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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Buy In

ASecurity

The buy-in doc — a ship-readiness pitch that leads with a working demo, pre-answers reviewer objections with evidence, states limitations, and names who must sign off. Use when the user says "buy-in doc", "prep me for review", or before requesting review/approval/merge.

2 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsrustreact

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add ajitta/know-your-unknowns --skill buy-in --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Buy In?

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

Security grade badge for Buy In
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ajitta-buy-in/badge)](https://www.skillsdirectory.com/skills/ajitta-buy-in)

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

Files
SKILL.md
---
name: buy-in
description: >
  The buy-in doc — a ship-readiness pitch that leads with a working demo, pre-answers
  reviewer objections with evidence, states limitations, and names who must sign off.
  Use when the user says "buy-in doc", "prep me for review",
  or before requesting review/approval/merge.
argument-hint: "[target work/PR] [audience: team/reviewers]"
---

# Buy-in — Reviewer Persuasion Doc (The Buy-In Doc)

Implementation done, but **others' approval** remains an unknown. Know what reviewers
will ask in advance — it becomes known.
the **quiz** skill validates **my understanding**;
buy-in prepares **others' trust**.
Origin: The Buy-In Doc — see skills/loop/references/talk-source.md.

## Procedure

1. From `$ARGUMENTS`, identify target work and audience (reviewers, team, decision-makers).
   No arguments → this session's implemented work, audience = reviewers.
   Inputs: the plan/spec, the prototype, and IMPLEMENTATION_NOTES.md.
2. **Demo first**: working result at top of doc — execution output, screenshot/GIF,
   interactive demo operable inside the doc if possible. Target read time: 90 seconds.
3. **Preempt objections**: anticipate ~5 questions/objections reviewers would raise,
   answer each with **evidence**, and give every answer a reference the reviewer can
   follow (spec §, IMPLEMENTATION_NOTES.md entry date, metric, test run, file:line).
   No unsupported rebuttals — no evidence, move it to limitations.
4. **Spec at a glance**: area / decision / ref table, one row per settled decision.
5. **Known limitations and unresolved unknowns**: if a deviation log exists (file or in-conversation),
   pull recorded deviations and unresolved risks here. Not hiding is the basis of trust.
6. **Sign-off list**: name people/teams needing to approve, with roles, and assign
   what each must check.
7. **Rollback plan**: one paragraph on how to revert if things break.

## Output

Ladder: Artifact tool → `.unknowns/<YYYY-MM-DD>-buy-in-<slug>.html` → markdown, same
structure (use markdown directly when the target is a PR body).
Reaction control = sign-off checklist, one checkbox per approver item; assembles into a
review-comment draft ("Reply with a ✓ on your piece").
Details: skills/loop/references/output-routing.md

## Integration

- Run the **quiz** skill before writing — work the user can't explain can't be
  defended in a buy-in doc either.
- The `unknowns:independent-reviewer` agent (spawned with the Agent tool) produces the
  strongest evidence for objection responses, including its "verified" list. Without the
  Agent tool, use the fresh-thread substitute in `skills/loop/references/surfaces.md` —
  and never present an unreviewed doc as reviewed.

Attribution

ajittaajitta
View sourceMore from ajitta →
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".

1074701 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', ...

695601 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.

691 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 →