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

Jargon

ASecurity

/iceberg:jargon — Build and manage the jargon list that /iceberg:edit removes and /iceberg:score flags (Rule 18). Pick an industry pack (technology, finance, marketing, corporate, legal), name your own words, or both. Writes .iceberg/jargon.txt. Trigger on: /iceberg:jargon, "drop these words", "ban these words", "remove jargon words", "my jargon list", "add <word> to the jargon list", "jargon for <industry>". Never writes the list without the user's confirmation.

8 stars
0 votes
0 copies
0 views
Added 10/6/2026
ai-agentsgo

Security Analysis

A100/100

Pro scans all 6 files and shows the line behind each finding

Scanned 10/6/2026

$npx -y skills add gagoar/iceberg --skill jargon --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Jargon?

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

Security grade badge for Jargon
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/gagoar-jargon/badge)](https://www.skillsdirectory.com/skills/gagoar-jargon)

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: jargon
description: >
  /iceberg:jargon — Build and manage the jargon list that /iceberg:edit removes and
  /iceberg:score flags (Rule 18). Pick an industry pack (technology, finance, marketing,
  corporate, legal), name your own words, or both. Writes .iceberg/jargon.txt.

  Trigger on: /iceberg:jargon, "drop these words", "ban these words", "remove jargon words",
  "my jargon list", "add <word> to the jargon list", "jargon for <industry>".

  Never writes the list without the user's confirmation.
argument-hint: "[industry | add <term> [=> replacement] | remove <term> | --show | --packs]"
allowed-tools: Read, Write, Glob, AskUserQuestion
---

# Iceberg Jargon List

Manages `.iceberg/jargon.txt` in the current working directory. Once the file exists, `/iceberg:edit` and `/iceberg:score` apply it automatically as Rule 18.

## List file format

```
# comments start with #
@pack finance            # pulls in a bundled pack
!synergy                 # keep the pack, but allow this one word
leverage => use
touch base               # bare entry: delete the phrase and repair the sentence
move the needle => improve <metric>
```

- One entry per line. `term => replacement` replaces. A bare `term` deletes.
- `@pack <name>` includes every entry from a bundled pack.
- Matching ignores case and covers whole words and phrases. Inflections match too: `leverage` also matches *leveraged* and *leveraging*.
- `!term` drops a term that a pack brought in. Use it to keep a pack but allow one word.
- If a term appears twice, the later line wins. A line in the user file therefore overrides the same term from a pack.

## Finding the bundled packs

Packs live at `skills/jargon/packs/<name>.txt` inside the plugin. Try `${CLAUDE_PLUGIN_ROOT}/skills/jargon/packs/<name>.txt` first. If that path does not resolve, Glob for `**/skills/jargon/packs/<name>.txt`. Bundled packs: `technology`, `finance`, `marketing`, `corporate`, `legal`.

## Modes

### No argument — interview

1. Ask which industry with AskUserQuestion. Offer the bundled packs. "Other" is always available.
2. Read the chosen pack and show its entries.
3. Ask which entries to keep, or whether to include the whole pack with `@pack <name>`.
4. Ask for extra words, one per line, with optional `=> replacement`.
5. Show the final file. Write `.iceberg/jargon.txt` only after the user confirms. Create `.iceberg/` if needed.

If `.iceberg/jargon.txt` already exists, read it first and offer to extend it. Never overwrite it silently.

### `<industry>` with no matching pack

Draft 30–50 entries for that industry in the file format. Prefer a plain replacement. Use a bare entry only when deletion is the right fix. Skip common words that would corrupt ordinary prose, such as *such*, *same*, *stack*, or *material*.

Show the draft and let the user cut or edit entries. After confirmation, save the entries literally. Do not write `@pack`, because no pack exists. The saved list stays fixed between runs.

### `add <term> [=> replacement]` and `remove <term>`

Edit `.iceberg/jargon.txt` in place. Create it if it does not exist (for `add`). For `remove`, delete the matching line. If the term comes from an `@pack`, add a `!term` line to the user file instead, and say so.

### `--show`

Print the merged list: packs first, then user-file entries, with later entries replacing earlier ones. Show the entry count.

### `--packs`

List each bundled pack with its entry count and three sample entries.

## Rules

- Never write or change the list without the user's confirmation, except `add` and `remove`, which the user asked for directly.
- Do not add entries the user did not choose.
- Entries are matched in prose only. Code blocks, inline code, URLs, and proper nouns are never touched.

Attribution

gagoargagoar
View sourceSee grades on GitHubMore from gagoar →
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 →