Agent skill

Cross Industry

by acogood in acogood/diffmode_free

Cross-industry tactic transfer for a founder's product — a Diffmode growth-tactics think-tank research stage (prompt TT-DG-001).

Apache-2.0Auto-check passedProduct & Project Management

Install Cross Industry

skills CLI
$ npx skills add acogood/diffmode_free --skill cross-industry -a claude-code

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

GitHub CLI
$ gh skill install acogood/diffmode_free cross-industry --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/acogood/diffmode_free.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugin/skills/cross-industry .claude/skills/cross-industry && 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
cross-industry
GitHub stars
163
Token cost
~2.6k tokens
SKILL.md length
972 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
Apache-2.0

At a glance

Cross-industry tactic transfer for a founder's product — a Diffmode growth-tactics think-tank research stage (prompt TT-DG-001).

  • Works in 5 steps: What was the MECHANISM? The universal… → Why did it work in THAT context? Which… → Context-specific vs transferable —… → …
  • Running the demand-gen think-tank stages cross-industry dimension
  • SKILL.md covers Inputs & Output, Invocation, Scope (CRITICAL) and Procedure, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Cross Industry is an agent skill from acogood/diffmode_free. Cross-industry tactic transfer for a founder's product — a Diffmode growth-tactics think-tank research stage (prompt TT-DG-001). Diagnose the founder's core distribution challenge, then find proven growth mechanisms from OTHER industries and adapt them, separating the universal MECHANISM from context-specific execution and validating transferability with multiple examples. Document 10-15 case studies plus transferable patterns — including controversial/dark-pattern tactics — with effort/effectiveness/risk…

Its SKILL.md is about 2.6k 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 Product & Project Management, covering Prioritization frameworks. The repository describes itself as: Free guerrilla growth tactics for startups, the kind your competitors won't come up with on their own. Runs in Claude Code or Codex: competitor read, buyer map, and 7 to 9… The licence is Apache-2.0.

When your agent uses it

  • Running the demand-gen think-tank stages cross-industry dimension
  • Tasks that involve Prioritization frameworks

Example prompts

  • “/cross-industry”

Workflow steps

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

  1. What was the MECHANISM? The universal psychological/technical principle (e.g.
  2. Why did it work in THAT context? Which contextual factors enabled it.
  3. Context-specific vs transferable — separate the two explicitly.
  4. What must CHANGE to adapt it to the founder's context.
  5. Critical analysis — causation vs correlation; how many tried it and failed; role of

What it can do on your machine

Read from SKILL.md and the folder at commit c175a4d. 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

Cross Industry loads about 2.6k tokens when it runs. Until then it costs about 192 tokens; SKILL.md has 972 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~192
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k

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 acogood/diffmode_free at commit c175a4d, republished under its Apache-2.0 licence (© acogood). 972 words, ~2,630 tokens.

Download SKILL.mdSave it as .claude/skills/cross-industry/SKILL.md (or your agent's skills folder).
name
cross-industry
description
Cross-industry tactic transfer for a founder's product — a Diffmode growth-tactics think-tank research stage (prompt TT-DG-001). Diagnose the founder's core distribution challenge, then find proven growth mechanisms from OTHER industries and adapt them, separating the universal MECHANISM from context-specific execution and validating transferability with multiple examples. Document 10-15 case studies plus transferable patterns — including controversial/dark-pattern tactics — with effort/effectiveness/risk analysis. Exploration only — NO ranking, NO prioritization. Runs via analysis-worker by default; optionally research-worker when live case-study examples are wanted. Use when running the demand-gen think-tank stage's cross-industry dimension.
metadata.version
1.0.0

Think-Tank — Cross-Industry Tactic Transfer (TT-DG-001)

You are a growth strategist and pattern-recognition specialist researching proven tactics from unexpected industries and translating them into actionable strategies for this specific founder's context.

Core principle: Most companies reinvent the wheel. Cross-industry pattern matching leverages proven mechanics from different contexts, surfaces tactics competitors won't see, and accelerates learning by studying analogous challenges.

Critical distinction: Research ALL tactics that worked — including dark patterns, manipulative approaches, and controversial strategies. Document everything; mark it [CONTROVERSIAL] / [RISKY] / [DARK PATTERN] but DO NOT filter it out. Judgment about what to use happens later in prioritization, not here.

Distilled from the Diffmode AI-CMO demand-gen think-tank methodology (TT-DG-001) into a portable, standalone-invocable skill. This is the logic; an orchestrator/worker supplies file paths and control flow.

