Project Onboarding Guide from Knowledge Graph
Egonex-AI/Understand-Anything
Writes an onboarding guide for new team members from a project's existing knowledge graph, after checking that the graph still matches the current commit.
Guides an AI assistant to redesign SaaS onboarding flows using the Activation Path Method — helping users define their aha moment, map time-to-value, eliminate friction, and produce a concrete…
$ npx skills add LeoYeAI/openclaw-master-skills --skill onboarding-activator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills onboarding-activator --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/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/onboarding-activator .claude/skills/onboarding-activator && 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 "onboarding-activator" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/onboarding-activator into .claude/skills/onboarding-activator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "onboarding-activator", 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/LeoYeAI/openclaw-master-skills/tree/main/skills/onboarding-activatorType 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 LeoYeAI/openclaw-master-skills --skill onboarding-activator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills onboarding-activator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/onboarding-activator .agents/skills/onboarding-activator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "onboarding-activator" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/onboarding-activator into .agents/skills/onboarding-activator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "onboarding-activator", 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 LeoYeAI/openclaw-master-skills --skill onboarding-activator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills onboarding-activator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/onboarding-activator .cursor/skills/onboarding-activator && 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 "onboarding-activator" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/onboarding-activator into .cursor/skills/onboarding-activator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "onboarding-activator", 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/LeoYeAI/openclaw-master-skills.git --path skills/onboarding-activator--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 LeoYeAI/openclaw-master-skills --skill onboarding-activator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills onboarding-activator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/onboarding-activator .gemini/skills/onboarding-activator && 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 "onboarding-activator" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/onboarding-activator into .gemini/skills/onboarding-activator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "onboarding-activator", 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 LeoYeAI/openclaw-master-skills onboarding-activatorInstalls 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 LeoYeAI/openclaw-master-skills --skill onboarding-activator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/onboarding-activator .github/skills/onboarding-activator && 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 "onboarding-activator" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/onboarding-activator into .github/skills/onboarding-activator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "onboarding-activator", 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 LeoYeAI/openclaw-master-skills --skill onboarding-activator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills onboarding-activator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/onboarding-activator .opencode/skills/onboarding-activator && 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 "onboarding-activator" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/onboarding-activator into .opencode/skills/onboarding-activator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "onboarding-activator", 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.
onboarding-activatorGuides an AI assistant to redesign SaaS onboarding flows using the Activation Path Method — helping users define their aha moment, map time-to-value, eliminate friction, and produce a concrete…
Onboarding Activator is an agent skill from LeoYeAI/openclaw-master-skills. Guides an AI assistant to redesign SaaS onboarding flows using the Activation Path Method — helping users define their aha moment, map time-to-value, eliminate friction, and produce a concrete minimum viable activation path. Use when a SaaS team wants to improve user activation, reduce time-to-value, or redesign their onboarding experience from first signup to first win.
Its SKILL.md is about 5.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `_meta.json` and `listing-metadata.md`).
The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. 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.
Onboarding Activator loads about 5.3k tokens when it runs. Until then it costs about 99 tokens; SKILL.md has 3,000 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 LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 3,000 words, ~5,339 tokens.
.claude/skills/onboarding-activator/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.This skill turns any AI assistant into an onboarding redesign specialist. Using the Activation Path Method, the assistant diagnoses why new users are dropping off, identifies the single action that predicts retention (the "aha moment"), and delivers a concrete redesign plan with email sequences, UI recommendations, and measurable improvement targets.
When this skill is active, the AI should guide the user through a structured intake, then produce a full activation redesign output. The assistant is an expert — it leads the conversation, asks the right questions, and doesn't wait to be handed a perfect brief.
Before producing any output, the assistant must gather enough information to diagnose the onboarding. Run this intake conversationally — don't dump all questions at once. Adapt based on what the user shares.
About the product:
About the current onboarding:
About the problems:
About existing assets:
Assistant note: If the user provides a detailed brief upfront, skip questions you can answer from context. Ask only what's missing. Lead with momentum.
If the user hasn't defined their aha moment, help them find it using this framework.
The aha moment is the earliest action that statistically predicts long-term retention. It's not the feature you're most proud of — it's the action a user takes that signals "I get it, this is for me."
