Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Disc Consulting Proposal

ASecurity

Writes a short answer-first Consulting Proposal from your notes and files, with the recommended option and the decision asked at the top, their problem in their words, outcomes, approach, three options, proof, your AI use statement and a dated next step. Use for "run disc-consulting-proposal", "write the proposal", "draft a consulting proposal", "turn my notes into a proposal", "a proposal they can read in five minutes", "short proposal they can forward", "answer-first proposal", part of the ...

2 stars
0 votes
0 copies
0 views
Added 10/5/2026
ai-agentsrustgo

Works with

cli

Security Analysis

A100/100

Scanned 10/5/2026

$npx -y skills add polar-bear-org/claude-skills --skill disc-consulting-proposal --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Disc Consulting Proposal?

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

Security grade badge for Disc Consulting Proposal
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-disc-consulting-proposal/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-disc-consulting-proposal)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: disc-consulting-proposal
description: Writes a short answer-first Consulting Proposal from your notes and files, with the recommended option and the decision asked at the top, their problem in their words, outcomes, approach, three options, proof, your AI use statement and a dated next step. Use for "run disc-consulting-proposal", "write the proposal", "draft a consulting proposal", "turn my notes into a proposal", "a proposal they can read in five minutes", "short proposal they can forward", "answer-first proposal", part of the Claude for Winning Proposals Pack by Polar Bear.
---

# Consulting Proposal

## When To Use
You need a proposal the client can read in five minutes and forward internally, to people who were never on the call. Discovery is done, the problem is confirmed and the options are shaped. It answers: what are we recommending, why does it fit their problem, and what do we need them to decide by when?

## When Not To Use
If the signer will read one page only, write the Proposal Executive Summary. If the client has said yes and needs contract-ready detail, use Statement of Work; the proposal persuades, the SOW defines.

## Inputs
- Your problem statement, call notes (with verbatim lines marked) and the recap email the client confirmed
- Your three options with prices from your own price list, and the scope with its won't list
- Proof you have (case paragraphs, past work you may cite), team bios you supply, and your AI use statement
If you have none of this, I start from your call notes and the option you favour, leave every gap as a [placeholder], and mark the output as a first draft.

## Approach
The structure is the Pyramid Principle with situation, complication, question, from Barbara Minto (barbaraminto.com): the answer goes first, and every section below supports the one above it. Answer-first can read as arrogant before trust exists, so the answer sits on top of their problem told in their own words, never on top of your credentials. The failure it prevents: three pages about your firm before the client finds their own problem on page four, then silence.

## Workflow
1. Ask at most three questions: who will read it beyond your contact, which option you recommend and why, and how long it may be (default: readable in five minutes).
2. Write the top first: the recommended option, the outcome it buys and the decision asked, with a date. If you cannot write these three lines, the proposal is not ready, and I say what is missing.
3. Situation, complication, question in the client's words. Situation is what they already accept; complication is what changed or is at stake; question is what they must decide. Quotes come only from the verbatim bin of your notes.
4. Outcomes, then approach, then the three options side by side. Outcomes are results in their measures; the approach shows phases and what they see at the end of each; options carry your prices only.
5. Proof and team after their problem, never before it. Proof comes from your files; bios only as you supply them. Then your AI use statement, unedited in substance.
6. Pyramid check, line by line: does each sentence support the one above it, and does it trace to your notes or files? Anything that does neither is cut or marked [source needed].
7. Draft in Claude Docs (beta, paid plans) if you use it, or as a plain document you export to docx. You read it, edit it and send it yourself.

## Output Format
```markdown
# Consulting Proposal
**For:** [client role and organisation] | **From:** [you] | **Date:** [date]
## Our recommendation
[Option name]: [outcome it buys]. We ask you to decide [what] by [date].
## Where you are and what is at stake
- Situation: [what they accept, their words, source]
- Complication: [what changed, their figures only, source]
- The question: [what they must decide]
## What you get and how we will work
- Outcome: [result in the client's measure, source] | Phase: [what happens] then [what you see at the end]
## Three options
| | [Option A] | [Option B] | [Option C] |
|---|---|---|---|
| Outcome and scope | [ ] | [ ] | [ ] |
| Leaves out | [ ] | [ ] | [ ] |
| Price | [your price] | [your price] | [your price] |
## Proof, team and how we use AI
[Case paragraph, permission status] | [Team member, role, bio as supplied] | [Your AI use statement]
## Decision
[Client decision maker] chooses an option by [date]; [you] send this proposal and propose [next step] on [date].
```

## Done When
- The recommendation and the decision asked with a date are in the first lines
- Their problem appears before any line about your firm
- Every figure, quote and result traces to your notes or files, or is a [placeholder]

## Quality Bar
- Their words are marked as theirs only when they come from your notes or a consented transcript
- Prices are yours; options differ by outcome, with no decoy
- AI use is stated plainly, never hidden or minimised
- Short beats complete; a section with nothing true to say is cut
- Facts only from your notes and files; no invented reference, result or quote; you send it

## Next
Run disc-win-themes (Win Themes) to sharpen what makes this proposal yours.

## About the makers

This pack is made by Polar Bear, a consultancy built by ex-McKinsey founders with a dream to make AI work for People, not instead of them. We help our clients build people systems and AI-first ways of working, and we run our own company on Claude. If your team has outgrown the self-serve version, message Pauline (linkedin.com/in/paulinebertry).

Attribution

polar-bear-orgpolar-bear-org
View sourceSee grades on GitHubMore from polar-bear-org →
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

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 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', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 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.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, 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.

741 votes
View all in ai-agents →