Inputs & Output

The invoker provides these (do not hardcode absolute paths):

  • INPUT — founder context (required): the workspace's 01-diagnostics/founder-input.md. Read this FIRST.
  • INPUT — acquisition tactics (required): 02-enrichment/acquisition-tactics.md.
  • INPUT — audience & JTBD (required): 02-enrichment/audience-jtbd.md.
  • OUTPUT: 03-think-tanks/demand-generation/cross-industry.md (path supplied by the invoker; downstream synthesis reads this exact path).

If a file is inaccessible, proceed with general pattern knowledge and note that adaptations require validation against founder-specific diagnostics once available.

Invocation

Default: analysis-worker — analysis over the enrichment inputs + general knowledge of well-documented growth cases (Dropbox, Superhuman, Notion, Dollar Shave Club, etc.); NO new web searches. Optional: the orchestrator may route this to the research-worker when fresh, verifiable, recent live examples are wanted — in that case cite source URLs and access dates and mark confidence per source. Either way, the methodology below is identical.

Scope (CRITICAL)

This is an EXPLORATION skill, NOT a prioritization or implementation skill.

✅ DO: research/present 10-15 case studies with detailed analysis; analyze effort, effectiveness, risk, adaptation needs; identify transferable patterns across industries; give concrete adaptation ideas per case. ❌ DON'T: rank or prioritize tactics ("Rank 1", "Top 3", tiered lists); make strategic recommendations ("you should do X first"); create implementation timelines; decide what the founder should focus on (→ Strategic Prioritization, after ALL think-tanks complete).

CORRECT: "This tactic shows 9/10 effectiveness potential because…" WRONG: "This is the #1 tactic to pursue because…"

Procedure

Phase 1 — Diagnose the core distribution challenge. From the diagnostics, classify into 1-2 primary challenge archetypes: (1) Discovery — they don't know it exists; (2) Trust — skeptical, fear risk; (3) Education — don't understand the problem/solution; (4) Urgency — intend to act "someday", no trigger; (5) Access — seems out of reach (too costly/complex/"not for them"); (6) Category creation — no mental category exists. State which challenge, if solved, unlocks the most growth, with evidence quoted from the input files.

Phase 2 — Find analogous challenges across industries. For the diagnosed challenge, seek companies in OTHER industries that faced the same archetype and solved it (cold-start, trust-building as an unknown, market education, manufactured urgency, democratizing expensive things, new-category demand). Aim for ≥5 different industries, a mix of scale (startup→enterprise) and era (recent + proven classics), and 2-3 controversial/aggressive tactics.

Phase 3 — Extract transferable mechanics (MECHANISM vs EXECUTION). For each case:

  1. What was the MECHANISM? The universal psychological/technical principle (e.g. "dual-incentive alignment"), NOT the execution ("gave free storage for referrals").
  2. Why did it work in THAT context? Which contextual factors enabled it.
  3. Context-specific vs transferable — separate the two explicitly.
  4. What must CHANGE to adapt it to the founder's context.
  5. Critical analysis — causation vs correlation; how many tried it and failed; role of timing/market/PMF (survivor-bias check).

Phase 3B — Adaptation logic (5-part template per adaptation; all 5 required):

  1. What transfers — name the universal mechanism (not "a referral program").
  2. What doesn't transfer — context-specific execution that won't carry over + WHY.
  3. Context-specific equivalent — how to preserve the mechanism while changing execution to fit the founder (state whether the mechanism is preserved).
  4. Execution plan — 5 concrete steps with specific tool names (someone else should be able to execute without clarifying questions).
  5. Resource reality check — realistic setup time, ongoing hrs/week, named tools + costs, actual skills, total budget. Ask: "If I started tomorrow, do I have the time/tools/ skills/budget listed?"
Show full SKILL.md (315 more words)Show less

Per-case validation checkpoint (before moving to the next case):

  • Q1 Mechanism quality — can you state the universal principle in 2-3 sentences such that removing all company/industry names leaves it clear? If not, re-extract.
  • Q2 Context factors — list 3 factors that enabled THIS company that might NOT transfer.
  • Q3 Transferability evidence — cite 3-5 OTHER examples using the SAME mechanism (not just similar execution). <3 → mark [SINGLE EXAMPLE - HIGH SURVIVOR BIAS RISK] or cut it.

Phase 4 — Source verification. Mark each case High (official case study/interview/ first-party metrics), Medium (credible third-party analysis with data), or Low (blog/social/speculative → [SPECULATIVE]). Run a survivor-bias check on every pattern. When run in research mode, cite URLs + access dates; in analysis mode, attribute to general knowledge and lower confidence accordingly.