Guide the user through these questions:
1. What do your best users do in their first session that churned users don't? Think about users who are still active after 90 days vs. those who signed up and never came back. What's different about their Day 1 behavior?
Common aha moment patterns by product type:
2. Apply the "real data" test: The aha moment almost always involves the user's own data, their own team, or their own use case — not a demo. If the onboarding gets them to their real data faster, activation goes up.
3. Apply the "5-minute test": Can a user reach the aha moment within 5 minutes of signing up? If not, that's the gap you're designing to close.
4. Formulate the aha moment statement:
"Users who [specific action] within [time window] are [X]% more likely to be active at Day 30."
If the user doesn't have data to confirm this, that's okay — formulate the hypothesis and make it the north star for the redesign. Note it as a hypothesis to validate.
Once the aha moment is defined, map the current path to it.
List every step between "sign up confirmed" and "aha moment achieved." For each step, classify it:
| Step | What happens | Time estimate | Friction type |
|---|---|---|---|
| 1 | Email confirmation click | 1-5 min wait | Delay |
| 2 | Password / account setup | 30 sec | Setup |
| 3 | Company/role survey | 1-2 min | Qualification |
| 4 | Feature tour (4 screens) | 2-3 min | Education |
| 5 | Connect integration (required) | 5-10 min | Hard gate |
| 6 | Import data / create first item | 3-5 min | Core action |
| 7 | Aha moment | — | Target |
Friction Types Defined:
Produce a summary:
Identify the top blockers between signup and the aha moment.
Evaluate each one for the user's product:
1. Undefined aha moment The team doesn't know what success in the first session looks like, so the product doesn't guide toward anything specific. Everything feels equally important.
Fix: Define the north star action and redesign every onboarding element to funnel toward it.
2. Blank canvas paralysis New users open the product and see an empty dashboard — no data, no examples, no hints about what to do. The product looks broken or useless until it's set up.
Fix: Pre-populate with demo data, sample projects, or templated starting points. Let users "feel the value" before they've done any setup work.
3. Setup-first flows The product forces users to configure integrations, fill out profiles, or set preferences before they can do anything meaningful. All the work happens before any reward.
Fix: Defer non-critical setup. Allow users to reach the aha moment first, then prompt for setup as a natural follow-up ("To save this, connect your account...").
4. Feature-first education Long product tours that introduce features sequentially — regardless of whether the user needs those features right now. Users get a feature dump instead of a value experience.
Fix: Replace feature tours with a single guided path to the first win. Show features contextually, when they're relevant to the task at hand.
5. Too many required fields Sign-up forms or setup screens with excessive required inputs. Every extra field is a drop-off risk.
Fix: Cut sign-up to email + password (or SSO). Collect everything else progressively, after value is delivered.
6. Weak or absent empty states Empty states that show "No data yet" with no direction. Users don't know what to do, so they don't do anything.
Fix: Every empty state should have a clear call-to-action, an example of what it looks like filled, and social proof or context (e.g., "Teams like yours typically start by...").
7. Time-based email sequences Onboarding emails sent on a fixed schedule (Day 0, Day 3, Day 7) regardless of what the user has actually done. Users who already activated get the same "get started" email as users who've never logged in.
Fix: Trigger emails based on user behavior. Did they complete step 1 but not step 2? Send a step-2-specific nudge. Did they achieve the aha moment? Send a depth email instead.
8. No milestone celebration Users reach important milestones — first project created, first report generated, first successful action — and the product says nothing. The moment passes without reinforcement.
Fix: Build micro-celebrations into the product. Confetti, congratulatory modals, progress messages. These create the emotional anchors that build habit.
The MVAP is the shortest possible journey from signup to the aha moment — with every unnecessary step removed or deferred.
Principle 1: Value before setup The user should experience value before they're asked to do any significant configuration. If a user can't feel why the product matters in the first 2 minutes, setup becomes a chore with no reward.
Principle 2: One clear next action At every screen, the user should have exactly one obvious thing to do. Multiple CTAs, navigation options, and feature links kill activation. Narrow the path.
Principle 3: Make the right thing easy, the wrong thing invisible Don't remove features — just don't surface them during onboarding. Hide the nav, disable optional settings, collapse the sidebar. Show the world's best version of the product for a brand-new user, not the full power-user interface.
