New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Industry Truths

by davekilleen in davekilleen/Dex

Define time-horizoned assumptions about your industry (today / 6mo / 12mo) that ground strategic thinking.

MITAuto-check passedDevelopment

Install Industry Truths

skills CLI
$ npx skills add davekilleen/Dex --skill industry-truths -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install davekilleen/Dex industry-truths --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/davekilleen/Dex.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/industry-truths .claude/skills/industry-truths && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
industry-truths
GitHub stars
494
Token cost
~2.2k tokens
SKILL.md length
945 words
Files
1
Skills in repo
61
Repo updated
First seen
Licence
MIT

At a glance

Define time-horizoned assumptions about your industry (today / 6mo / 12mo) that ground strategic thinking.

  • Works in 5 steps: Read current Industry_Truths.md → Check dates in change log (when last… → Ask: "What's changed since you last… → …
  • The user is making roadmap
  • SKILL.md covers Execution mode, Purpose, The Problem and Usage, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Industry Truths is an agent skill from davekilleen/Dex. Define time-horizoned assumptions about your industry (today / 6mo / 12mo) that ground strategic thinking. Use when the user is making roadmap, positioning or investment calls, or says 'what am I assuming about the market'. Also use proactively before a big strategic recommendation. Not for capturing a single decision; use decision-log.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Architecture decision records. The repository describes itself as: Your AI Chief of Staff — a personal operating system starter kit that adapts to your role. No coding required. The licence is MIT.

When your agent uses it

  • The user is making roadmap
  • Investment calls
  • Says what am I assuming about the market

Example prompts

  • “what am I assuming about the market”
  • “/industry-truths”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Read current Industry_Truths.md
  2. Check dates in change log (when last updated?)
  3. Ask: "What's changed since you last updated this? New data? Assumptions proven/disproven?"
  4. Offer to update specific sections or add to change log
  5. Highlight any truths where time horizon has passed (e.g., 6-month truth from 6 months ago—was it right?)

What it can do on your machine

Read from SKILL.md and the folder at commit d0ffc6b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Industry Truths loads about 2.2k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 945 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~89
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from davekilleen/Dex at commit d0ffc6b, republished under its MIT licence (© davekilleen). 945 words, ~2,198 tokens.

Download SKILL.mdSave it as .claude/skills/industry-truths/SKILL.md (or your agent's skills folder).
name
industry-truths
description
Define time-horizoned assumptions about your industry (today / 6mo / 12mo) that ground strategic thinking. Use when the user is making roadmap, positioning or investment calls, or says 'what am I assuming about the market'. Also use proactively before a big strategic recommendation. Not for capturing a single decision; use `decision-log`.
<!-- Generated from `.claude/skills/industry-truths/SKILL.md` by `scripts/generate-agents-skills.py`. Do not edit. -->

Execution mode

Run inline in the current conversation by default, so this work can see what the user has already discussed, decided, or settled this session. Do not fork merely because this skill was selected. Only run in the background when the user explicitly asks for a background run or the host has already obtained a specific background-work approval for this run.

Purpose

In rapidly changing industries (especially AI/tech), strategic decisions require grounding in what you believe to be true at different time horizons. This skill helps you define, document, and maintain those assumptions so every ideation session and strategic conversation carries that context.

The Problem

When everything's shifting fast, it's easy to:

  • Make bets that won't age well
  • Forget key assumptions when ideating
  • Build on quicksand instead of informed beliefs
  • Lose track of what you believed vs. what actually happened

The solution: A structured file of industry truths across three time horizons (Today, 6 months, 12 months) that travels with your AI context.

Usage

  • /industry-truths — Create or update your Industry Truths file
  • /industry-truths review — Review current truths and update based on new data
  • /industry-truths validate — Compare your truths against what actually happened

Interview Flow

This is an interactive conversation, not a form. The goal is to tease out deeply held beliefs through questions, not just capture bullet points.

