Boundary Setting Scripts
mohitagw15856/pm-claude-skills
Set a boundary with someone — a friend, family member, coworker, or partner — clearly and kindly, with the actual words and a plan for the pushback.
Setting and maintaining personal boundaries across all relationships.
$ npx skills add LeoYeAI/openclaw-master-skills --skill boundaries-saying-no -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills boundaries-saying-no --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/boundaries-saying-no .claude/skills/boundaries-saying-no && 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 "boundaries-saying-no" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/boundaries-saying-no into .claude/skills/boundaries-saying-no/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "boundaries-saying-no", 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/boundaries-saying-noType 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 boundaries-saying-no -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills boundaries-saying-no --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/boundaries-saying-no .agents/skills/boundaries-saying-no && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "boundaries-saying-no" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/boundaries-saying-no into .agents/skills/boundaries-saying-no/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "boundaries-saying-no", 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 boundaries-saying-no -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills boundaries-saying-no --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/boundaries-saying-no .cursor/skills/boundaries-saying-no && 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 "boundaries-saying-no" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/boundaries-saying-no into .cursor/skills/boundaries-saying-no/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "boundaries-saying-no", 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/boundaries-saying-no--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 boundaries-saying-no -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills boundaries-saying-no --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/boundaries-saying-no .gemini/skills/boundaries-saying-no && 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 "boundaries-saying-no" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/boundaries-saying-no into .gemini/skills/boundaries-saying-no/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "boundaries-saying-no", 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 boundaries-saying-noInstalls 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 boundaries-saying-no -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/boundaries-saying-no .github/skills/boundaries-saying-no && 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 "boundaries-saying-no" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/boundaries-saying-no into .github/skills/boundaries-saying-no/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "boundaries-saying-no", 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 boundaries-saying-no -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 boundaries-saying-no --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/boundaries-saying-no .opencode/skills/boundaries-saying-no && 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 "boundaries-saying-no" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/boundaries-saying-no into .opencode/skills/boundaries-saying-no/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "boundaries-saying-no", 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.
boundaries-saying-noSetting and maintaining personal boundaries across all relationships.
Boundaries Saying No is an agent skill from LeoYeAI/openclaw-master-skills. Setting and maintaining personal boundaries across all relationships. Use when someone can't say no, feels constantly drained by others' demands, is being guilt-tripped, or needs to establish limits with family, work, friends, or partners.
Its SKILL.md is about 5.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `_meta.json`).
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 (its code samples are yaml and agent-adaptation).
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.
Boundaries Saying No loads about 5.2k tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 864 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). 864 words, ~5,168 tokens.
.claude/skills/boundaries-saying-no/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Boundaries are not walls, not punishment, not ultimatums, and not "being difficult." They're clear statements about what you will and won't accept, communicated directly. Most people who struggle with boundaries were trained — by family, by culture, by workplaces — to believe that their own needs are less important than other people's comfort. That training is wrong, and unlearning it is a skill, not a personality transplant. This skill provides actual scripts you can use verbatim, because when you're in the moment and your brain is screaming "just say yes to avoid conflict," you need words ready to go, not abstract concepts.
This skill references and extends: difficult-conversations, safe-exit-planner.
# Localization note — boundary norms differ significantly across cultures.
- Collectivist cultures (East Asian, South Asian, Latin American, Middle Eastern):
Boundaries with family can carry heavier social consequences. "I love you and I'm
not discussing this" may need to be softened. Frame boundaries as caring for the
relationship, not rejecting the person. In some cultures, direct refusal is
considered extremely rude — offer alternatives rather than flat "no."
- Workplace norms:
US/AU/CA: Relatively acceptable to push back on workload directly.
UK: More indirect communication expected. "I'm not sure I can take that on"
rather than "No, I can't do that."
Japan/Korea: Hierarchy makes direct refusal to superiors very difficult.
Work through indirect signals or intermediaries.
Nordic countries: Flat hierarchies make workplace boundaries easier.
