Daily
sickn33/agentic-awesome-skills
Documentation and capabilities reference for Daily. An agent skill from sickn33/agentic-awesome-skills.
Daily protection and relapse prevention companion for people in recovery.
$ npx skills add curiositech/some_claude_skills --skill sober-addict-protector -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install curiositech/some_claude_skills sober-addict-protector --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/curiositech/some_claude_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/sober-addict-protector .claude/skills/sober-addict-protector && 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 "sober-addict-protector" agent skill from https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/sober-addict-protector into .claude/skills/sober-addict-protector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sober-addict-protector", 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/curiositech/some_claude_skills/tree/main/.claude/skills/sober-addict-protectorType 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 curiositech/some_claude_skills --skill sober-addict-protector -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install curiositech/some_claude_skills sober-addict-protector --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/curiositech/some_claude_skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/sober-addict-protector .agents/skills/sober-addict-protector && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "sober-addict-protector" agent skill from https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/sober-addict-protector into .agents/skills/sober-addict-protector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sober-addict-protector", 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 curiositech/some_claude_skills --skill sober-addict-protector -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install curiositech/some_claude_skills sober-addict-protector --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/curiositech/some_claude_skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/sober-addict-protector .cursor/skills/sober-addict-protector && 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 "sober-addict-protector" agent skill from https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/sober-addict-protector into .cursor/skills/sober-addict-protector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sober-addict-protector", 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/curiositech/some_claude_skills.git --path .claude/skills/sober-addict-protector--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 curiositech/some_claude_skills --skill sober-addict-protector -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install curiositech/some_claude_skills sober-addict-protector --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/curiositech/some_claude_skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/sober-addict-protector .gemini/skills/sober-addict-protector && 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 "sober-addict-protector" agent skill from https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/sober-addict-protector into .gemini/skills/sober-addict-protector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sober-addict-protector", 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 curiositech/some_claude_skills sober-addict-protectorInstalls 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 curiositech/some_claude_skills --skill sober-addict-protector -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/curiositech/some_claude_skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/sober-addict-protector .github/skills/sober-addict-protector && 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 "sober-addict-protector" agent skill from https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/sober-addict-protector into .github/skills/sober-addict-protector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sober-addict-protector", 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 curiositech/some_claude_skills --skill sober-addict-protector -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install curiositech/some_claude_skills sober-addict-protector --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/curiositech/some_claude_skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/sober-addict-protector .opencode/skills/sober-addict-protector && 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 "sober-addict-protector" agent skill from https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/sober-addict-protector into .opencode/skills/sober-addict-protector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sober-addict-protector", 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.
sober-addict-protectorDaily protection and relapse prevention companion for people in recovery.
Sober Addict Protector is an agent skill from curiositech/some_claude_skills. Daily protection and relapse prevention companion for people in recovery. Expert in identifying high-risk situations, managing triggers, maintaining accountability, encouraging therapy/couples counseling investment, and building sustainable recovery habits. Activate on "relapse prevention", "staying sober", "trigger management", "recovery daily", "sobriety check-in", "high risk situation", "couples therapy recovery", "protect sobriety". NOT for active crisis (call 988 or your sponsor), prescribing medications…
Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `.claude-plugin/plugin.json` and `references/couples-therapy-resources.md`).
The repository describes itself as: Claude skills that make my life easier. The licence is MIT.
Read from SKILL.md and the folder at commit 6713fc7. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditWebFetchFrom 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.
Sober Addict Protector loads about 3.3k tokens when it runs, and up to ~6.6k if it reads all its reference files. Until then it costs about 148 tokens; SKILL.md has 389 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 curiositech/some_claude_skills at commit 6713fc7, republished under its MIT licence (© curiositech). 389 words, ~3,332 tokens.
.claude/skills/sober-addict-protector/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.Daily companion for protecting your sobriety through proactive strategies, trigger management, and sustainable recovery practices.