Opening Context

Start by explaining the concept:

Building on quicksand is expensive.

In fast-moving industries, strategic decisions need grounding in what you believe to be true at different time horizons. This skill helps you define those assumptions so they travel with every strategic conversation.

We'll explore three horizons:

  1. Today — What you believe is true right now
  2. 6 months — Emerging certainties
  3. 12 months — Strategic bets

Plus: who you track for signals (your "inferred truths" sources).

This takes about 15 minutes. Ready to start?

Section 1: Your Domain

Ask: What's your industry or domain? (e.g., "B2B SaaS," "Product Management," "AI/ML tooling," "Enterprise Sales")

Why: Context for the rest of the questions. Truths about AI tooling differ from truths about enterprise sales.

Section 2: Today's Truths

Prompt: Let's start with what you believe is true today. Not conventional wisdom—your genuine beliefs based on what you're seeing.

Guiding questions (ask 2-3, don't interrogate):

  • What's changing faster than most people realize?
  • What conventional wisdom is becoming outdated?
  • What's the new moat/advantage in your space?
  • What cost structure is shifting?
  • What's the new bottleneck/constraint?

Capture: 3-5 clear statements with brief reasoning

Example output format:

  • Cost of intelligence → zero — Open source models (Llama, DeepSeek) approaching frontier quality, forcing frontier labs into enterprise plays
  • Distribution is the only moat — Technical differentiation window shrinking to weeks
Section 3: Six Months Out

Prompt: Now let's think six months out. What do you believe will be true by [specific month 6 months from now]? These are emerging certainties—things you're reasonably confident about.

Guiding questions:

  • What complexity will be solved by then?
  • What ideas that are too expensive/hard today will become viable?
  • What adoption curve will cross a threshold?
  • What will enterprise buyers expect as table stakes?

Capture: 3-5 emerging certainties with implications

Example:

  • Agent orchestration complexity solved — When this happens, individual developers can out-compete established players
  • Token-expensive ideas become viable — Local/mobile inference reaches production quality
Show full SKILL.md (409 more words)Show less
Section 4: Twelve Months Out

Prompt: Finally, 12 months out—your strategic bets. What do you believe will be true a year from now? These might be wrong, but they're shaping your decisions today.

Guiding questions:

  • What category will dominate?
  • What pricing model will be default?
  • What team structure becomes normal?
  • What assumptions break completely?

Capture: 3-5 strategic bets with reasoning

Example:

  • Vertical AI agents dominate horizontal tools — Generic productivity loses to specialized, context-aware agents
  • Seat-based pricing dies — Usage/outcome-based becomes default
Section 5: Anti-Truths (Optional but Powerful)

Prompt: What did you used to believe that you now think is wrong? Capturing these helps track your evolving thinking.

Capture: 2-3 rejected beliefs with brief explanation

Example:

  • "AI is a feature, not a product" → Dead wrong. AI enables entirely new product categories.

File Creation

After the interview, create 04-Projects/Product_Strategy/Industry_Truths.md (or update if it exists):

markdown
---
created: [today's date]
updated: [today's date]
domain: [user's domain]
tags: [strategy, assumptions, industry-truths]
---

# Industry Truths — [Domain]

A living document of what I believe to be true about [domain] at different time horizons. These ground all strategic thinking, ideation, and investment decisions.

**Purpose:** In a world where we're building on quicksand, this file ensures I'm not forgetting key assumptions when ideating. These truths travel with the AI so we're always thinking within this context.