- Gender dynamics:
Women face disproportionate social penalties for setting boundaries in most
cultures. The scripts here work regardless, but acknowledge that the
backlash risk is real and not imagined.
- Physical boundaries:
In high-contact cultures (Mediterranean, Latin American, Middle Eastern),
personal space norms differ. Physical boundary scripts may need cultural
calibration.
- Legal protections:
Workplace boundary enforcement varies. In the US, hostile work environment
claims require documented patterns. In the EU, worker protections are
generally stronger. Reference local employment law.Agent action: Clarify the concept. Most people have been taught wrong definitions.
WHAT BOUNDARIES ARE:
- Clear statements about what YOU will and won't do.
- About your behavior, not controlling theirs.
- "I won't stay in a conversation where I'm being yelled at."
(This is about what YOU will do — leave.)
- Flexible, context-dependent, and yours to set without justification.
WHAT BOUNDARIES ARE NOT:
- Punishment: "I'm not talking to you until you apologize."
(That's a power move, not a boundary.)
- Ultimatums: "If you do X, I'll leave you."
(That's a threat. A boundary states what you'll do regardless of
their response.)
- Walls: Shutting everyone out is avoidance, not boundaries.
- Selfish: Protecting your capacity so you can show up for people
is the opposite of selfish.
THE KEY DISTINCTION:
A boundary is about YOU. Not about them.
"You can't call me after 9pm" = controlling their behavior.
"I don't answer the phone after 9pm" = your boundary.
Same outcome. Completely different framing. The first invites argument.
The second is a statement of fact.Agent action: Provide the core technique and practice scripts.
THE NO + ONE SENTENCE FORMULA
Say no. Give one reason maximum. Stop talking.
The more you explain, the more material you give them to argue with.
Every additional sentence is a crack they can wedge open. Short is
strong.
EXAMPLES:
WORK:
"I can't take that on this week."
(Full stop. You don't owe a detailed schedule breakdown.)
FAMILY:
"I can't make it to Thanksgiving this year."
(You don't need to explain why. "I can't make it" is a complete answer.)
FRIENDS:
"I can't come Saturday. Hope you have fun."
(Not "I can't come because I have this thing and then this other
thing and I'm really sorry and..." — just no + well-wishes.)
PARTNER:
"I need tonight to myself. Let's do something together tomorrow."
(Not a rejection — a redirect.)
THE HARDEST PART: The silence after "no." Your brain will scream
at you to fill it with justifications. Don't. Let the silence sit.
They'll either accept it or push back, and if they push back, you
repeat it (see Step 3).Agent action: Teach the repetition technique for when people push back.
THE BROKEN RECORD — WHEN THEY DON'T ACCEPT YOUR NO
Some people hear "no" as the start of a negotiation. The broken
record technique shuts this down without escalation. You repeat your
boundary calmly, without new arguments, until they stop pushing.
EXAMPLE:
Them: "Come on, just stay for one more drink."
You: "I'm heading out. Thanks though."
Them: "But it's still early! Don't be lame."
You: "I hear you. I'm heading out."
Them: "Just one more. What's the big deal?"
You: "I'm heading out. See you next time."
NOTICE:
- Same message each time. No new reasons.
- Calm tone. Not angry, not apologetic.
- Acknowledge what they said ("I hear you") but don't engage with
the argument.
- No escalation. No defending. Just repetition.
WHY IT WORKS: Pushback is designed to get you to change your answer.
When you don't provide new arguments, there's nothing new to argue
with. Most people give up after 2-3 repetitions.
THE RULE: You don't need a better reason. Your first reason was
sufficient. Repeating it proves that.Agent action: Provide context-specific boundary scripts the user can adapt.
WORK BOUNDARIES
Boss asks you to take on more when you're at capacity:
"I want to do good work on what I have. If I take this on, something
else needs to come off my plate. What would you like me to deprioritize?"
Coworker keeps dumping their work on you:
"I can't help with that today. You might try [alternative resource]."