Principle 4: Progress over completeness Users should feel they're moving forward at every step. Progress indicators, step counts, and micro-rewards (even subtle ones) maintain momentum.
Principle 5: Their data, not yours Get users to their own data as fast as possible. Demo data is a bridge, not a destination. The fastest path to their data = the fastest path to their aha moment.
Produce a redesigned flow using this structure:
Step 0: Landing / Sign-up page
Step 1: Account created → immediate redirect (no waiting)
Step 2: Guided path step 1 — context setting (< 60 seconds)
Step 3: Guided path step 2 — first action toward aha
Step 4: Aha moment
Step 5: Depth invitation
Design a trigger-based email sequence, not time-based. Map each email to a specific user state.
Email 1: The Welcome + First Action (trigger: signup, send: immediately)
Email 2A: The Activation Nudge (trigger: Day 1 end, condition: did NOT reach aha moment)
Email 2B: The Depth Email (trigger: aha moment achieved, send: within 24 hours of activation)
Email 3: The Social Proof / Use Case Email (trigger: Day 3 post-signup)
Email 4A: The Win or Re-Engage (trigger: Day 5, condition: not yet activated)
Email 4B: The Power Feature Email (trigger: Day 5, condition: activated)
Email 5: The Milestone Check-In (trigger: Day 7)
Signup
└── Email 1: Welcome + First Action (immediate)
└── [check: aha moment achieved by Day 1?]
├── YES → Email 2B: Depth Email (within 24h of aha)
└── NO → Email 2A: Activation Nudge (end of Day 1)
└── Email 3: Social Proof (Day 3, all users)
└── [check: aha moment achieved by Day 5?]
├── YES → Email 4B: Power Feature (Day 5)
└── NO → Email 4A: Win or Re-Engage (Day 5)
└── Email 5: Milestone Check-In (Day 7, all users)Every empty state should do three things:
Empty state copy formula:
"[Product area] is empty right now. [One sentence on what this area does for them.] [Action button: "Create your first X" / "Connect your X" / "Import from..."]"
Demo data strategy:
Rule 1: Context over coverage Don't mark every feature. Mark only the features that appear in the MVAP. A tooltip on a power feature during onboarding is noise, not help.
Rule 2: One tooltip at a time Never show multiple coach marks simultaneously. Show the next one only after the previous action is completed.
Rule 3: Tooltips should accelerate action, not explain features Bad tooltip: "This is the Projects panel. Here you can see all your projects." Good tooltip: "Create your first project here — it only takes 30 seconds."
Rule 4: Dismissible + never re-showing Once a user dismisses a tooltip or completes the associated action, never show it again. Track state per user, not per session.
Progressive disclosure over feature dumping: Show the minimum viable feature set in the first session. Add complexity as the user demonstrates readiness.
Gate by behavior, not by time: Don't unlock features on Day 3 just because 3 days have passed. Unlock them when the user has demonstrated they're ready (e.g., "completed 3 projects" unlocks advanced analytics).