Use for:
NOT for:
┌─────────────────────────────────────────────────────────────────┐
│ DAILY PROTECTION CHECK │
├─────────────────────────────────────────────────────────────────┤
│ │
│ MORNING │
│ ├── How did I sleep? (1-10) │
│ ├── What's my emotional state? (name 3 feelings) │
│ ├── Any triggers expected today? │
│ └── What's my protection plan? │
│ │
│ MIDDAY │
│ ├── Am I HALT? (Hungry, Angry, Lonely, Tired) │
│ ├── Any cravings? (rate 1-10) │
│ └── Have I connected with support today? │
│ │
│ EVENING │
│ ├── Did anything catch me off guard? │
│ ├── What worked well today? │
│ ├── Am I set up for a safe tomorrow? │
│ └── Gratitude: 3 things │
│ │
└─────────────────────────────────────────────────────────────────┘H - HUNGRY
├── Blood sugar drops trigger irritability and poor decisions
├── Skipping meals is a warning sign
└── Action: Eat something nutritious within 30 minutes
A - ANGRY
├── Unprocessed anger is a major relapse trigger
├── "I deserve to use" thinking emerges
└── Action: Call someone, write it out, move your body
L - LONELY
├── Isolation is the petri dish of relapse
├── "No one understands" thinking
└── Action: Reach out even when you don't want to
T - TIRED
├── Exhaustion erodes willpower
├── Decision-making suffers
└── Action: Rest if possible, reduce demands on yourself
S - STRESSED
├── Chronic stress depletes coping resources
├── "I need to take the edge off"
└── Action: Use stress reduction skills, reassess workload
+ SICK
├── Physical illness triggers vulnerability
├── Be extra careful with prescribed medications
└── Action: Tell your doctor about your recovery statusBefore entering ANY environment, ask:
☐ Will substances be present?
☐ Will people who use be there?
☐ Can I leave if I need to?
☐ Does anyone know where I am?
☐ Do I have my escape plan?
☐ What's my reason for going?
☐ Am I in a good headspace?
If more than 2 boxes are concerning → RECONSIDER or PREPARE HEAVILYWhen craving hits:
1. DELAY (15-30 minutes)
├── Cravings peak and pass
├── Set a timer if needed
└── "I'll decide in 20 minutes"
2. DISTRACT
├── Physical activity (even a walk)
├── Call someone in recovery
├── Cold water on face/hands
├── Play the tape forward
└── Change your environment
3. DECIDE (from a calmer place)
├── "Is this what I really want?"
├── "What happens tomorrow?"
└── "What would future me thank me for?"When romanticizing use:
"If I use right now..."
├── First 10 minutes: [brief relief, familiar feeling]
├── 1 hour later: [guilt, shame, hiding it]
├── Tomorrow: [hangover/withdrawal, broken promises]
├── 1 week later: [deeper hole, more damage]
├── 1 month later: [possibly back where I started or worse]
Now ask: "Is the first 10 minutes worth all that follows?""I notice I'm having a craving."
"This is uncomfortable, but it's just a feeling."
"I'm going to observe it without fighting it."
Rate intensity: [1-10]
Where do I feel it? [body location]
"I'm breathing into this sensation."
"Like a wave, it will rise... peak... and fall."
"I don't have to act on it."
"I'm just going to wait and watch."
[After 15-30 minutes]
"The intensity has shifted to: [1-10]"
"I survived this without using."
"Every time I do this, I get stronger."If you're in a relationship and in recovery:
THE REALITY:
├── Your addiction affected your partner
├── Trust was damaged
├── Communication patterns are broken
├── Your partner may have their own trauma
├── Codependency patterns need addressing
├── Recovery changes the relationship dynamic
└── BOTH of you need support
THE RISK OF SKIPPING:
├── Unaddressed resentment builds
├── Partner may not know how to support you
├── Old patterns repeat
├── Relationship stress → relapse trigger
├── Partner burnout → relationship failure
└── Kids (if any) see unhealthy patterns continue
THE BENEFIT OF INVESTING:
├── Structured space to rebuild trust
├── Learn healthy communication
├── Process hurt WITH professional support
├── Both partners feel heard
├── Build a relationship that SUPPORTS recovery
└── Model healthy relationships for childrenFinancial barriers are real. Here are options:
├── Ask your treatment center for referrals
├── Community mental health centers (sliding scale)
├── Training clinics at universities (supervised students)
├── EAP through employer (often free sessions)
├── Online therapy (often cheaper)
├── Group couples therapy (if available)
├── Al-Anon/Nar-Anon + your program (free, different from therapy)
└── INVEST what you would have spent on substances
Key truth: The cost of NOT doing couples therapy
often exceeds the cost of divorce.General timeline:
├── First 30 days: Focus on individual stability
├── 30-90 days: May introduce family/couples work if stable
├── After 90 days: Couples therapy becomes more important
Signs you need it NOW:
├── Partner threatening to leave
├── Constant conflict at home
├── Partner is triggered by your recovery activities
├── Communication has completely broken down
├── One or both of you are "walking on eggshells""I'm in meetings/groups, why do I need individual therapy?"
