Claude Academy Guide
anthropics/skills
Adds a matching Claude Academy course, tutorial or use case to the end of an answer about learning to use Claude, but only when the match is strong.
Applies the SUCCESs Framework from Made to Stick by Chip Heath and Dan Heath.
$ npx skills add getagentseal/founder-playbook --skill made-to-stick -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install getagentseal/founder-playbook made-to-stick --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/getagentseal/founder-playbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/made-to-stick .claude/skills/made-to-stick && rm -rf skills-srcUse ~/.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/
Install the "made-to-stick" agent skill from https://github.com/getagentseal/founder-playbook/tree/main/skills/made-to-stick into .claude/skills/made-to-stick/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "made-to-stick", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/getagentseal/founder-playbook/tree/main/skills/made-to-stickType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add getagentseal/founder-playbook --skill made-to-stick -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install getagentseal/founder-playbook made-to-stick --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/getagentseal/founder-playbook.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/made-to-stick .agents/skills/made-to-stick && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "made-to-stick" agent skill from https://github.com/getagentseal/founder-playbook/tree/main/skills/made-to-stick into .agents/skills/made-to-stick/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "made-to-stick", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add getagentseal/founder-playbook --skill made-to-stick -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install getagentseal/founder-playbook made-to-stick --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/getagentseal/founder-playbook.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/made-to-stick .cursor/skills/made-to-stick && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "made-to-stick" agent skill from https://github.com/getagentseal/founder-playbook/tree/main/skills/made-to-stick into .cursor/skills/made-to-stick/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "made-to-stick", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/getagentseal/founder-playbook.git --path skills/made-to-stick--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add getagentseal/founder-playbook --skill made-to-stick -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install getagentseal/founder-playbook made-to-stick --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/getagentseal/founder-playbook.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/made-to-stick .gemini/skills/made-to-stick && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "made-to-stick" agent skill from https://github.com/getagentseal/founder-playbook/tree/main/skills/made-to-stick into .gemini/skills/made-to-stick/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "made-to-stick", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install getagentseal/founder-playbook made-to-stickInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add getagentseal/founder-playbook --skill made-to-stick -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/getagentseal/founder-playbook.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/made-to-stick .github/skills/made-to-stick && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "made-to-stick" agent skill from https://github.com/getagentseal/founder-playbook/tree/main/skills/made-to-stick into .github/skills/made-to-stick/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "made-to-stick", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add getagentseal/founder-playbook --skill made-to-stick -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install getagentseal/founder-playbook made-to-stick --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/getagentseal/founder-playbook.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/made-to-stick .opencode/skills/made-to-stick && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "made-to-stick" agent skill from https://github.com/getagentseal/founder-playbook/tree/main/skills/made-to-stick into .opencode/skills/made-to-stick/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "made-to-stick", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
made-to-stickApplies the SUCCESs Framework from Made to Stick by Chip Heath and Dan Heath.
Made To Stick is an agent skill from getagentseal/founder-playbook. Applies the SUCCESs Framework from Made to Stick by Chip Heath and Dan Heath. Use when crafting messages that need to be remembered, writing pitches, creating presentations, designing training materials, telling stories that drive action, or diagnosing why a message isn't landing. The six principles (Simple, Unexpected, Concrete, Credible, Emotional, Stories) diagnose and fix communication failures. Triggers include 'how do I make this memorable', 'my pitch isn't landing', 'people forget what we told them', 'how…
Its SKILL.md is about 4.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `cases.md`, `examples.md` and `frameworks.md`).
It sits in Education, covering Training and onboarding materials. The repository describes itself as: 15 proven business books distilled into AI-native skills. Works with Claude Code, ChatGPT, Gemini, Cursor. The licence is MIT.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e811e63. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Made To Stick loads about 4.1k tokens when it runs. Until then it costs about 219 tokens; SKILL.md has 1,903 words of instructions outside code blocks.
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.
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.
