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

Dr Capture Request

ASecurity

Record an operator's suggested change verbatim and split it into numbered requirements (REQUEST.md). First phase of every change tranche; no interpretation, no code reading.

142 stars
0 votes
0 copies
0 views
Added 9/19/2026
documentationgo

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add AHepi/DeepReason --skill dr-capture-request --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Dr Capture Request?

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

Security grade badge for Dr Capture Request
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ahepi-dr-capture-request/badge)](https://www.skillsdirectory.com/skills/ahepi-dr-capture-request)

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

Download Zip
Files
SKILL.md
---
name: dr-capture-request
description: Record an operator's suggested change verbatim and split it into numbered requirements (REQUEST.md). First phase of every change tranche; no interpretation, no code reading.
---

# Capture the request

Input: the operator's message(s). Output: `REQUEST.md`. You quote; you
do not paraphrase, improve, or fill gaps. Interpretation happens in
`dr-spec-change`, where it is visible and reviewable — not here, where
it would silently replace the operator's words.

## Procedure

1. Copy the operator's suggestion VERBATIM into a quoted block. If the
   suggestion spans several messages (including earlier in the
   conversation), quote each with its position. Do not trim "context"
   — trimmed context is how inputs get forgotten.
2. Split into atomic requirements R1..Rn. Atomic = one testable
   obligation each. Split conjunctions ("do X and then Y" → R1: X,
   R2: Y). Keep the operator's own words in each requirement; add
   nothing.
3. Capture constraints stated anywhere in the conversation that bind
   this change (deadlines, "don't touch X", style preferences, budget
   remarks like "prioritise this"). These become C1..Cn with verbatim
   quotes.
4. Mark each requirement's kind: `behavior` (code must act
   differently), `artifact` (a file/document/skill must exist),
   `process` (how the work must be done, e.g. "commit as you go").
5. List open questions Q1..Qn — places where the words genuinely
   underdetermine the work. Do NOT answer them here.

## REQUEST.md template

    # Request: <operator's own headline words>
    Captured: <date> from <operator message position(s)>

    ## Verbatim
    > <exact quote(s)>

    ## Requirements
    R1 (<kind>): "<operator's words for this obligation>"
    R2 (<kind>): ...

    ## Standing constraints
    C1: "<verbatim>" — <where stated>

    ## Open questions (for dr-spec-change)
    Q1: <what the words leave undetermined>

    ## Amendments
    (append-only; later operator messages land here as R<n+1>... or
    "R2a supersedes R2", each with its verbatim quote)

## Exit criteria

- REQUEST.md committed and pushed.
- Zero interpretation performed: every R and C contains a quote.
- Return to the orchestrator.

Attribution

AHepiAHepi
View sourceMore from AHepi →
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

Context Fundamentals

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.

179001 votes

release-notes

Draft release notes and changelog entries from git history or merged PRs between two refs (tags/SHAs/branches), including breaking changes, migrations, and upgrade steps. Use when the user asks for release notes, changelog updates, or a GitHub Release draft.

1301 votes

docs-style-guide

Documentation style guide enforcer by @planetabhi. Applies and reviews the writing style guide when authoring or editing product documentation and tutorials. Use to check prose for voice, tense, word choice, inclusive language, formatting, code block, UI, Markdown, and number/date conventions.

11 votes

Caveman Help

Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".

1023330 votes

How It Works

Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".

929660 votes
View all in documentation →