Groups provide:
├── Peer support
├── Accountability
├── Shared experience
└── Community
Individual therapy provides:
├── Personalized attention to YOUR patterns
├── Trauma processing (can't do deeply in groups)
├── Underlying issues (anxiety, depression, ADHD)
├── Skill building specific to your triggers
└── Privacy for sensitive topics
BOTH are important. They're not interchangeable."I don't need therapy, I just need to stay sober"
→ Underlying issues will resurface if not addressed
→ Many people relapse because they stop at abstinence
"I can't be that vulnerable"
→ Vulnerability in a safe space builds strength
→ Start slow, trust builds over time
"It's too expensive"
→ What does a relapse cost? (Money, relationships, job, health)
→ Explore sliding scale options
"I don't click with my therapist"
→ Finding the right fit matters
→ It's okay to try different therapists
→ But also give it a few sessions before decidingTHE BIG 5 (do these every single day):
├── 1. Connect with recovery support
│ (meeting, sponsor call, recovery friend)
├── 2. Recovery reading or reflection
│ (10 minutes minimum)
├── 3. Physical movement
│ (exercise, walk, any movement)
├── 4. Regular meals
│ (blood sugar stability = emotional stability)
└── 5. Consistent sleep schedule
(sleep deprivation is a major risk factor)WEEKLY MINIMUMS:
├── At least 3 meetings/support groups
├── Sponsor/mentor contact
├── Therapy session (if in individual)
├── Self-care activity (not screens)
├── Review your relapse prevention plan
└── Check in on home relationship healthIf you came close to using but didn't:
FIRST: You didn't use. Acknowledge that.
THEN PROCESS:
├── What was the trigger?
├── What warning signs did I miss?
├── What eventually stopped me?
├── What can I learn from this?
├── Who do I need to tell? (sponsor, therapist)
└── What needs to change to prevent next time?
IMPORTANT:
├── A close call is NOT failure
├── It's information
├── Don't shame yourself into silence
├── Tell someone who will support, not judge
└── Update your relapse prevention planLAPSE: A brief return to use followed by return to recovery
RELAPSE: Full return to addictive patterns
If you lapse:
├── Stop using immediately
├── Tell someone (sponsor, therapist, trusted person)
├── Don't "might as well" continue
├── Get back to recovery activities TODAY
├── Increase support temporarily
└── Process what happened without shame
Key: A lapse doesn't have to become a relapse.
But secrecy and shame fuel progression.CONCERNING PATTERNS:
├── Partner brings substances into the home
├── Partner dismisses your recovery ("one drink won't hurt")
├── Constant conflict without resolution
├── Walking on eggshells around each other
├── Partner hasn't addressed their own issues
├── Mutual resentment building
├── You hide things from partner
├── Partner controls your recovery activities
└── Feeling worse at home than in treatment
WHAT TO DO:
├── Name the pattern to yourself
├── Discuss with counselor/sponsor first
├── Request couples therapy
├── Set clear boundaries
├── Assess if the relationship supports or threatens recovery
└── Remember: Your recovery must be protectedPattern: After feeling good for a while, believing you've beat addiction. Danger: Leads to dropping recovery activities, thinking you can moderate. Reality: Recovery is ongoing. The "cured" feeling is a success of recovery, not its conclusion.
Pattern: Stopping meetings, therapy, sponsor contact because "I've got this." Danger: Isolation returns, skills atrophy, support network fades. Reality: Connection is protective, not remedial. Maintain it.
Pattern: Rationalizing one-time use for a special occasion or to "test" yourself. Danger: Addiction doesn't work that way. One use can trigger cascade. Reality: There's no "just this once" for a brain with addiction patterns.
Pattern: Refusing to tell partner, family, or close friends about recovery. Danger: Secrecy breeds shame; uninformed people can't support you. Reality: Appropriate disclosure to close people increases success.
Core Philosophy: Relapse is not required in recovery, but close calls are common. This skill exists to help you see risks before they become crises, maintain the practices that protect you, and remember that investing in therapy—especially couples therapy—is not optional if you want long-term recovery AND relationships.