Expected to be available 24/7 (emails, texts after hours):
"I check messages during work hours. I'll get back to you first thing
tomorrow."
Someone taking credit for your work:
"I want to make sure the record is clear — I led [specific piece].
Happy to present it in the next meeting."
FAMILY BOUNDARIES
Parent who criticizes your life choices:
"I love you and I'm not discussing this."
(Repeat as needed. Do not justify your choices.)
Parent who guilt-trips you about visits:
"I can visit [specific date]. That's what works for my schedule."
(Not: "I'm sorry I can't come more often, it's just that work is
crazy and..." — that's an invitation to argue.)
Sibling who asks for money:
"I can't lend money right now." Period. You don't owe an accounting
of your finances.
Relative who comments on your body/weight/food:
"I don't discuss my body. How about [topic change]?"
In-laws who overstep:
This one requires partner alignment first. You and your partner
agree on the boundary together, and the partner communicates it
to their own parents. "My partner and I have decided..."
FRIEND BOUNDARIES
Friend who only calls when they need something:
"I've noticed our conversations are mostly about your stuff. I need
this to go both ways."
Friend who's always late:
"I'll wait 15 minutes. If you're not there, I'll assume plans changed."
(Then follow through.)
Friend who pressures you to drink/use:
"I'm not drinking tonight." No elaboration needed. If they push,
broken record.
PARTNER BOUNDARIES
Need alone time:
"I need 30 minutes to decompress when I get home before I can talk.
It's not about you — it's how I recharge."
Don't want to discuss something right now:
"I'm not in a place to talk about this productively. Can we come
back to it [specific time]?"
Physical boundary:
"I'm not in the mood for [activity] right now. I'd love to [alternative]."Agent action: Teach the FOG framework and how to identify manipulation tactics.
THE FOG: FEAR, OBLIGATION, GUILT
Manipulative people (often unconsciously) use three levers to override
your boundaries:
FEAR: "If you don't come to Thanksgiving, I don't know what I'll do."
"You'll regret this." "Fine, I'll just handle it myself" (martyrdom).
OBLIGATION: "After everything I've done for you." "Family is supposed
to be there for each other." "You owe me."
GUILT: "I guess I'm just not important to you." "You've changed."
"Everyone else manages to show up."
HOW TO SPOT IT:
- You feel terrible after saying a reasonable "no."
- They frame your boundary as YOU hurting THEM.
- They bring up past favors as leverage.
- They use silent treatment, tears, or anger as punishment for
your boundary.
- You find yourself apologizing for having needs.
HOW TO RESPOND:
- Name it (internally): "This is a guilt trip. My boundary is
reasonable."
- Don't argue the manipulation. That's a trap. Argue the content
and you lose.
- Return to your boundary: "I understand you're upset. My answer
is still [boundary]."
- Accept that they'll be unhappy. That's allowed. Their feelings
about your boundary are their responsibility, not yours.
CRITICAL TRUTH: Guilt after saying no is NORMAL. It's not evidence
that you did something wrong. It's the residue of old programming.
The guilt fades. The resentment from never saying no doesn't.Agent action: Address the hardest boundary category with specific guidance.
BOUNDARIES WITH PARENTS — THE HARDEST CATEGORY
Why it's harder: Parents wrote your original operating system. The
guilt response to disappointing them is literally hardwired from
childhood. This doesn't mean the boundary is wrong. It means the
feelings will be louder.
COMMON PARENT BOUNDARY SITUATIONS:
The parent who needs to know everything:
"I appreciate your concern. I'll share what I'm comfortable sharing."
They don't need to know your salary, your relationship details,
your medical decisions, or your plans until you're ready.
The parent who can't accept you're an adult:
"I've thought about this and made my decision. I'm not asking for
permission."
The parent who weaponizes disappointment:
"I'm sorry you're disappointed. I still love you and this is my
decision."
The parent who shows up unannounced:
"I need you to call before coming over. If you show up without
calling, I may not be able to let you in."
Then FOLLOW THROUGH. The boundary means nothing if you cave.