The full file from getagentseal/founder-playbook at commit e811e63, republished under its MIT licence (© getagentseal). 1,903 words, ~4,148 tokens.
.claude/skills/made-to-stick/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.Note: This skill is independent analysis and commentary, not a reproduction of the original text. It synthesizes the book's core ideas with modern startup practice, surfaces where frameworks are outdated or incomplete, and integrates perspectives from adjacent disciplines. For the full argument and context, read the original book.
"There is no such thing as an inherently uninteresting subject. There are only uninterested communicators." - Chip Heath & Dan Heath
Is your message failing to land?
|-- YES --> Do people understand it but forget it?
| |-- YES --> Probably missing CONCRETE or STORIES. Check those principles.
| +-- NO --> Do people tune out before hearing it?
| |-- YES --> Missing UNEXPECTED (no hook) or SIMPLE (too complex).
| +-- NO --> Do they hear it but not care?
| |-- YES --> Missing EMOTIONAL. They believe but don't act.
| +-- NO --> Do they care but not believe it?
| |-- YES --> Missing CREDIBLE.
| +-- NO --> THIS SKILL. Run the full diagnostic.
+-- NO --> Is the message landing but people aren't acting?
|-- YES --> Missing STORIES (no mental simulation of action) or
| EMOTIONAL (they believe but don't feel).
+-- NO --> The message is working. Don't fix what isn't broken.The enemy of sticky messages is the Curse of Knowledge.
Once you know something, you can't imagine not knowing it. You tap a song on a table and think it's obvious - but listeners guess correctly only 2.5% of the time (you predicted 50%). This is the tappers-and-listeners experiment, and it's the central metaphor of the entire book.
Every expert, every founder, every leader suffers from this curse. It makes you talk in abstractions when your audience needs concrete details. It makes you assume shared context that doesn't exist. It makes your messages forgettable.
The SUCCESs framework is the systematic antidote.
WHAT COMMUNICATORS DO: WHAT STICKY MESSAGES DO:
Bury the lead in context Lead with the core (SIMPLE)
Start with what's expected Start with what's surprising (UNEXPECTED)
Speak in abstractions Speak in sensory, tangible terms (CONCRETE)
Rely on their own authority Let the message prove itself (CREDIBLE)
Appeal to reason and logic Appeal to identity and feeling (EMOTIONAL)
Present conclusions Tell stories that simulate action (STORIES)Six principles. Not a checklist where you need all six, but a diagnostic toolkit. Most messages fail on 1-2 specific principles. Identify which ones and fix those.
Find the core. Share the core. Nothing else.
This is not about dumbing down. It's about forced prioritization - finding the single most important thing and saying it in a way that's both compact and profound.
Commander's Intent (CI): The military's solution to the Curse of Knowledge. Instead of detailed battle plans that fall apart on contact with the enemy, officers communicate the ONE thing that matters: "Break the will of the enemy in this region." Soldiers can improvise around that intent when plans fail.
Your Commander's Intent: If your audience remembers only ONE thing, what must it be?
Tools for simplicity:
| Tool | How It Works | Example |
|---|---|---|
| Inverted Pyramid | Lead with the most important info first | Journalism standard: headline, lead, details |
| Generative Analogy | Compress an idea into a schema people already have | Disney calls employees "cast members" - this single metaphor generates correct behavior across thousands of situations |
| High-Concept Pitch | Describe via known reference points | "Jaws on a spaceship" (Alien), "Die Hard on a bus" (Speed) |
| Proverbs | Compact + profound | "A bird in the hand is worth two in the bush" - simple AND deep |
The accuracy trap: Don't sacrifice memorability for completeness. "Maximize shareholder value" is accurate but generates no useful behavior. Southwest's "THE low-fare airline" is less precise but drives every decision in the company.
Test: Can a front-line employee use your message to make a decision you'd agree with, without asking you?
Get attention with surprise. Keep attention with curiosity.
