Physical Address
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing local business websites, e-commerce sites, or any site where a physical presence affects trust or local search visibility.
De-escalation techniques for in-person confrontations and tense physical situations.
$ npx skills add LeoYeAI/openclaw-master-skills --skill physical-de-escalation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills physical-de-escalation --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/physical-de-escalation .claude/skills/physical-de-escalation && 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 "physical-de-escalation" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/physical-de-escalation into .claude/skills/physical-de-escalation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "physical-de-escalation", 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/physical-de-escalationType 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 physical-de-escalation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills physical-de-escalation --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/physical-de-escalation .agents/skills/physical-de-escalation && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "physical-de-escalation" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/physical-de-escalation into .agents/skills/physical-de-escalation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "physical-de-escalation", 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 physical-de-escalation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills physical-de-escalation --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/physical-de-escalation .cursor/skills/physical-de-escalation && 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 "physical-de-escalation" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/physical-de-escalation into .cursor/skills/physical-de-escalation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "physical-de-escalation", 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/physical-de-escalation--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 physical-de-escalation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills physical-de-escalation --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/physical-de-escalation .gemini/skills/physical-de-escalation && 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 "physical-de-escalation" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/physical-de-escalation into .gemini/skills/physical-de-escalation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "physical-de-escalation", 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 physical-de-escalationInstalls 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 physical-de-escalation -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/physical-de-escalation .github/skills/physical-de-escalation && 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 "physical-de-escalation" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/physical-de-escalation into .github/skills/physical-de-escalation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "physical-de-escalation", 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 physical-de-escalation -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 physical-de-escalation --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/physical-de-escalation .opencode/skills/physical-de-escalation && 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 "physical-de-escalation" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/physical-de-escalation into .opencode/skills/physical-de-escalation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "physical-de-escalation", 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.
physical-de-escalationDe-escalation techniques for in-person confrontations and tense physical situations.
Physical De Escalation is an agent skill from LeoYeAI/openclaw-master-skills. De-escalation techniques for in-person confrontations and tense physical situations. Use when someone faces angry customers, aggressive strangers, workplace confrontations, or needs to calm a heated situation in a physical space.
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.
6 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.
Links to these hosts (documentation or services it may open):
crisisprevention.comosha.govanthropic.comFrom 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.
Physical De Escalation loads about 5.2k tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 746 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). 746 words, ~5,186 tokens.
.claude/skills/physical-de-escalation/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Most conflict advice focuses on what to say. This skill is about what to do with your body when you're in a room with someone who is angry, aggressive, or escalating. Body language, positioning, voice, and physical distance do more to de-escalate a confrontation than the perfect script. Retail workers, bartenders, nurses, teachers, and parents use these techniques every day. They work because they address the physiology of aggression — a person in fight-or-flight mode is responding to physical cues before they process words. Get the body language right and the words matter less. Get it wrong and even perfect words won't help.
# Localization note — cultural norms around conflict vary significantly
- Personal space expectations differ:
US/Northern Europe: ~4 feet conversational distance
Latin America/Middle East/Southern Europe: ~2-3 feet
East Asia: varies, but physical contact between strangers is rare
- Eye contact norms:
US/Western Europe: direct eye contact signals confidence/honesty
East Asia/some Indigenous cultures: prolonged eye contact can
signal aggression or disrespect
Adapt eye contact advice to cultural context.
- Physical gestures: open palms are near-universal as non-threatening,
but specific gestures vary (thumbs-up offensive in some cultures, etc.)
- Legal self-defense frameworks vary by jurisdiction:
US: varies by state (stand your ground vs. duty to retreat)
UK: "reasonable force" standard
Many jurisdictions: duty to retreat if safe to do so
- Emergency numbers: US 911, UK 999, AU 000, EU 112Agent action: Teach the user how to rapidly read a situation before responding.
