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

Intake

ASecurity

Run slice intake as a live discussion under the product expert's contract, then record the owner's request and decisions verbatim as an intake-decision record. Load when the user brings a feature request for discussion or invokes /intake.

16 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agentspythongogit

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add woditschka/agentic-coding-reference --skill intake --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Intake?

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

Security grade badge for Intake
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/woditschka-intake-195c37e3/badge)](https://www.skillsdirectory.com/skills/woditschka-intake-195c37e3)

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

Download Zip
Files
SKILL.md
---
name: intake
description: >-
  Run slice intake as a live discussion under the product expert's contract,
  then record the owner's request and decisions verbatim as an intake-decision
  record. Load when the user brings a feature request for discussion or
  invokes /intake.
compatibility:
  - claude-code
  - github-copilot
  - opencode
reads:
  - docs/prd.md
metadata:
  version: "1.0"
  author: team
---

# Intake

The intake discussion runs in the current root session under the product expert's judgment contract — no clearing, no fresh session, no dispatch while the discussion is live. The exit appends one `intake-decision` record: the owner's request and decisions, quoted verbatim. Root records the discussion's outcome; it never authors a product statement — the `product-requirements-expert` dispatch that follows grounds the slice in the record's quotes, not in root's memory of the chat.

Headless runs skip the discussion and seed the same record from the task prompt's decision clauses (`source: "task-prompt"`). Both front doors produce one contract; everything downstream is identical.

## Instructions

1. **Adopt the contract.** Load the `prd-authoring` skill and hold the product expert's judgment for the discussion: the PRD boundary, the non-goal discipline, the slice-sizing rule. When the discussion turns structural (trade-offs, integration, feasibility), also load `design-validation` and hold both. Skills ship on every channel; the specialists' write scopes stay theirs.
2. **Run the discussion** under the elicitation doctrine in [`agentic-harness.md`](../handoff-routing/agentic-harness.md) § Conversations Stay in Root: push back asymmetrically, hold once, surface every contradiction, own the stop.
3. **Name the exit** and let the owner confirm it. *Resolved* proceeds to steps 4–6. *Out of scope for this slice* leaves the question open — it resurfaces as a `consultation-request` if implementation needs it.
4. **Mint the `req_id`.** A `next`-triaged pick carries its REQ; otherwise take the next free `REQ-XX-NNN` per the `docs/prd.md` conventions (`prd-authoring` skill).
5. **Record the intake.** Append one `intake-decision` record via `python3 scripts/handoff.py append` (`handoff-append` skill). Fields: `author: "human"`; `request` — the owner's request, quoted verbatim; `decisions` — each decision the owner stated, quoted verbatim; `source: "intake-discussion"`; `notes` — points the owner deliberately left unsettled. Only `decisions` text can authorize a scope override at Gate 1; the request is context, never authority. Schema: `schemas/scratch/intake-decision.schema.json`.
6. **Route.** Run `python3 scripts/handoff.py route`. The `intake-ready` decision dispatches `product-requirements-expert`; its prompt names the record, never restates it.

## Rules

- A quote is the owner's words. When a position emerged in discussion but the owner never stated it compactly, ask the owner to state the decision and quote the answer — a distillate is authorship, not relay.
- A decision the owner has not stated is an open question, never a `decisions` entry.
- The record binds the human, never the specialist: the product expert judges the quoted intake cold against the PRD and may push back via a `consultation-request` targeting `human`.
- One record per intake exit. A re-opened discussion ends in a fresh `intake-decision`; the latest record governs.

Attribution

woditschkawoditschka
View sourceMore from woditschka →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 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.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 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 →