Two problems, two solutions:
| Problem | Solution | Mechanism |
|---|---|---|
| Getting attention | Surprise | Break a schema (violate expectations) |
| Keeping attention | Curiosity | Open a knowledge gap, then fill it |
The surprise sequence:
Gap Theory of Curiosity (Loewenstein, 1994): Curiosity happens when there's a gap between what we know and what we want to know. To make people curious: (1) point out what they DON'T know, (2) highlight that they should care, (3) fill the gap.
Mysteries vs. surprise: Surprise gets attention in a moment. Mysteries keep attention across time. Structure complex messages as mysteries when possible.
Warning: Surprise for its own sake (gimmicks) is counterproductive. The surprise must serve the core message.
Speak in sensory language. Actions, things, images - not abstractions.
"Of the six traits, concreteness is perhaps the easiest to embrace. It may also be the most effective."
Why we slip into abstraction: Expertise makes you think in patterns and principles. You forget your audience thinks in concrete examples. Engineers make drawings more elaborate when they should walk to the factory floor.
Velcro Theory of Memory: The more sensory hooks an idea has, the more it sticks. Abstract ideas have few hooks. Concrete ideas (sights, sounds, smells, touch, taste) have many.
| Abstract | Concrete |
|---|---|
| "Increase customer satisfaction" | "When a guest's towel falls in the pool, replace it before they ask" |
| "The next great search engine" | "Seat 131 passengers, fly nonstop Miami to NYC, land on Runway 4-22 at La Guardia" |
| "We value diversity" | "Our longest-tenured member is a 73-year-old retired government worker with no prior dance experience" |
| "Improve employee productivity" | "If wireless saves an employee 1-2 minutes per day, it's paid for itself" |
The "White Things" test: Name white things in the world (hard). Name white things in your refrigerator (easy). Concreteness focuses and mobilizes thinking.
For founders: Visit actual customers. General Mills sent the Hamburger Helper team into customers' homes ("Fingertips" program). Abstract data produced abstract strategy. Concrete observation produced an 11% sales increase.
Make the audience believe you - or better, let them believe themselves.
Three sources of credibility, from external to internal:
| Source | Type | Examples |
|---|---|---|
| Authorities | External | Experts with credentials, celebrities, anti-authorities (real people with lived experience) |
| The Message Itself | Internal | Vivid details, human-scale statistics, the Sinatra Test |
| The Audience | Self-verify | Testable credentials ("See for yourself") |
Anti-authorities are often stronger than authorities. Pam Laffin (29-year-old smoker dying of emphysema) was more persuasive for anti-smoking than any surgeon general could be. Honesty and lived experience > status.
Statistics rule: Never use a number in isolation. Always use statistics to illustrate a RELATIONSHIP. "5,000 nuclear warheads" means nothing. One BB in a bucket (Hiroshima), then 5,000 BBs poured in (current arsenal) - the roar that went on and on, followed by dead silence. That's a statistic that changes minds.
The Human-Scale Principle: Reframe statistics in terms people can intuit. Not "sun to earth accuracy" but "New York to LA, within two thirds of an inch."
The Sinatra Test: "If I can make it there, I'll make it anywhere." One example that alone establishes credibility for an entire domain. Safexpress delivered Harry Potter books on release day (every book, every bookstore, 8 AM, no leaks) - that single credential won a Bollywood distribution deal.
Testable Credentials: The most powerful form. Outsource credibility to the audience. "Are you better off than you were four years ago?" (Reagan). "Where's the beef?" (Wendy's). Let people discover the truth themselves.
Make people care. Belief without feeling doesn't produce action.
"If I look at the mass, I will never act. If I look at the one, I will." - Mother Teresa
The Rokia Study: People donated $2.38 to save one named girl (Rokia, 7, from Mali). People donated $1.14 when given statistics about millions suffering. People given BOTH Rokia + statistics donated $1.43. Statistics actively suppressed emotional giving. The analytical frame of mind is the enemy of empathy.