5-SECOND THREAT ASSESSMENT:
When you encounter an agitated person, scan these five things
before you say or do anything:
1. HANDS — What are they doing with their hands?
Open and visible = lower threat
Clenched fists = escalating
Hands hidden / reaching into pockets or waistband = high alert
Holding an object (bottle, tool, bag) = potential weapon
2. STANCE — How is their body positioned?
Squared up facing you directly = confrontational
Bladed (one foot forward, angled) = preparing for action
Pacing or bouncing = adrenaline surge, escalating
Seated or leaning back = lower threat
3. FACE — What does their expression tell you?
Jaw clenched, nostrils flared = anger, escalating
Thousand-yard stare / flat affect = potentially most dangerous
Eyes scanning for witnesses/exits = calculating
Crying or trembling = distress, not necessarily aggression
4. VOICE — What's happening with their speech?
Loud and fast = adrenaline, fear, anger
Quiet and controlled + tense body = potentially more dangerous
than someone yelling
Repeating the same phrase = stuck in a loop, not processing
Slurred or erratic = substance influence (changes approach)
5. CONTEXT — What's the environment?
Are there exits? Other people? Objects that could be weapons?
Is the person cornered? (Cornered people are more dangerous.)
Are there children or vulnerable people present?
Is this person known to you, or a stranger?
THREAT LEVEL DECISION:
LOW: Person is upset but in control. Approach and de-escalate.
MEDIUM: Person is escalating, aggressive posture, yelling.
De-escalate but maintain distance and plan your exit.
HIGH: Pre-attack indicators present (see below). Do not engage.
Create distance. Call for help. Leave if possible.Agent action: Teach physical positioning for de-escalation.
YOUR BODY POSITION — THE MOST IMPORTANT VARIABLE:
THE 45-DEGREE ANGLE:
- NEVER stand face-to-face with an agitated person. Squaring up
is a primate dominance signal. It triggers escalation.
- Stand at a 45-degree angle to them. One foot slightly forward,
body angled. This is non-confrontational and also gives you
better balance and the ability to move quickly if needed.
THE REACTIONARY GAP:
- Maintain at least 6 feet (two arm-lengths) from an agitated
person. This is not about politeness — it's about reaction time.
- At 6 feet, you have roughly 1.5 seconds to react if they lunge.
At 3 feet, you have zero.
- If they close distance, step back. Don't hold your ground out
of pride. Moving back is a de-escalation tool, not weakness.
- If they keep closing distance after you've backed up twice,
this is a pre-attack indicator. Disengage entirely.
HAND POSITION:
- Hands visible at all times. Open palms. Below shoulder height.
- The "interview stance": hands in front of your body at chest
height, palms facing the person, fingers relaxed. This looks
non-threatening but is also a ready position.
- NEVER point your finger at them. Pointing is perceived as
aggressive in almost every culture on earth.
- NEVER cross your arms. It reads as dismissive or hostile.
- NEVER put hands on hips. It's a dominance display.
- NEVER put hands in your pockets. You can't react and they
can't see what you're doing.
YOUR FEET:
- Weight on the balls of your feet, not your heels.
- One foot slightly behind the other (not side by side).
- You should be able to move in any direction quickly.
- Don't lock your knees.
THE EXIT PRINCIPLE:
- Never let an agitated person get between you and the exit.
- Position yourself so you always have a clear path out.
- If you're in a room, move so the door is behind you or to
your side, not behind them.Agent action: Cover how to use voice and words to de-escalate.
VOICE MODULATION — MORE IMPORTANT THAN WORDS:
VOLUME: Match their energy at about 70%, then slowly bring yours
down. If they're yelling, don't whisper — they'll think you're
mocking them. Start slightly below their volume, then gradually
decrease. They will unconsciously follow.
PACE: Slow. Down. An agitated person speaks fast. You speak at
half their speed. Slow speech signals that no one is in danger,
which is the message you're sending to their nervous system.
PITCH: Low. High-pitched voices trigger anxiety. Drop your pitch
to the bottom of your comfortable range. Breathe from your
diaphragm, not your chest.