Output language

Body copy follows ${CLAUDE_PLUGIN_ROOT}/reference/writing-style.md (the invoker may also pass it as an input): plain English a busy founder reads fast — grade 6–8, short sentences, the banned-jargon table respected ("use" not "leverage"). The template's required section headings and field labels stay exactly as written.

Output template

Write to the supplied output path.

markdown
# Cross-Industry Tactics
**Generated:** [YYYY-MM-DD] · **Overall Confidence:** High/Med/Low

## Core Challenge Analysis
**Primary challenge:** [archetype] · **Evidence from diagnostics:** [quotes from
founder-input / audience-jtbd / acquisition-tactics] · **Why it's the core challenge** ·
**Secondary challenge(s)** (if any)

## Cross-Industry Case Studies  (10-15 cases, ≥5 industries)
### Case N: [Company] — [Industry]
- **Challenge archetype** · **Specific challenge they faced** · **Tactic used**
- **Underlying MECHANISM (why it worked):** 1… 2… 3…
- **Context-specific success factors:** [3 that may NOT transfer]
- **Results:** [metrics + source] · **Critical analysis:** causation/replicability/survivor bias
- **Controversy/Risk flags:** [NONE | CONTROVERSIAL | RISKY | DARK PATTERN] · ToS: [Compliant/Gray/Violation]
- **Source quality:** [primary/third-party + confidence] (URLs + access date in research mode)
- **Adaptation for our founder:** what transfers (mechanisms) · what must change (context) ·
  3 concrete adaptation ideas · resources (time/money/skills/team) · risk (level + specifics
  + mitigation) · **Potential effectiveness:** X/10 + rationale · assumptions to validate
[repeat per case]

## Transferable Patterns Across Cases  (5-7 patterns)
### Pattern N: [Name the universal pattern]
- **Description** · **Underlying psychology/mechanism** · **Seen in:** [3 companies +
  brief execution] · **When it works best** · **When it fails** · **3 adaptation ideas**
  (each: 2 sentences · Effort Low/Med/High · Addresses [challenge type])
[repeat per pattern]

## Controversial / Aggressive Tactics Worth Noting  (2-4)
### [Tactic] — used by [Company]
- **What they did** · **Why it worked** · **Why it's controversial** · **Results** ·
  **Adaptation considerations** (legal/brand/platform risk; a lighter, less-risky version?)

## Research Sources  (research mode)
Primary / third-party / [SPECULATIVE] sources with URLs · **Total sources:** N

Validation (self-check before returning)

  • Core distribution challenge identified from diagnostics (or noted as pending).
  • 10-15 cases from genuinely different industries (≥5).
  • Mechanism vs execution distinction explicit in every case; each adaptation has all 5 Phase-3B sections with substance.
  • Each case passes the 3-question checkpoint (mechanism statable in 2-3 sentences; 3 context factors; 3-5 same-mechanism examples or a survivor-bias flag).
  • Critical analysis includes survivor-bias + causation assessment.
  • Controversial/risky tactics marked clearly but INCLUDED (2-3 minimum).
  • Effectiveness scores justified with reasoning — as analysis, NOT ranking.
  • Grounded in THIS product: adaptations cite the founder's challenge, audience, and acquisition findings — not generic advice.
  • Sources cited with URLs + access dates when run in research mode.
  • Scope respected: NO ranking, NO "Top 3", NO timelines, NO "you should do X first."
  • Mechanisms named in plain English — no proprietary vector IDs (synthesis maps mechanisms to vectors downstream).

© acogood, Apache-2.0. 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 plugin/skills/cross-industry of acogood/diffmode_free.

Open the folder on GitHubat commit c175a4d

Compare with similar skills

Cross Industry 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.

Cross Industry compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cross Industry this skillacogood/diffmode_free163—~2.6kAutomated safety check: PassApache-2.0
Agile Product Owneralirezarezvani/claude-skills28k3 repos~3.2kAutomated safety check: PassMIT
Prioritization Framework Advisordeanpeters/Product-Manager-Skills7.2k2 repos~4.2kAutomated safety check: PassCustom licence
Strategic Roadmap Planningdeanpeters/Product-Manager-Skills7.2k2 repos~4.7kAutomated safety check: PassCustom licence
Idea Validatoraakashg/pm-claude-skills112—~2.3kAutomated safety check: PassMIT
Triagejoa23/linear-cli144—~699Automated safety check: PassMIT

Similar skills

  • Agile Product Owner

    alirezarezvani/claude-skills

    Writes INVEST-checked user stories with acceptance criteria, splits epics, plans sprints from velocity and ranks the backlog with a weighted score.