Three strategies for making people care:
| Strategy | Mechanism | Example |
|---|---|---|
| Association | Link idea to something people already care about | "Don't Mess with Texas" - link littering to state pride, not environment |
| Self-Interest (WIIFY) | Answer "What's In It For You?" | But go beyond features to identity - Maslow's peak, not basement |
| Identity | Appeal to who people ARE or want to be | "What would someone like me do?" (James March's identity model) |
Maslow's Basement problem: Marketers default to base-level appeals (save money, save time). Often the audience cares more about self-actualization, belonging, or esteem. "Don't Mess with Texas" worked because it appealed to Texan identity (esteem/belonging), not to environmental duty (abstract).
Semantic Stretch warning: Some words get used so often they lose emotional power ("unique," "quality," "innovative," "cutting-edge"). If a word could apply to any company in your industry, it's emotionally dead.
Stories are flight simulators for the brain.
Mental simulation research shows that imagining an event activates the same brain regions as experiencing it. Stories don't just inform - they prepare people to act.
Three inspirational plot types:
| Plot | Core Pattern | When to Use |
|---|---|---|
| Challenge | Underdog overcomes obstacles | When you need to inspire persistence, effort, courage |
| Connection | People bridge divides (racial, class, demographic) | When you need to build empathy, teamwork, tolerance |
| Creativity | Someone has an insight that solves a puzzle | When you need to inspire innovation, new thinking |
Springboard stories: Stephen Denning at the World Bank couldn't convince the institution to embrace knowledge management with data and arguments. He told a single story: a health worker in Zambia logging onto the CDC website to solve a malaria problem. That one story launched a transformation of the entire organization.
Spotting vs. creating: You don't need to invent stories. The best stories already exist in your organization, among your customers, in your data. Your job is to spot them and retell them.
The speakers vs. stickers experiment: After a round of one-minute speeches using statistics, only 5% of listeners remembered a statistic. 63% remembered a story. Stories are 12x more memorable than statistics.
When a message isn't working, use this to find the broken principle:
| Symptom | Likely Broken Principle | Fix |
|---|---|---|
| "It's too complicated" | Simple | Find Commander's Intent. Cut everything else. |
| "People tune out immediately" | Unexpected | Lead with what's counterintuitive. Open a gap. |
| "They nod but forget it next day" | Concrete | Replace abstractions with sensory details and examples. |
| "They don't believe us" | Credible | Add anti-authorities, Sinatra Test examples, testable credentials. |
| "They believe but don't care" | Emotional | Make it about one person, not millions. Appeal to identity. |
| "They care but don't act" | Stories | Give them a mental simulation. Tell a Challenge or Springboard story. |
Every communication task maps to SUCCESs:
I need my audience to... Use this principle:
PAY ATTENTION Unexpected (surprise + curiosity gap)
UNDERSTAND AND REMEMBER Concrete (sensory, tangible, specific)
BELIEVE / AGREE Credible (authorities, details, Sinatra Test, testable)
CARE Emotional (individual focus, identity, self-interest)
ACT Stories (mental simulation, springboard stories)Simple isn't listed because it's the prerequisite for all of them. If you haven't found the core, none of the other principles can save you.
Made to Stick is a message design toolkit. It helps you craft individual messages that land. It doesn't help you decide what to say (that's strategy), where to say it (Traction), or how to structure your overall brand narrative (StoryBrand). Think of it as the quality control layer that sits on top of your messaging strategy.
© getagentseal, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 4 other files in skills/made-to-stick of getagentseal/founder-playbook.