TONE: Calm, but not condescending. The difference between
de-escalation and patronizing is respect. You're not calming
a child. You're talking to a human who is overwhelmed.
VERBAL TECHNIQUES THAT WORK:
1. Acknowledge first, solve second:
"I can see you're frustrated, and I want to help."
NOT: "Calm down." (Never say "calm down." Ever. It has never
once in human history made anyone calm down.)
2. Use their name if you know it:
"Mark, I'm listening. Tell me what happened."
Names activate the part of the brain that processes identity,
which can pull someone out of pure fight-or-flight.
3. Ask open questions to get them talking:
"What happened?" "What do you need right now?"
Talking uses the prefrontal cortex. Rage uses the amygdala.
Getting them to narrate shifts brain activity.
4. Paraphrase back what they said:
"So you waited 45 minutes and nobody helped you. That's not
okay, and I understand why you're upset."
This proves you're listening, which is often the only thing
they actually want.
5. Offer limited choices (not unlimited ones):
"I can do X or Y for you. Which works better?"
Choices give them a sense of control, which is usually what
aggression is trying to reclaim.
6. Set limits calmly and clearly when needed:
"I want to help you, and I need you to stop yelling so I can.
Can we do that?"
Not a threat. A boundary stated as a collaboration.
PHRASES TO NEVER USE:
- "Calm down"
- "You need to relax"
- "That's not a big deal"
- "There's nothing I can do"
- "You're being unreasonable"
- "It's policy" (as a final answer — explain the why instead)
- "I don't get paid enough for this" (even if true)Agent action: Teach the user when de-escalation has failed and it's time to leave.
PRE-ATTACK INDICATORS — WHEN TO STOP TALKING AND START LEAVING:
These are physiological and behavioral signs that a person has
moved past anger into the decision to be violent. If you see
two or more of these, de-escalation has likely failed.
PHYSICAL SIGNS:
- Target glance: quick look at the spot they plan to hit (your
jaw, chest, or a vulnerable area), then back to your eyes
- Thousand-yard stare: eyes go flat, unfocused — they've stopped
processing your words and are in a physiological state
- Face flushes or goes pale (adrenaline dump)
- Jaw clenches, lips tighten or compress
- Fists clench and unclench repeatedly
- Shoulders rise (traps tensing for a strike)
- Blading: one foot steps back, body turns sideways (fighting
stance, whether they know it or not)
- Weight shifts to the balls of the feet
- Removes glasses, hat, or jacket (clearing obstructions)
- Stretching neck or rolling shoulders (loosening up)
BEHAVIORAL SIGNS:
- Sudden silence after prolonged yelling (they've made a decision)
- Ignoring everything you say (no longer processing language)
- Closing distance despite your attempts to maintain gap
- Scanning for witnesses (looking to see who's watching)
- Looking at potential weapons (bottles, chairs, tools)
IF YOU SEE THESE SIGNS:
1. Do NOT turn your back to them.
2. Create distance immediately. Back away at an angle.
3. Put a barrier between you (table, counter, car, anything).
4. Leave the space if you can.
5. Call for help (coworker, security, 911) loudly enough that
the aggressor knows others are aware of the situation.
6. If you cannot leave, protect your head and call for help.
YOUR SAFETY IS NOT NEGOTIABLE. No job, no argument, no
possession is worth a physical injury. Leave.Agent action: Walk through the most common real-world confrontation scenarios.
SCENARIO: ANGRY RETAIL/FOOD SERVICE CUSTOMER
- Position yourself behind the counter if possible (built-in barrier)
- Don't match their volume. Acknowledge their frustration.
- "I hear you. Let me see what I can do right now."
- If they won't de-escalate after two attempts, get a manager
(not because you can't handle it — because a new face resets
the dynamic)
- If they threaten violence, step away and call security/police.
You are not paid to absorb threats.
SCENARIO: BAR/NIGHTLIFE CONFRONTATION
- Don't engage in a dominance contest. The drunk brain wants to
win, not solve a problem.
