only seeds on the first push, `--json` is for automation, and `-y` is auto-detected
when there is no TTY.

Before uploading it prints the file list and a tarball summary — count, size,
integrity hash. That's the last honest look at what you're shipping; read it.

It also runs a **local pre-flight scan** (`Security scan passed`). Don't confuse that
with the registry's evaluation — the local one gates your upload, the registry's runs
afterwards and gates everyone's install.

## 4. After

Evaluation is asynchronous and typically finishes in well under a minute. Poll
`forgecat view <profile>` until the four risk axes replace
`pending (not yet evaluated)`, then install it for real. Until then installs are
refused, and `--force` does nothing about it — that gate answers only to
`--allow-unevaluated`.

## 5. Recovering source (owner-only)

    forgecat clone @scope/name --out ./work   # first time
    forgecat pull --out ./work                # refresh to the registry's latest

`clone` drops a `.forgecat-source.json` beside the files recording the profile, the
version you took, and the file list. `pull` reads it to know what to refresh, and
always fetches latest by name — it is a one-way re-fetch, not a merge. `--force`
overwrites your local edits and nothing reconciles them.

Both work non-interactively with `-y`.

## 6. Taking it back

    forgecat unpublish @scope/name@0.2.0    # one version
    forgecat unpublish @scope/name          # everything — types the name to confirm
    forgecat visibility @scope/name private
    forgecat tag add|remove|list @scope/name <tags...>

Unpublishing the last remaining version archives the whole profile in the same
transaction. Already-installed copies keep working — this pulls it from the Vault,
it doesn't reach into anyone's forge.

## Verify

    forgecat view @scope/name

🐾 Marked. `name@version` is in the Vault.

Attribution

nota-americanota-america
View sourceSee grades on GitHubMore from nota-america →
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 →