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
  • 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.

Back to skills

Skill Forge

ASecurity

Use when authoring, packaging or debugging a Mercury skill and its discovery description. Not for session capture via /skillify, agent definitions, hooks or extension packaging.

6 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentspythondebugginggit

Works with

cli

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add Whq02/MercuryCLI --skill skill-forge --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Skill Forge?

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

Security grade badge for Skill Forge
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/whq02-skill-forge/badge)](https://www.skillsdirectory.com/skills/whq02-skill-forge)

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

Download Zip
Files
SKILL.md
---
name: skill-forge
description: Use when authoring, packaging or debugging a Mercury skill and its discovery description. Not for session capture via /skillify, agent definitions, hooks or extension packaging.
argument-hint: "<skill name or path> [purpose]"
---
# Skill forge

## Locate
- Put `SKILL.md` in a lowercase, hyphenated skill directory.
- Use `<project>/.mercury/skills/<name>/` for project scope, the config home's `skills/<name>/` for user scope, or a declared extension skill directory.
- Account for bundled-name precedence; otherwise the first loaded name wins.
- Keep supporting material in `references/` and offline helpers in `scripts/`.

## Define
- Set `name` to the directory name and supply `description`.
- Start the description with the task and `Use when`; put the exclusion second.
- Keep routing information within the first 250 characters and the whole description within 1,000.
- Add `when-to-use` only for distinct triggers; use `argument-hint` for invocation syntax.
- Set `disable-model-invocation: true` for user-only invocation; set `user-invocable: false` to hide slash completion.
- Use `allowed-tools`, `model` and `effort` only when their overrides are needed; verify model IDs against the live catalogue.
- For skills that deploy, delete, post or pay, require user invocation and describe the effects before execution.

## Write
- Put the procedure first; keep the body within 250 lines.
- Link references at the decision that needs them; do not duplicate their content.
- State how supplied arguments and omitted arguments affect the procedure.
- For disk skills, use `$ARGUMENTS` for invocation arguments and `${MERCURY_SKILL_DIR}` for local paths.
- For bundled skills, resolve helper paths from the supplied base directory; bundled arguments are appended to the body.
- Preserve required steps when cutting an existing skill; remove repetition and unsupported claims.

## Check
- Resolve `${MERCURY_SKILL_DIR}` from the supplied base directory.
- Lint names, frontmatter, description, paths and body size with `python3 "${MERCURY_SKILL_DIR}/scripts/skill_lint.py" <skill-directory>`; use `--self-test` to test the helper.
- Give each helper an offline `--self-test`; run it.
- Invoke the skill on a representative request and confirm the intended body loads.

## Source
Checked: 2026-09-15. [Mercury skill implementation](https://github.com/Whq02/MercuryCLI/tree/fc81e29e4129a56b1bfb3beca9819ebfb29875f9/src/skills).

Attribution

Whq02Whq02
View sourceMore from Whq02 →
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".

1066601 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', ...

686011 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.

651 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 →