- Speak to their friend, not them: "Hey, can you help your buddy
out? I think he needs some air." Friends are your best
de-escalation partner.
- If no friends: "Let me buy you some water, man. You look like
you need a minute." (Offering something shifts the dynamic.)
- Watch for the sucker punch — most bar assaults are not
telegraphed with a windup. Watch the shoulders, not the hands.
- Leave the venue if it's not resolving. Being "right" in a bar
fight means nothing.
SCENARIO: ROAD RAGE
- Do not get out of your car. Ever.
- Do not make eye contact (in this context it's a challenge).
- Do not gesture (even an apologetic wave can be misread).
- Drive to a well-lit, populated area (gas station, fire station,
police station) if someone is following you.
- If they approach your car at a stop, keep windows up, doors
locked. Drive away, even if it means running a red light.
- Call 911 if they're following you. Stay on the line.
SCENARIO: NEIGHBOR DISPUTE
- Address it early. Unresolved small conflicts escalate.
- Go to their door at a calm time, not in the heat of the moment.
- Lead with your experience, not their behavior:
"I've been having trouble sleeping because of noise after 11"
vs. "You're too loud at night."
- Propose a specific solution, not a demand.
- If they become aggressive, disengage: "I can see this isn't a
good time. I'll come back later." Then don't. Write a letter
instead if needed. Some situations are better in writing.
SCENARIO: FAMILY GATHERING ESCALATION
- Step out of the room. Invite the agitated person:
"Let's grab some air for a minute."
Changing the physical environment breaks the escalation cycle.
- Don't referee between two people arguing. Separate them first.
- Don't take sides publicly. Talk to each person individually.
- The phrase "You might be right" costs you nothing and de-
escalates almost anything. It's not agreeing — it's
acknowledging their perspective exists.Agent action: Cover how to safely intervene in someone else's confrontation.
BYSTANDER INTERVENTION (the 5 D's):
DIRECT: Address the aggressor directly.
"Hey, that's enough." Only use if you feel safe doing so and
the aggressor is not significantly larger/threatening.
DISTRACT: Create a distraction to break the dynamic.
Drop something loudly. Ask the victim for directions. Spill a
drink. "Excuse me, is this your car? I think it's getting
towed." The goal is interruption, not confrontation.
DELEGATE: Get someone else to help.
Find security, a manager, another bystander. "Can you call 911?
I'm going to stay here and keep an eye on this."
DELAY: If the confrontation has ended, check on the victim after.
"Are you okay? Do you need help?" This matters more than people
think. Witnessed violence with no follow-up is deeply isolating.
DOCUMENT: Record what's happening (phone video) IF it's safe
to do so and you're not the only person who can intervene
physically. Evidence helps later. But don't prioritize filming
over helping.
CRITICAL: Do not intervene physically unless someone is in
immediate danger and no other option exists. You don't know
if there's a weapon. You don't know the full situation. Call
professionals when possible.de_escalation:
user_context:
primary_scenario: null
work_environment: null
frequency_of_confrontations: null
has_de_escalation_training: false
skills_covered:
five_second_assessment: false
body_positioning: false
voice_modulation: false
verbal_techniques: false
pre_attack_indicators: false
scenario_protocols: false
bystander_intervention: false
incidents:
recent_confrontation: null
outcome: null
what_worked: null
what_didnt: null
follow_up:
training_recommendation: null
practice_scenarios_completed: []triggers:
- name: active_confrontation
condition: "user indicates they are currently in or just exited a confrontation"
action: "Are you safe right now? If you're still in the situation: create distance, keep your hands visible, speak slowly and calmly, and position yourself near an exit. If you've left the situation: take a few minutes to breathe and let your adrenaline come down before making any decisions."
- name: workplace_pattern
condition: "de_escalation.user_context.frequency_of_confrontations == 'frequent' AND de_escalation.user_context.has_de_escalation_training IS false"
action: "You're dealing with confrontations regularly at work without formal training. Your employer should be providing Crisis Prevention Institute (CPI) training or equivalent. It's typically a 1-2 day course that covers everything in this skill with hands-on practice. Want me to help you make the case to your manager?"
