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

Add Curation Action

ASecurity

Add a curation action to a charter persona — a chat the operator can open on a workspace, a persona or the plane with a prompt already typed. Use when asked to add, write or change a persona's curation action, or to give a persona a new entry in the Curate menu.

6 stars
0 votes
0 copies
0 views
Added 10/2/2026
ai-agentsbashgit

Works with

claude code

Security Analysis

A100/100

Scanned 10/2/2026

$npx -y skills add diazoxide/charter --skill add-curation-action --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Add Curation Action?

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

Security grade badge for Add Curation Action
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/diazoxide-add-curation-action/badge)](https://www.skillsdirectory.com/skills/diazoxide-add-curation-action)

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: add-curation-action
description: Add a curation action to a charter persona — a chat the operator can open on a workspace, a persona or the plane with a prompt already typed. Use when asked to add, write or change a persona's curation action, or to give a persona a new entry in the Curate menu.
---

# Adding a curation action

A **curation action** is a chat the operator opens from a workspace, a persona or the plane,
with a prompt already typed into it. The operator reads the prompt and presses Enter; nothing
sends it for them. The persona that declares the action is the one that runs it.

Each is one file, `personas/<persona>/curation/<id>.md`:

```markdown
---
label: Review open work
on: workspace
runs-in: subject
---

Use the review skill on the workspace {subject.name}.
```

- `label` — what the menu shows. Required, one line.
- `on` — the kinds of subject it is offered on: `workspace`, `persona`, `plane`, comma-separated.
  Required.
- `runs-in` — `subject` (the workspace's directory, `personas/<name>/`, or the plane root) or
  `plane`. Without it, a workspace action runs in the workspace and the others at the plane
  root.
- The body is the prompt. It may use exactly four variables: `{subject.kind}`,
  `{subject.name}`, `{subject.path}` and `{plane.root}`. They are filled in as plain text;
  any other `{word}` is an error.

## 1. Ask what it is for

Ask the operator what the chat should do, which subjects it belongs on, and where it should
run. Draft the prompt as the operator would want to read it before pressing Enter: **one short,
plain line** that says what to do and on which subject. When the work has steps, put them in a
skill and name the skill in words in that line — never as a `/slash` command, which only one
harness reads.

Keep it short because the harness shows a long paste as a placeholder nobody can read, and
charter then opens no chat for it: Claude Code over 800 characters or at 4 lines, Codex over
1,000 characters. `charter persona lint` warns when a prompt, filled in for a long subject name,
would be shown that way. Done when the operator approves the label, the kinds and the prompt.

## 2. Write it

```bash
charter persona curation add <persona> <id> --label "<label>" --on workspace,persona [--runs-in plane] <<'PROMPT'
<the prompt>
PROMPT
```

`<id>` is lowercase letters, digits, `.`, `_` and `-`. The command writes the file only when it
reads back with no error, and never over one that is there: to change an action, remove it and
add it again.

```bash
charter persona curation remove <persona> <id>
```

charter's own actions are `charter/safe-remove`, `charter/compact` and
`charter/add-curation-action`. A persona's action with one of their ids or labels is refused,
so choose another.

## 3. Check it

```bash
charter persona curation list <persona>
charter curation show workspace:<name>     # or persona:<name>, or plane
charter persona lint <persona>
```

`curation show` prints what a subject is offered, in order, each with who runs it, where, and
the prompt as it will be typed. Show the operator what `curation list` says. Done when the new
action is listed there with no warning, and `persona lint` has no warning about it. The
file is committed with the persona and travels with the plane's next save.

Attribution

diazoxidediazoxide
View sourceSee grades on GitHubMore from diazoxide →
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', ...

698621 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 →