---

## Today (Current Reality)

[User's "today" truths with brief reasoning for each]

---

## 6 Months Out (Emerging Certainties)

[User's 6-month truths with implications]

---

## 12 Months Out (Strategic Bets)

[User's 12-month truths with reasoning]

---

## Anti-Truths (What I Used to Believe, Now Reject)

[User's rejected beliefs with brief explanation]

---

## How I Use This

1. **Before Ideation:** Review truths relevant to the problem space
2. **During Roadmapping:** Validate assumptions against time horizons
3. **Monthly Review:** Update based on new data, move items between horizons
4. **Share with AI:** Include in context for strategic conversations

---

## Change Log

### [Today's date]
- Initial version created via /industry-truths skill

Completion

After creating the file, tell the user:

✅ Created Industry_Truths.md

Dex is already configured to reference this file during strategic conversations (product decisions, roadmap planning, ideation sessions). Your truths will automatically inform future strategic thinking.

Next steps:

  • Review the file and refine as needed
  • Set a monthly reminder to update it (new data, move items between horizons)
  • Use it before strategic conversations: "Let's ideate within my industry truths"
  • Track validation: what was right, what was wrong, why?

Run /industry-truths review to update or /industry-truths validate to check past predictions.

Review Mode (/industry-truths review)

If user runs /industry-truths review:

  1. Read current Industry_Truths.md
  2. Check dates in change log (when last updated?)
  3. Ask: "What's changed since you last updated this? New data? Assumptions proven/disproven?"
  4. Offer to update specific sections or add to change log
  5. Highlight any truths where time horizon has passed (e.g., 6-month truth from 6 months ago—was it right?)

Validate Mode (/industry-truths validate)

If user runs /industry-truths validate:

  1. Read change log and time horizons
  2. For each past-due truth (e.g., 6-month truth from >6 months ago):
    • Ask: "Did this happen?"
    • Capture: Right / Wrong / Partially / Too Early
  3. Add validation notes to change log
  4. Suggest: "Want to archive validated truths and set new ones?"

Why this matters: Tracking accuracy trains your intuition about what bets to trust.

Meta Notes

This skill is:

  • A thought leadership artifact that ships as working software
  • Immediately actionable for Dex users
  • Demonstrates Dex's value as context-carrying personal OS
  • Creates compound value (truths improve every strategic conversation)

Encourage sharing: "Built my industry truths with Dex" is shareable social content

© davekilleen, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/industry-truths of davekilleen/Dex.

Open the folder on GitHubat commit d0ffc6b

Compare with similar skills

Industry Truths next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Industry Truths compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Industry Truths this skilldavekilleen/Dex494—~2.2kAutomated safety check: PassMIT
Cabloy Spec Generationcabloy/cabloy982—~3.2kAutomated safety check: NotesMIT
Bmad Architectureaj-geddes/claude-code-bmad-skills488—~1.9kAutomated safety check: NotesCustom licence
Decidecoreyhaines31/makerskills851—~1.9kAutomated safety check: PassMIT
Vibe CodingOfficeDev/microsoft-365-agents-toolkit780—~5.5kAutomated safety check: PassCustom licence
Documentation Criteriashinpr/claude-code-workflows694—~1.9kAutomated safety check: PassMIT

Similar skills

  • Cabloy Spec Generation

    cabloy/cabloy

    A skill your agent uses to create or maintain Cabloy suite specifications under repo-specs, including PRD, SRS, PDP/WBS, acceptance planning, progress, and suite ADRs.

    982 GitHub stars~3.2k tokensUpdated today
    DevelopmentAuto-check: notes

  • Bmad Architecture

    aj-geddes/claude-code-bmad-skills

    Solutioning skill (Winston, the Architect). An agent skill from aj-geddes/claude-code-bmad-skills.

    488 GitHub stars~1.9k tokensUpdated 3 mo ago
    DevelopmentAuto-check: notes

  • Decide

    coreyhaines31/makerskills

    When you have a decision to make and want a structured workflow that picks the load-bearing questions, walks through them, reaches a call (or "wait"), and archives the rationale for future reference.

    851 GitHub stars~1.9k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

  • Vibe Coding

    OfficeDev/microsoft-365-agents-toolkit

    End-to-end workflow for agent-driven changes that add or modify behavior in the toolkit packages.