Every day sober is a day won. Protect it.
© curiositech, 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 (references) in .claude/skills/sober-addict-protector of curiositech/some_claude_skills.
Open the folder on GitHubat commit 6713fc7
Sober Addict Protector 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 |
|---|---|---|---|---|---|---|
| Sober Addict Protector this skillcuriositech/some_claude_skills | 243 | — | ~3.3k | Automated safety check: Pass | MIT | |
| Dailysickn33/agentic-awesome-skills | 47k | 3 repos | ~3.6k | Automated safety check: Pass | MIT | |
| Backup Recoverysickn33/agentic-awesome-skills | 47k | 2 repos | ~3k | Automated safety check: Warn | MIT | |
| Disaster Recoverysickn33/agentic-awesome-skills | 47k | 2 repos | ~3k | Automated safety check: Pass | MIT | |
| Implementing Memory Protection With Dep Aslrmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Testing Ransomware Recovery Proceduresmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 |
sickn33/agentic-awesome-skills
Documentation and capabilities reference for Daily. An agent skill from sickn33/agentic-awesome-skills.
sickn33/agentic-awesome-skills
Implement backup and recovery strategies. An agent skill from sickn33/agentic-awesome-skills.
sickn33/agentic-awesome-skills
Implement disaster recovery strategies and runbooks. An agent skill from sickn33/agentic-awesome-skills.
mukul975/Anthropic-Cybersecurity-Skills
Implements memory protection mechanisms including DEP (Data Execution Prevention), ASLR (Address Space Layout Randomization), CFG (Control Flow Guard), and other exploit mitigations to prevent…
mukul975/Anthropic-Cybersecurity-Skills
Tests and validates ransomware recovery procedures - backup restore operations (e.g.
sickn33/agentic-awesome-skills
Research LinkedIn professional profiles and public business-contact data, including email/phone lookup, people search, and YouTube channel business-email discovery.
curiositech/some_claude_skills
Detect crisis signals in user content using NLP, mental health sentiment analysis, and safe intervention protocols.
curiositech/some_claude_skills
End-to-end form handling with react-hook-form, Zod schemas, validation patterns, error messaging, field arrays, and multi-step wizards.
curiositech/some_claude_skills
Build production CI/CD pipelines with GitHub Actions. An agent skill from curiositech/some_claude_skills.
curiositech/some_claude_skills
Expert in background job processing with Bull/BullMQ (Redis), Celery, and cloud queues.
curiositech/some_claude_skills
Strategic analyst that maps competitive landscapes, identifies white space opportunities, and provides positioning recommendations.
curiositech/some_claude_skills
Build production computer vision pipelines for object detection, tracking, and video analysis.
Daily protection and relapse prevention companion for people in recovery. Sober Addict Protector is an agent skill from curiositech/some_claude_skills. Daily protection and relapse prevention companion for people in recovery.
Sober Addict Protector fits situations like: sobriety check-in; high risk situation; couples therapy recovery; protect sobriety.
Run `npx skills add curiositech/some_claude_skills --skill sober-addict-protector -a claude-code`. Or copy the skill folder (.claude/skills/sober-addict-protector in curiositech/some_claude_skills) into .claude/skills/sober-addict-protector in your project. Claude Code loads it when a task matches its description.
Run `npx skills add curiositech/some_claude_skills --skill sober-addict-protector -a codex`. Or copy the skill folder (.claude/skills/sober-addict-protector in curiositech/some_claude_skills) into .agents/skills/sober-addict-protector 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 curiositech/some_claude_skills --skill sober-addict-protector -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sober-addict-protector, .gemini/skills/sober-addict-protector, .github/skills/sober-addict-protector and .opencode/skills/sober-addict-protector in your project.
SKILL.md names no scripts, command-line tools or credentials: Sober Addict Protector is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, WebFetch.
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.
Sober Addict Protector is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.2k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Sober Addict Protector: Daily (sickn33/agentic-awesome-skills, 47k stars), Backup Recovery (sickn33/agentic-awesome-skills, 47k stars), Disaster Recovery (sickn33/agentic-awesome-skills, 47k stars) and Implementing Memory Protection With Dep Aslr (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.
curiositech (a GitHub organization) maintains it in curiositech/some_claude_skills, which has 243 GitHub stars. The repository holds 95 skills in this directory. The repository was last updated on September 6, 2026.
Source: curiositech/some_claude_skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.