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

Business Pr Release

ASecurity

Write the tier-3 one-page announcement — figures drawn only from the public case study, denominators attached, limitations one-liner included

3 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsbash

Works with

claude code

Security Analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned 10/4/2026

$npx -y skills add tony/skills --skill business-pr-release --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Business Pr Release?

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

Security grade badge for Business Pr Release
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tony-business-pr-release/badge)](https://www.skillsdirectory.com/skills/tony-business-pr-release)

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: business-pr-release
description: >-
  Write the tier-3 one-page announcement — figures drawn only from the
  public case study, denominators attached, limitations one-liner included
disable-model-invocation: true
allowed-tools: ["Bash", "Read", "Write", "Grep", "AskUserQuestion"]
metadata:
  argument-hint: "[run directory]"
  source: "plugins/business/skills/pr-release/SKILL.md"
---

# PR Release (tier 3)

Derive a one-page announcement from the public case study — and only
from it. The public case study is the sanitization firewall: this
command introduces no figure that is not already in it and re-derives
nothing from the interim package. Value is engineer-hours, cycle
time, and capacity; never money.

Read `references/interim-format.md` first — it
defines run location. Defer these until the firewall (the public case
study) is located:

- `references/provenance.md` — tag rendering,
  denominators, the no-currency contract.
- `references/audiences.md` — the tier-3
  contract.

User arguments: $ARGUMENTS

## Procedure

### 1. Locate the run

Use the `$ARGUMENTS` path if given, else the newest run per
`interim-format.md`. Confirm the choice with the user.

### 2. Locate and verify the firewall

Check for `<run>/reports/case-study-public.md`. If it is missing,
ask via `ask-user-choice` whether to run
the `business-case-study-public` skill now or stop — never draft the release
straight from the interim package. If present, run the firewall
sweep from `audiences.md`; a sweep failure routes back to
the `business-case-study-public` skill, never into hand-patching here.

### 3. Compose one page

Read the deferred references above. From the public case study only:

1. **Headline result** — the case study's headline, with its tag
   and range.
2. **Supporting numbers** — two or three, each with its denominator
   and window length, exactly as they appear in the case study.
3. **Quote placeholder** — clearly marked as a placeholder, with
   attribution left blank for the user to fill.
4. **Limitations one-liner** — a single candid sentence distilled
   from the case study's limitations section.

Write `<run>/reports/pr-release.md`.

## Rules

- Every figure must be traceable to the public case study verbatim
  or by stated rounding; if a wanted figure is not there, the answer
  is to extend the case study first, not to reach into the run.
- The tier-3 contract in `audiences.md` applies in full — no
  internal identifiers, no currency.

## Output

Open with a one-line hero (`✓ PR release: <headline>`,
`✓ Evidence report: <supported claim, unknowns named>`, or
`⚠ Blocked: <reason>`), then exactly these sections:

1. `## Run` — the run chosen.
2. `## Firewall` — the public case study used, and confirmation
   that every figure traces to it.
3. `## Report` — where it was written and the headline.

End with an `ask-user-choice` panel: revise the headline, regenerate
after updating the case study, or stop. Skip the panel in plan mode
or when running non-interactively.


## Portability notes

- `ask-user-choice` — present the listed options and wait for the user to pick one. Hosts with a structured multiple-choice tool (Claude Code's `AskUserQuestion`) should use it; otherwise print a numbered list and wait for a numbered reply. Never proceed on an assumed answer.
- `$ARGUMENTS` — the text the user passed when invoking this skill. If your host does not substitute it, read it as the user's request in the current turn, and ask when there is none.
- Bundled files — every relative path in this skill points at a file shipped inside this skill directory. Read them from here, not from the host's plugin tree.

Attribution

tonytony
View sourceSee grades on GitHubMore from tony →
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', ...

698431 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 →