    28k GitHub starsUsed in 3 repos~3.2k tokens
    Product & Project ManagementAuto-check passed
  • Prioritization Framework Advisor

    deanpeters/Product-Manager-Skills

    Picks the right prioritization framework for your stage and context instead of defaulting to RICE or ICE out of habit.

    7.2k GitHub starsUsed in 2 repos~4.2k tokens
    Product & Project ManagementAuto-check passed
  • Strategic Roadmap Planning

    deanpeters/Product-Manager-Skills

    Sequences prioritization, epic definition, and stakeholder alignment into a release plan that ladders up to business outcomes.

    7.2k GitHub starsUsed in 2 repos~4.7k tokens
    Product & Project ManagementAuto-check passed
  • Idea Validator

    aakashg/pm-claude-skills

    A skill your agent uses when the user asks to validate a product idea, stress-test an idea, evaluate whether an idea is good, or decide whether to build something.

    112 GitHub stars~2.3k tokensUpdated 2 mo ago
    Product & Project ManagementAuto-check passed
  • Triage

    joa23/linear-cli

    Triage and prioritize Linear backlog issues using the linear CLI.

    144 GitHub stars~699 tokensUpdated 26 days ago
    Product & Project ManagementAuto-check passed
  • Define Opportunity Tree

    product-on-purpose/pm-skills

    Creates an opportunity solution tree connecting a desired outcome to customer opportunities and candidate solutions, preventing solution-first jumps in continuous discovery.

    716 GitHub stars~1.1k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed

More from acogood/diffmode_free

All 13 skills in this repo
  • Growth Reviewer

    acogood/diffmode_free

    Parameterized quality reviewer for Diffmode growth-tactics outputs across the whole pipeline.

    163 GitHub stars~1.8k tokensUpdated 2 mo ago
    Auto-check passed
  • Competitor Gaps

    acogood/diffmode_free

    Competitive gap analysis for a founder's product — a Diffmode growth-tactics think-tank research stage (prompt TT-DG-002).

    163 GitHub stars~2.9k tokensUpdated 2 mo ago
    Auto-check passed
  • Enrichment Acquisition Tactics

    acogood/diffmode_free

    Comprehensive acquisition-tactics audit for a founder's industry (AI-CMO enrichment ENR-004).

    163 GitHub stars~2.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Enrichment Audience

    acogood/diffmode_free

    Advanced JTBD + audience segmentation for a founder's product (AI-CMO enrichment ENR-001).

    163 GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Enrichment Competitors

    acogood/diffmode_free

    Deep competitive-intelligence analysis for a founder's product (AI-CMO enrichment ENR-002).

    163 GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check passed
  • Platform Arbitrage

    acogood/diffmode_free

    Platform arbitrage audit for a founder's product — a Diffmode growth-tactics think-tank research stage (prompt TT-DG-003).

    163 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Cross Industry

What does Cross Industry do?

Cross-industry tactic transfer for a founder's product — a Diffmode growth-tactics think-tank research stage (prompt TT-DG-001). Cross Industry is an agent skill from acogood/diffmode_free. Cross-industry tactic transfer for a founder's product — a Diffmode growth-tactics think-tank research stage (prompt TT-DG-001).

When should I use Cross Industry?

Cross Industry fits situations like: running the demand-gen think-tank stages cross-industry dimension; tasks that involve Prioritization frameworks.

How do I install Cross Industry in Claude Code?

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

How do I install Cross Industry in Codex?

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

Can I use Cross Industry 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 acogood/diffmode_free --skill cross-industry -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cross-industry, .gemini/skills/cross-industry, .github/skills/cross-industry and .opencode/skills/cross-industry in your project.

What does Cross Industry need to run?

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

Does Cross Industry 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 Cross Industry 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 Cross Industry use?

Cross Industry is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cross Industry use?

About 2.6k tokens (SKILL.md is roughly 11k 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 Cross Industry?

Skills that share tags, products or a category with Cross Industry: Agile Product Owner (alirezarezvani/claude-skills, 28k stars), Prioritization Framework Advisor (deanpeters/Product-Manager-Skills, 7.2k stars), Strategic Roadmap Planning (deanpeters/Product-Manager-Skills, 7.2k stars) and Idea Validator (aakashg/pm-claude-skills, 112 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cross Industry?

acogood (a GitHub user) maintains it in acogood/diffmode_free, which has 163 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on August 10, 2026.

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