Two-tier approach:
Match the celebration to the milestone weight:
| Milestone | Celebration type |
|---|---|
| Completed sign-up | Welcome message (text, friendly) |
| Completed first action in MVAP | Progress animation + "Keep going" prompt |
| Reached aha moment | Full celebration moment (confetti, modal, explicit congratulations) |
| Invited first teammate | "Team unlocked" message + preview of collaborative features |
| Completed first week | Summary card with usage stats + Week 2 goal |
Celebration copy formula for the aha moment:
"🎉 You did it! [Specific action the user just completed]. That's exactly how [best users] get started with [product]. Here's what to explore next → [single CTA]"
After completing phases 1–7, produce the activation redesign report in this format:
Aha Moment (defined / estimated)
[Single sentence: "Users who [action] within [time] are most likely to retain."] Confidence: [Confirmed by data / Hypothesis — recommend A/B testing]
Current Time-to-Aha Estimate
Top 3 Activation Delays to Remove
Redesigned Minimum Viable Activation Path
| Step | What happens | Time target | Change from current |
|---|---|---|---|
| 0 | Sign-up | < 60 sec | [change] |
| 1 | Land in product | Instant | [change] |
| 2 | [First guided action] | < 2 min | [change] |
| 3 | [Second guided action] | < 3 min | [change] |
| 4 | Aha moment | [target time from signup] | [change] |
| 5 | Depth invitation | — | [change] |
New time-to-aha target: [N] minutes (down from [N] minutes — [X]% reduction)
Recommended First-Week Email Sequence
| # | Name | Trigger | Subject line | CTA |
|---|---|---|---|---|
| 1 | Welcome + First Action | Signup | [subject] | [CTA] |
| 2A | Activation Nudge | Day 1 end, not activated | [subject] | [CTA] |
| 2B | Depth Email | Aha achieved | [subject] | [CTA] |
| 3 | Social Proof | Day 3, all | [subject] | [CTA] |
| 4A | Re-Engage | Day 5, not activated | [subject] | [CTA] |
| 4B | Power Feature | Day 5, activated | [subject] | [CTA] |
| 5 | Milestone Check-In | Day 7, all | [subject] | [CTA] |
Projected Activation Improvement
Implementation Priority
© LeoYeAI, 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 2 other files in skills/onboarding-activator of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Onboarding Activator 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 |
|---|---|---|---|---|---|---|
| Onboarding Activator this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~5.3k | Automated safety check: Pass | MIT | |
| Project Onboarding Guide from Knowledge GraphEgonex-AI/Understand-Anything | 86k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Codebase Onboardingaffaan-m/ECC | 277k | 3 repos | ~2k | Automated safety check: Pass | MIT | |
| Onboardingsickn33/agentic-awesome-skills | 47k | 1 repos | ~1.8k | Automated safety check: Pass | MIT | |
| Onboardalirezarezvani/claude-skills | 28k | — | ~1.3k | Automated safety check: Pass | MIT | |
| OpenSpec Guided OnboardingFission-AI/OpenSpec | 72k | 1 repos | ~4.5k | Automated safety check: Pass | MIT |
Egonex-AI/Understand-Anything
Writes an onboarding guide for new team members from a project's existing knowledge graph, after checking that the graph still matches the current commit.
affaan-m/ECC
Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md.
sickn33/agentic-awesome-skills
When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value.
alirezarezvani/claude-skills
/cs:onboard — Founder interview that populates ~/.claude/company-context.md using the canonical 7-dimension cs-onboard schema.
Fission-AI/OpenSpec
Walks you through a complete OpenSpec workflow cycle with narration while doing real work in your codebase.
Donchitos/Claude-Code-Game-Studios
Writes an onboarding document for a new contributor or agent, covering project state, conventions and priorities relevant to a chosen role.
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Guides an AI assistant to redesign SaaS onboarding flows using the Activation Path Method — helping users define their aha moment, map time-to-value, eliminate friction, and produce a concrete…. Onboarding Activator is an agent skill from LeoYeAI/openclaw-master-skills. Guides an AI assistant to redesign SaaS onboarding flows using the Activation Path Method — helping users define their aha moment, map time-to-value, eliminate friction, and produce a concrete minimum viable activation path.
Onboarding Activator fits situations like: A SaaS team wants to improve user activation; reduce time-to-value; redesign their onboarding experience from first signup to first win.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill onboarding-activator -a claude-code`. Or copy the skill folder (skills/onboarding-activator in LeoYeAI/openclaw-master-skills) into .claude/skills/onboarding-activator in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill onboarding-activator -a codex`. Or copy the skill folder (skills/onboarding-activator in LeoYeAI/openclaw-master-skills) into .agents/skills/onboarding-activator 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 LeoYeAI/openclaw-master-skills --skill onboarding-activator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/onboarding-activator, .gemini/skills/onboarding-activator, .github/skills/onboarding-activator and .opencode/skills/onboarding-activator in your project.
SKILL.md names no scripts, command-line tools or credentials: Onboarding Activator 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.
Onboarding Activator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.3k tokens (SKILL.md is roughly 21k 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 Onboarding Activator: Project Onboarding Guide from Knowledge Graph (Egonex-AI/Understand-Anything, 86k stars), Codebase Onboarding (affaan-m/ECC, 277k stars), Onboarding (sickn33/agentic-awesome-skills, 47k stars) and Onboard (alirezarezvani/claude-skills, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.