THE HARDEST PART — FOLLOW-THROUGH:
Setting the boundary is step one. Enforcing it is the real work.
When you state a consequence ("I'll leave the conversation if
you raise your voice"), you MUST follow through. One cave-in
teaches them the boundary is negotiable.
EXPECT:
- Pushback. Anger. Guilt trips. Silent treatment.
- These are not signs you did something wrong. They're signs the
other person preferred the old arrangement where you had no limits.
- It usually gets worse before it gets better.
- Some parents adjust. Some don't. You can't control which.Agent action: Address physical boundary violations, especially in workplace contexts.
PHYSICAL BOUNDARIES — YOUR BODY, YOUR RULES
"Don't touch me" is a complete sentence. You never need to explain
why you don't want to be touched.
WORKPLACE PHYSICAL BOUNDARIES:
- Unwanted shoulder rubs, hugs, pats: "Please don't touch me."
If it continues: document (date, time, what happened) and report
to HR in writing (email = paper trail).
- Standing too close: Step back. If they follow: "I need a bit more
space." No smile required.
- Handshake grip games: Firm handshake is fine. Bone-crushing or
lingering is a dominance move. "That's quite a grip" + withdraw
your hand.
SOCIAL PHYSICAL BOUNDARIES:
- Huggers when you don't want to hug: Put your hand out for a
handshake or wave before they reach you. "I'm not a hugger — good
to see you though."
- Someone grabbing your arm to get your attention: "Hey — don't grab
me. Just say my name."
- Tickling, poking, play-hitting: "Stop. I don't like that." Age
doesn't matter. "Oh, lighten up" is not an acceptable response
to someone asking not to be touched.
TRADES AND SERVICE JOBS:
- Customer grabs you, touches you, stands too close: "Please step
back." You are not required to be friendly about it. Your employer
should back you up. If they don't, document and escalate.
- Coworker "joke" touching (slapping, shoulder-punching, grabbing
tools from your hands): "Don't do that." Once is enough. If it
continues, it's HR territory.
IF IT ESCALATES:
Any repeated unwanted physical contact after you've said stop is
harassment. Document everything. Report in writing. If your employer
doesn't act, contact your state's labor board or an employment attorney.Agent action: Provide the escalation path when someone repeatedly violates boundaries.
ESCALATION PROTOCOL — WHEN THEY WON'T STOP
LEVEL 1: STATE THE BOUNDARY (clear, calm, once)
"I need you to stop calling me after 9pm."
LEVEL 2: RESTATE + NAME THE PATTERN
"I've asked you not to call after 9pm and it's happened three more
times. I need this to stop."
LEVEL 3: STATE THE CONSEQUENCE
"If you call after 9pm again, I'm going to stop answering your calls
entirely for a week."
LEVEL 4: ENFORCE THE CONSEQUENCE
Follow through. No exceptions. No "well, this time it seemed urgent."
They already know the boundary. Enforcing it is the only thing that
creates change.
LEVEL 5: REDUCE OR END CONTACT
If someone repeatedly violates your boundaries despite clear
communication and consequences, the boundary becomes distance.
"I've tried to make this work with [boundary]. Since it's not being
respected, I need to take a break from this relationship."
IMPORTANT:
- You don't skip levels. Give people a genuine chance to adjust.
- You don't stay at Level 1 forever. Repeating a boundary that's
being ignored without escalating teaches them it's safe to ignore.
- You're allowed to go straight to Level 5 if there's a safety issue.
Abuse, threats, or violence skip the protocol entirely.
See safe-exit-planner for dangerous situations.boundaries_session:
relationship_context: null
specific_boundary_needed: null
manipulation_pattern_identified: null
escalation_level: null
safety_concern: false
scripts_provided: []
guilt_response_addressed: false
follow_through_plan: null
resources_provided: []
related_skills_referenced: []triggers:
- name: safety_escalation
condition: "user describes fear of physical harm, threats, or violence in response to boundary-setting"
schedule: "immediate"
action: "Reference safe-exit-planner skill and provide DV hotline resources. Boundary scripts alone are insufficient for dangerous situations."
