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

Drafting Partner

ASecurity

Use when co-writing a proposal, specification, report, policy or long memo through an agreed brief, outline and review. Not for code, short messages or file formatting.

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

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Drafting Partner?

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

Security grade badge for Drafting Partner
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/whq02-drafting-partner-mercurycli/badge)](https://www.skillsdirectory.com/skills/whq02-drafting-partner-mercurycli)

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

Download Zip
Files
SKILL.md
---
name: drafting-partner
description: Use when co-writing a proposal, specification, report, policy or long memo through an agreed brief, outline and review. Not for code, short messages or file formatting.
argument-hint: "<document type and purpose> [notes or draft path]"
---
# Drafting partner

## Agree the structure
- Read supplied drafts and supporting material fully.
- Record the reader, decision, outcome, length, format and deadline.
- Ask for missing constraints together; confirm the brief and current argument.
- Propose a section sequence with each section's claim or purpose.
- Incorporate the user's structural changes before drafting.

## Draft
- Follow the agreed order; lead each section with its claim.
- Pause between sections when collaboration is requested; otherwise produce the requested full pass.
- Cite factual sources, verify figures and mark unresolved claims `[confirm]`.
- Number specification requirements and acceptance criteria.
- Put proposal recommendations before options and report findings before detail.

## Review
- Run only the selected passes: argument, reader, cut, line or fact.
- Check support and objections; first-page decisions and defined terms; length; sentences and consistency; dates, names and numbers.
- Resolve or remove `[confirm]` items; record revisions and exclusions.
- Resolve `${MERCURY_SKILL_DIR}` from the supplied base directory.
- Check headings, empty sections, duplicates and length balance with `python3 "${MERCURY_SKILL_DIR}/scripts/outline_check.py" draft.md`; use `--self-test` to test the helper.
- Check the outline and final draft; deliver the agreed format.
- Use word-documents for Word output and pdf-documents for PDF output.

## Source
Checked: 2026-09-15. [User needs](https://www.gov.uk/service-manual/user-research/start-by-learning-user-needs).

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 →