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 Case Study Paragraph

ASecurity

Writes a Case Study Paragraph for a proposal, 120 to 180 words of challenge, action and result matched to this client's situation without bending the facts, a 40-word version, the permission status and results only as the past client approved them. Use for "run disc-case-study-paragraph", "case study paragraph", "add a case to the proposal", "relevant experience", "proof for this proposal", "short case for the RFP", "which past project fits", part of the Claude for Winning Proposals Pack by P...

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

Works with

cli

Security Analysis

A100/100

Scanned 10/5/2026

$npx -y skills add polar-bear-org/claude-skills --skill disc-case-study-paragraph --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Disc Case Study Paragraph?

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

Security grade badge for Disc Case Study Paragraph
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-disc-case-study-paragraph/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-disc-case-study-paragraph)

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-case-study-paragraph
description: Writes a Case Study Paragraph for a proposal, 120 to 180 words of challenge, action and result matched to this client's situation without bending the facts, a 40-word version, the permission status and results only as the past client approved them. Use for "run disc-case-study-paragraph", "case study paragraph", "add a case to the proposal", "relevant experience", "proof for this proposal", "short case for the RFP", "which past project fits", part of the Claude for Winning Proposals Pack by Polar Bear.
---

# Case Study Paragraph

## When To Use
The proposal needs proof a model cannot generate, and only your real work counts. A new prospect is asking, quietly, "have they done this before, for someone with our problem?" You have past work that fits and need it written short, honestly and in a form you are allowed to share.

## When Not To Use
If you do not yet know which proof the proposal needs, start with Win Themes. If you have no past work that honestly mirrors this client, say so in the Consulting Proposal and offer a smaller first phase instead of a stretched case.

## Inputs
- Your notes on the past project: the situation, what you did, what changed, in your words or the past client's
- The results as the past client approved them, and what they agreed to (named, anonymised, not asked)
- This client's situation in three lines, and where the paragraph sits in the proposal
If you have none of this, I run five short questions on the past project and mark the paragraph "first draft, permission not confirmed".

## Approach
Challenge, action, result is a practitioner convention, described here generically. The paragraph matches the prospect by selection, never by alteration: it chooses which true detail to lead with and says the rest less. The trap is the mirror, bending a past project until it describes one that did not happen. A prospect who asks one follow-up question about a bent case stops trusting the whole proposal.

## Workflow
1. Ask at most three questions: which past project you have in mind, what the past client agreed to (named and approved, anonymised and approved, or not yet asked), and what this prospect most needs to recognise.
2. Challenge, one or two sentences: the past client's situation by role and problem ("a past client's operations lead faced [problem]"). No size, sector or type unless the past client approved that detail and you insist on it.
3. Action, two or three sentences: what you did, specific, including the turn that changed direction. Name no past-client staff without permission.
4. Result, one or two sentences: only as approved, with base and period where the past client gave them. Without approval, a [placeholder] and "ask". A delivered piece of work with no measured outcome says what was delivered and stops.
5. Bridge, one sentence: what you would do the same way for this client, as an intent, never a promise of the same result.
6. Trim to 120 to 180 words, then write a 40-word version from the challenge and result sentences.
7. If permission is "not yet asked", draft a short request to the past client for you to send, stating exactly which words and figures would appear.

## Output Format
```markdown
# Case Study Paragraph
**Past project:** [internal name] | **Written for:** [prospect role and need] | **Date:** [date]
## Permission status
[Named and approved / Anonymised and approved / Not yet asked], confirmed by [past client role] on [date]
## Paragraph (120 to 180 words)
[Challenge] [Action] [Result as approved] [Bridge as intent]
## Short version (40 words)
[Challenge and result in 40 words]
## Sources
| Statement | Source | Approved for use |
|---|---|---|
| [result line] | [notes, email, date] | [yes, no, ask] |
## Permission request draft (if not yet asked)
[Short note for you to send, listing the exact words and figures]
## Decision
[You] confirm the permission status and the result line with the past client before [proposal send date].
```

## Done When
- Every statement traces to your notes and every result to the past client's approval
- The prospect's situation shaped the order of details, not the facts
- Both lengths are within their word limits and the permission status is stated

## Quality Bar
- Past client described by role and problem, never by size, sector or type unless approved
- One result with base and period, or none; never "results like these" or "typically"
- The bridge is an intent, never a promise of the same outcome
- Only real work, results as approved; Claude never invents a reference or a result

## Next
Run disc-ai-use-statement (AI Use Statement) to say plainly how AI is used in the work.

## 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 →