- name: post_incident_debrief
condition: "de_escalation.incidents.recent_confrontation IS SET AND de_escalation.incidents.outcome IS null"
action: "You mentioned a recent confrontation but we didn't debrief on how it went. What happened? What did you try? What worked and what didn't? This kind of review is how the skill actually develops."
- name: scenario_practice
condition: "de_escalation.skills_covered.verbal_techniques IS true AND de_escalation.follow_up.practice_scenarios_completed IS EMPTY"
action: "You've covered the de-escalation techniques. Want to practice with a scenario? I can describe a situation and you can talk through how you'd handle it — positioning, voice, and words. It's the closest thing to practice without a real confrontation."© 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/physical-de-escalation of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Physical De Escalation 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 |
|---|---|---|---|---|---|---|
| Physical De Escalation this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~5.2k | Automated safety check: Pass | MIT | |
| Physical Addressthedaviddias/Front-End-Checklist | 74k | — | ~574 | Automated safety check: Pass | MIT | |
| Adding Warehouse Person PropertiesPostHog/posthog | 40k | — | ~2.9k | Automated safety check: Pass | Custom licence | |
| Mapping Mitre Attack Techniquesmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Building Soc Escalation Matrixmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Anti Reversing Techniqueswshobson/agents | 40k | — | ~980 | Automated safety check: Pass | MIT |
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing local business websites, e-commerce sites, or any site where a physical presence affects trust or local search visibility.
PostHog/posthog
Sync columns from a synced data warehouse table onto PostHog person or group properties, so warehouse data becomes usable anywhere person and group properties already work: feature flag targeting…
mukul975/Anthropic-Cybersecurity-Skills
Maps observed adversary behaviors, security alerts, and detection rules to MITRE ATT&CK techniques and sub-techniques to quantify detection coverage and guide control prioritization.
mukul975/Anthropic-Cybersecurity-Skills
Build a structured SOC escalation matrix defining severity tiers, response SLAs, tiered escalation paths, and notification procedures for security incidents, using context-driven criteria that…
wshobson/agents
Understand anti-reversing, obfuscation, and protection techniques encountered during software analysis.
THU-MAIC/OpenMAIC
Derives a reusable personal skill for course-making from a representative sample of the user's own past classrooms and chat history, confirmed with them before saving.
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.
De-escalation techniques for in-person confrontations and tense physical situations. Physical De Escalation is an agent skill from LeoYeAI/openclaw-master-skills. De-escalation techniques for in-person confrontations and tense physical situations.
Physical De Escalation fits situations like: someone faces angry customers; aggressive strangers; workplace confrontations; needs to calm a heated situation in a physical space.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill physical-de-escalation -a claude-code`. Or copy the skill folder (skills/physical-de-escalation in LeoYeAI/openclaw-master-skills) into .claude/skills/physical-de-escalation in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill physical-de-escalation -a codex`. Or copy the skill folder (skills/physical-de-escalation in LeoYeAI/openclaw-master-skills) into .agents/skills/physical-de-escalation 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 physical-de-escalation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/physical-de-escalation, .gemini/skills/physical-de-escalation, .github/skills/physical-de-escalation and .opencode/skills/physical-de-escalation in your project.
SKILL.md names no scripts, command-line tools or credentials: Physical De Escalation is instructions for the agent only. Our summary lists: Node.js.
SKILL.md names 3 domains. As links in the text: crisisprevention.com, osha.gov and anthropic.com. 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.
Physical De Escalation 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 Physical De Escalation: Physical Address (thedaviddias/Front-End-Checklist, 74k stars), Adding Warehouse Person Properties (PostHog/posthog, 40k stars), Mapping Mitre Attack Techniques (mukul975/Anthropic-Cybersecurity-Skills, 34k stars) and Building Soc Escalation Matrix (mukul975/Anthropic-Cybersecurity-Skills, 34k 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.