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

Pm Mission Vision Tenets

ASecurity

Use when auditing, drafting, or refining Mission, Vision, and Tenets/Values statements. Applies Lencioni's four-type framework to classify existing tenets, enforces the label + 1-3 sentence best practice format, tests coherence across Mission→Vision→Tenets, and runs the "would you fire someone for this?" test. Invoke for leadership offsites, values workshops, or any tenet rewrite session.

8 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agentsgogit

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add tstapler/dotfiles --skill pm-mission-vision-tenets --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pm Mission Vision Tenets?

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

Security grade badge for Pm Mission Vision Tenets
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tstapler-pm-mission-vision-tenets/badge)](https://www.skillsdirectory.com/skills/tstapler-pm-mission-vision-tenets)

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

Download Zip
Files
SKILL.md
---
name: pm-mission-vision-tenets
description: Use when auditing, drafting, or refining Mission, Vision, and Tenets/Values statements. Applies Lencioni's four-type framework to classify existing tenets, enforces the label + 1-3 sentence best practice format, tests coherence across Mission→Vision→Tenets, and runs the "would you fire someone for this?" test. Invoke for leadership offsites, values workshops, or any tenet rewrite session.
---

# Mission, Vision & Tenets

Guides auditing and writing Mission, Vision, and Tenets using frameworks from Collins, Lencioni, and validated tech company practice (Amazon, Stripe, Netflix).

## Definitions

| Artifact | Question it answers | Lifetime |
|----------|-------------------|---------|
| Mission | Why does this org exist? | Timeless — changes only if fundamental purpose changes |
| Vision (BHAG) | Where are we going? | Finite — you know when you've achieved it |
| Tenets | How do people behave when mission is at stake? | Semi-stable — can evolve as org learns |

## Workflow

### Step 1: Classify Before You Write (Lencioni)

Run every existing or candidate tenet through the four-type test before touching language:

1. **Core** — genuinely held, you'd fire someone for violating this, you were already living it before writing it down
2. **Aspirational** — what you wish you were; belongs in strategy/OKRs, not on a values list
3. **Permission-to-Play** — ethical minimum any decent company has (honesty, respect); don't list as distinctive
4. **Accidental** — emerged from founding team personality; may or may not be worth keeping

**Fire test**: "Would you fire someone for violating this, even if their results were excellent?" If no → not core.
**Symmetry test**: "Would any legitimate company choose the opposite?" If no → baseline decency, not a distinctive value.

Only Core values belong on the final list.

### Step 2: Draft to Format

Best practice format (Amazon/Stripe validated):

1. **Label**: 3-5 words — must work as conversational shorthand in meetings
2. **Behavior sentence**: what someone who holds this value *does*, active voice
3. **Tradeoff sentence**: the uncomfortable implication, or what violation looks like
4. Optional: negative framing ("they never say X") — specificity of discomfort signals real conviction

**Rule**: 1-3 sentences. If you can't write it in 3 sentences, the team hasn't resolved it. Compression is a diagnostic.

Tone:
- Active voice ("Leaders do X" not "We believe in X")
- Specific over general ("aspire to be the world's fastest" not "we value speed")
- Include the tradeoff — good tenets make a real choice visible

### Step 3: Test Coherence

For each tenet: "Is this derivable from our Mission?"

If you removed all tenets and tried to reconstruct them from the Mission alone, would you get something close? If not — either generic (any company could claim it) or misplaced (belongs in process/strategy).

Read the full sequence aloud: Mission → Vision → Tenet 1 → Tenet 2 → ... Does it tell a coherent story?

**Collins test**: "Could a visitor drop in from another planet and infer the vision just by observing how people behave?"

### Step 4: Check Count

- Sweet spot: **5-8 tenets**
- High-credibility zone: **3-6**
- Each label must be recallable in a decision moment without looking it up
- If the full text must be read to apply the value, it hasn't been internalized

## Common Failure Modes

- ❌ One-word platitudes: "Integrity." "Innovation." "Excellence." — Lencioni explicitly names these
- ❌ Symmetric values: opposite would be repugnant = baseline decency, not distinctive value
- ❌ Lists where every item is positive and non-excludable
- ❌ Aspirational values listed as core (you aspire to be innovative but aren't yet)
- ❌ Too many: 10+ not recallable without prompting
- ❌ Too long: beyond 3 sentences loses the snap that makes tenets invokable in real decisions

## Offsite Process

**Before drafting:**
- Each leader writes independently: "3-5 things I'd never compromise on, even at competitive cost" — compare lists; convergence without coordination = discovered core value
- Collins Mars Group: "If we were rebuilding the best of this org with 5-7 seats, who goes? What do they do?"

**Time allocation (Collins):**
- 70-80% identifying misalignments — policies/behaviors that contradict claimed values
- 10-20% language drafting
- Most offsites get this backwards

## Full Framework Reference

For detailed company examples (Amazon LP format, Stripe principles, Netflix culture memo) and extended Collins/Lencioni source material, see: `reference.md`

Attribution

tstaplertstapler
View sourceMore from tstapler →
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 →