    780 GitHub stars~5.5k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Documentation Criteria

    shinpr/claude-code-workflows

    Determines which of PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires, and where each is stored.

    694 GitHub stars~1.9k tokensUpdated 9 days ago
    DevelopmentAuto-check passed

  • Ad Review

    CorridorTech/PoseCap

    Two-axis fresh-context code review per WORKFLOW §10. An agent skill from CorridorTech/PoseCap.

    224 GitHub stars~2.4k tokensUpdated 4 days ago
    DevelopmentAuto-check: notes

More from davekilleen/Dex

All 61 skills in this repo

  • Dspy Ruby

    davekilleen/Dex

    This skill should be used when working with DSPy.rb, a Ruby framework for building type-safe, composable LLM applications.

    494 GitHub starsUsed in 1 repo~3.9k tokens
    Auto-check passed

  • Diff Adopt Profile

    davekilleen/Dex

    Adopt a full published Heydex profile by handle ('set me up like @davekilleen').

    494 GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed

  • Diff Generate

    davekilleen/Dex

    Package one workflow — how you use Dex for a specific job — into a shareable DexDiff methodology doc.

    494 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

  • Creating Agent Skills

    davekilleen/Dex

    Expert guidance for creating, writing, and refining Claude Code Skills.

    494 GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed

  • Feedback

    davekilleen/Dex

    Report a Dex bug to the Dex team with zero homework — Dex investigates locally, builds a privacy-safe report, shows it to you (or auto-sends if you've chosen that), and tracks the ticket until it's…

    494 GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed

  • Dhh Rails Style

    davekilleen/Dex

    This skill should be used when writing Ruby and Rails code in DHH's distinctive 37signals style.

    494 GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed

Categories

Questions about Industry Truths

What does Industry Truths do?

Define time-horizoned assumptions about your industry (today / 6mo / 12mo) that ground strategic thinking. Industry Truths is an agent skill from davekilleen/Dex. Define time-horizoned assumptions about your industry (today / 6mo / 12mo) that ground strategic thinking.

When should I use Industry Truths?

Industry Truths fits situations like: the user is making roadmap; investment calls; says what am I assuming about the market.

How do I install Industry Truths in Claude Code?

Run `npx skills add davekilleen/Dex --skill industry-truths -a claude-code`. Or copy the skill folder (.agents/skills/industry-truths in davekilleen/Dex) into .claude/skills/industry-truths in your project. Claude Code loads it when a task matches its description.

How do I install Industry Truths in Codex?

Run `npx skills add davekilleen/Dex --skill industry-truths -a codex`. Or copy the skill folder (.agents/skills/industry-truths in davekilleen/Dex) into .agents/skills/industry-truths in your project. Codex loads it when a task matches its description.

Can I use Industry Truths in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add davekilleen/Dex --skill industry-truths -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/industry-truths, .gemini/skills/industry-truths, .github/skills/industry-truths and .opencode/skills/industry-truths in your project.

What does Industry Truths need to run?

SKILL.md names no scripts, command-line tools or credentials: Industry Truths is instructions for the agent only.

Does Industry Truths access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Industry Truths safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Industry Truths use?

Industry Truths is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Industry Truths use?

About 2.2k tokens (SKILL.md is roughly 8.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Industry Truths?

Skills that share tags, products or a category with Industry Truths: Cabloy Spec Generation (cabloy/cabloy, 982 stars), Bmad Architecture (aj-geddes/claude-code-bmad-skills, 488 stars), Decide (coreyhaines31/makerskills, 851 stars) and Vibe Coding (OfficeDev/microsoft-365-agents-toolkit, 780 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Industry Truths?

davekilleen (a GitHub user) maintains it in davekilleen/Dex, which has 494 GitHub stars. The repository holds 61 skills in this directory. The repository was last updated on October 9, 2026.

Source: davekilleen/Dex on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.