Back to Skills

Loop

Start an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly). Uses CronCreate for scheduling. Use when the user runs /ar:loop or asks to run an autoresearch experiment continuously on a schedule.

ai
By alirezarezvani
19k2.7kUpdated 3 days agoPythonMIT

Skill Content

# /ar:loop — Autonomous Experiment Loop

Start a recurring experiment loop that runs at a user-selected interval.

## Usage

```
/ar:loop engineering/api-speed             # Start loop (prompts for interval)
/ar:loop engineering/api-speed 10m         # Every 10 minutes
/ar:loop engineering/api-speed 1h          # Every hour
/ar:loop engineering/api-speed daily       # Daily at ~9am
/ar:loop engineering/api-speed weekly      # Weekly on Monday ~9am
/ar:loop engineering/api-speed monthly     # Monthly on 1st ~9am
/ar:loop stop engineering/api-speed        # Stop an active loop
```

## What It Does

### Step 1: Resolve experiment

If no experiment specified, list experiments and let user pick.

### Step 2: Select interval

If interval not provided as argument, present options:

```
Select loop interval:
  1. Every 10 minutes  (rapid — stay and watch)
  2. Every hour         (background — check back later)
  3. Daily at ~9am      (overnight experiments)
  4. Weekly on Monday   (long-running experiments)
  5. Monthly on 1st     (slow experiments)
```

Map to cron expressions:

| Interval | Cron Expression | Shorthand |
|----------|----------------|-----------|
| 10 minutes | `*/10 * * * *` | `10m` |
| 1 hour | `7 * * * *` | `1h` |
| Daily | `57 8 * * *` | `daily` |
| Weekly | `57 8 * * 1` | `weekly` |
| Monthly | `57 8 1 * *` | `monthly` |

### Step 3: Create the recurring job

Use `CronCreate` with this prompt (fill in the experiment details):

```
You are running autoresearch experiment "{domain}/{name}".

1. Read .autoresearch/{domain}/{name}/config.cfg for: target, evaluate_cmd, metric, metric_direction
2. Read .autoresearch/{domain}/{name}/program.md for strategy and constraints
3. Read .autoresearch/{domain}/{name}/results.tsv for experiment history
4. Run: git checkout autoresearch/{domain}/{name}

Then do exactly ONE iteration:
- Review results.tsv: what worked, what failed, what hasn't been tried
- Edit the target file with ONE change (strategy escalation based on run count)
- Commit: git add {target} && git commit -m "experiment: {description}"
- Evaluate: python {skill_path}/scripts/run_experiment.py --experiment {domain}/{name} --single
- Read the output (KEEP/DISCARD/CRASH)

Rules:
- ONE change per experiment
- NEVER modify the evaluator
- If 5 consecutive crashes in results.tsv, delete this cron job (CronDelete) and alert
- After every 10 experiments, update Strategy section of program.md

Current best metric: {read from results.tsv or "no baseline yet"}
Total experiments so far: {count from results.tsv}
```

### Step 4: Store loop metadata

Write to `.autoresearch/{domain}/{name}/loop.json`:

```json
{
  "cron_id": "{id from CronCreate}",
  "interval": "{user selection}",
  "started": "{ISO timestamp}",
  "experiment": "{domain}/{name}"
}
```

### Step 5: Confirm to user

```
Loop started for {domain}/{name}
  Interval: {interval description}
  Cron ID: {id}
  Auto-expires: 3 days (CronCreate limit)

  To check progress: /ar:status
  To stop the loop:  /ar:loop stop {domain}/{name}

  Note: Recurring jobs auto-expire after 3 days.
  Run /ar:loop again to restart after expiry.
```

## Stopping a Loop

When user runs `/ar:loop stop {experiment}`:

1. Read `.autoresearch/{domain}/{name}/loop.json` to get the cron ID
2. Call `CronDelete` with that ID
3. Delete `loop.json`
4. Confirm: "Loop stopped for {experiment}. {n} experiments completed."

## Important Limitations

- **3-day auto-expiry**: CronCreate jobs expire after 3 days. For longer experiments, the user must re-run `/ar:loop` to restart. Results persist — the new loop picks up where the old one left off.
- **One loop per experiment**: Don't start multiple loops for the same experiment.
- **Concurrent experiments**: Multiple experiments can loop simultaneously ONLY if they're on different git branches (which they are by default — each experiment gets `autoresearch/{domain}/{name}`).