- name: guilt_normalization
condition: "user expresses guilt or anxiety after setting a boundary"
schedule: "on_demand"
action: "Provide Step 5 FOG framework and normalize guilt as expected, not evidence of wrongdoing"
- name: parent_boundary_support
condition: "user needs to set boundaries specifically with parents or in-laws"
schedule: "on_demand"
action: "Jump to Step 6 parent-specific guidance and provide relevant scripts"
- name: workplace_boundary_documentation
condition: "user describes repeated workplace boundary violations"
schedule: "on_demand"
action: "Provide documentation protocol, escalation path, and reference to employment law resources"© 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 1 other file in skills/boundaries-saying-no of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Boundaries Saying No 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 |
|---|---|---|---|---|---|---|
| Boundaries Saying No this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~5.2k | Automated safety check: Pass | MIT | |
| Boundary Setting Scriptsmohitagw15856/pm-claude-skills | 1.4k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Wiki Maintaineropenclaw/openclaw | 392k | 1 repos | ~462 | Automated safety check: Pass | MIT | |
| Manage Settingsasgeirtj/system_prompts_leaks | 69k | — | ~3.1k | Automated safety check: Pass | CC0-1.0 | |
| Obsidian Vault Maintaineropenclaw/openclaw | 392k | 1 repos | ~262 | Automated safety check: Pass | MIT | |
| Openclaw PR Maintaineropenclaw/openclaw | 392k | — | ~2.3k | Automated safety check: Pass | MIT |
mohitagw15856/pm-claude-skills
Set a boundary with someone — a friend, family member, coworker, or partner — clearly and kindly, with the actual words and a plan for the pushback.
openclaw/openclaw
Maintain the OpenClaw memory wiki vault with deterministic pages, managed blocks, and source-backed updates.
asgeirtj/system_prompts_leaks
Any explicit Muse Code setting question or change (model, reasoning effort, /settings) requires a silent readskill call for bundled:manage-settings as FIRST ACTION—no assistant text or other tool…
openclaw/openclaw
Maintain an Obsidian-friendly memory wiki vault with wikilinks, frontmatter, and official Obsidian CLI awareness.
openclaw/openclaw
Review, triage, repair, or land OpenClaw issues and pull requests with current-source evidence and the native maintainer workflow.
warpdotdev/warp
Finds and changes Warp application settings by searching a bundled JSON schema and editing the matching TOML settings file at the right nesting depth.
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.
Setting and maintaining personal boundaries across all relationships. Boundaries Saying No is an agent skill from LeoYeAI/openclaw-master-skills. Setting and maintaining personal boundaries across all relationships.
Boundaries Saying No fits situations like: someone cant say no; feels constantly drained by others demands; is being guilt-tripped; needs to establish limits with family.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill boundaries-saying-no -a claude-code`. Or copy the skill folder (skills/boundaries-saying-no in LeoYeAI/openclaw-master-skills) into .claude/skills/boundaries-saying-no in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill boundaries-saying-no -a codex`. Or copy the skill folder (skills/boundaries-saying-no in LeoYeAI/openclaw-master-skills) into .agents/skills/boundaries-saying-no 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 boundaries-saying-no -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/boundaries-saying-no, .gemini/skills/boundaries-saying-no, .github/skills/boundaries-saying-no and .opencode/skills/boundaries-saying-no in your project.
SKILL.md names no scripts, command-line tools or credentials: Boundaries Saying No is instructions for the agent only. Our summary lists: Node.js.
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.
Boundaries Saying No is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.2k 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 Boundaries Saying No: Boundary Setting Scripts (mohitagw15856/pm-claude-skills, 1.4k stars), Wiki Maintainer (openclaw/openclaw, 392k stars), Manage Settings (asgeirtj/system_prompts_leaks, 69k stars) and Obsidian Vault Maintainer (openclaw/openclaw, 392k 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.