Open the folder on GitHubat commit e811e63
Made To Stick 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Made To Stick this skillgetagentseal/founder-playbook | 729 | — | ~4.1k | Automated safety check: Pass | MIT | |
| Claude Academy Guideanthropics/skills | 180k | 3 repos | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Lecture Performance Reviewcat-xierluo/legal-skills | 720 | — | ~2.2k | Automated safety check: Pass | None | |
| Vocational Task-Engine Course DesignTHU-MAIC/OpenMAIC | 40k | — | ~794 | Automated safety check: Pass | MIT | |
| Workshop-Style Course DesignTHU-MAIC/OpenMAIC | 40k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Design ThinkingProrise-cool/Claude-Code-Multi-Agent | 306 | 1 repos | ~3.6k | Automated safety check: Pass | None |
anthropics/skills
Adds a matching Claude Academy course, tutorial or use case to the end of an answer about learning to use Claude, but only when the match is strong.
cat-xierluo/legal-skills
Analyzes raw lecture transcripts for verbal tics, pacing, time use and promise follow-through, with optional slide-by-slide comparison and cross-session tracking.
THU-MAIC/OpenMAIC
Plans vocational training as a hands-on work task with operation stages, tool and equipment state, safety boundaries and GO or STOP checkpoints instead of a lecture.
THU-MAIC/OpenMAIC
Shapes a course as a hands-on workshop, with an exercise or check every couple of pages, short task-brief slides and a closing page that combines the pieces into a small project.
Prorise-cool/Claude-Code-Multi-Agent
Design Thinking methodology for human-centered innovation. An agent skill from Prorise-cool/Claude-Code-Multi-Agent.
mingchen666/Reviva
Find, verify, and curate teaching resources for lesson preparation.
getagentseal/founder-playbook
Builds lead generation systems using Alex Hormozi's Core Four framework (warm outreach, content, cold outreach, paid ads), lead magnets, and Rule of 100.
getagentseal/founder-playbook
Designs irresistible Grand Slam Offers using Alex Hormozi's value equation, obstacle-solution mapping, value-cost trim/stack, and offer-naming patterns.
getagentseal/founder-playbook
Frameworks from Kim & Mauborgne for creating uncontested market space and making competition irrelevant.
getagentseal/founder-playbook
Startup diagnostic router. An agent skill from getagentseal/founder-playbook.
getagentseal/founder-playbook
Cialdini's seven principles of compliance (the classic six — reciprocation, commitment-consistency, social proof, liking, authority, scarcity — plus Unity, added 2016) and Pre-Suasion.
getagentseal/founder-playbook
Applies Eric Ries's Lean Startup methodology for building products under extreme uncertainty.
Categories
Applies the SUCCESs Framework from Made to Stick by Chip Heath and Dan Heath. Made To Stick is an agent skill from getagentseal/founder-playbook. Applies the SUCCESs Framework from Made to Stick by Chip Heath and Dan Heath.
Made To Stick fits situations like: crafting messages that need to be remembered; writing pitches; creating presentations; designing training materials.
Run `npx skills add getagentseal/founder-playbook --skill made-to-stick -a claude-code`. Or copy the skill folder (skills/made-to-stick in getagentseal/founder-playbook) into .claude/skills/made-to-stick in your project. Claude Code loads it when a task matches its description.
Run `npx skills add getagentseal/founder-playbook --skill made-to-stick -a codex`. Or copy the skill folder (skills/made-to-stick in getagentseal/founder-playbook) into .agents/skills/made-to-stick in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add getagentseal/founder-playbook --skill made-to-stick -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/made-to-stick, .gemini/skills/made-to-stick, .github/skills/made-to-stick and .opencode/skills/made-to-stick in your project.
SKILL.md names no scripts, command-line tools or credentials: Made To Stick is instructions for the agent only.
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.
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.
Made To Stick is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.1k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Made To Stick: Claude Academy Guide (anthropics/skills, 180k stars), Lecture Performance Review (cat-xierluo/legal-skills, 720 stars), Vocational Task-Engine Course Design (THU-MAIC/OpenMAIC, 40k stars) and Workshop-Style Course Design (THU-MAIC/OpenMAIC, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
getagentseal (a GitHub organization) maintains it in getagentseal/founder-playbook, which has 729 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 6, 2026.
Source: getagentseal/founder-playbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.