How to use

  1. Copy the skill content above
  2. Create a .claude/skills directory in your project
  3. Save as .claude/skills/claude-skills-loop.md
  4. Use /claude-skills-loop in Claude Code to invoke this skill

Claude Code Skills & Plugins — Agent Skills for Every Coding Tool

345 production-ready Claude Code skills, plugins, and agent skills for 13 AI coding tools.

The most comprehensive open-source library of Claude Code skills and agent plugins — also works with OpenAI Codex, Gemini CLI, Cursor, and 9 more coding agents. Reusable expertise packages covering engineering, DevOps, marketing (incl. AEO — Answer Engine Optimization for LLM citation), security (PreToolUse hooks), compliance, C-level advisory (incl. founder-mode CFO/CMO/CRO/CPO/COO/CHRO/CISO/GC/CDO/CAIO/CCO/VPE personas + 21 /cs:* slash commands), productivity (capture/email/reflect), an academic research stack (litreview/grants/dossier/patent/syllabus/pulse/notebooklm + hybrid router), and enterprise Research Operations (clinical-research/research-finance/market-research/product-research, v2.9.0).

Works with: Claude Code · OpenAI Codex · Gemini CLI · OpenClaw · Hermes Agent1 · Mistral Vibe2 · Cursor · Aider · Windsurf · Kilo Code · OpenCode · Augment · Antigravity

License: MIT Skills Agents Personas Commands Stars SkillCheck Validated

5,200+ GitHub stars — the most comprehensive open-source Claude Code skills & agent plugins library.


What Are Claude Code Skills & Agent Plugins?

Claude Code skills (also called agent skills or coding agent plugins) are modular instruction packages that give AI coding agents domain expertise they don't have out of the box. Each skill includes:

  • SKILL.md — structured instructions, workflows, and decision frameworks
  • Python tools — 579 CLI scripts (all stdlib-only, zero pip installs)
  • Reference docs — 702 templates, checklists, and domain-specific knowledge files

One repo, thirteen platforms. Works natively as Claude Code plugins, Codex agent skills, Gemini CLI skills, Hermes Agent skills, Mistral Vibe skills, and converts to more tools via scripts/convert.sh. All 579 Python tools run anywhere Python runs.

Skills vs Agents vs Personas

SkillsAgentsPersonas
PurposeHow to execute a taskWhat task to doWho is thinking
ScopeSingle domainSingle domainCross-domain
VoiceNeutralProfessionalPersonality-driven
Example"Follow these steps for SEO""Run a security audit""Think like a startup CTO"

All three work together. See Orchestration for how to combine them.


Quick Install

Gemini CLI (New)

# Clone the repository
git clone https://github.com/alirezarezvani/claude-skills.git
cd claude-skills

# Run the setup script
./scripts/gemini-install.sh

# Start using skills
> activate_skill(name="senior-architect")

Claude Code (Recommended)

# Add the marketplace
/plugin marketplace add alirezarezvani/claude-skills

# Install by domain
/plugin install engineering-skills@claude-code-skills          # 24 core engineering
/plugin install engineering-advanced-skills@claude-code-skills  # 25 POWERFUL-tier
/plugin install product-skills@claude-code-skills               # 12 product skills
/plugin install marketing-skills@claude-code-skills             # 43 marketing skills
/plugin install ra-qm-skills@claude-code-skills                 # 12 regulatory/quality
/plugin install pm-skills@claude-code-skills                    # 6 project management
/plugin install c-level-skills@claude-code-skills               # 28 C-level advisory (full C-suite)
/plugin install business-growth-skills@claude-code-skills       # 4 business & growth
/plugin install finance-skills@claude-code-skills               # 2 finance (analyst + SaaS metrics)

# Or install individual skills
/plugin install skill-security-auditor@claude-code-skills       # Security scanner
/plugin install playwright-pro@claude-code-skills                  # Playwright testing toolkit
/plugin install self-improving-agent@claude-code-skills         # Auto-memory curation
/plugin install content-creator@claude-code-skills              # Single skill

OpenAI Codex

npx agent-skills-cli add alirezarezvani/claude-skills --agent codex
# Or: git clone + ./scripts/codex-install.sh

OpenClaw

bash <(curl -s https://raw.githubusercontent.com/alirezarezvani/claude-skills/main/scripts/openclaw-install.sh)

Manual Installation

git clone https://github.com/alirezarezvani/claude-skills.git
# Copy any skill folder to ~/.claude/skills/ (Claude Code) or ~/.codex/skills/ (Codex)

Multi-Tool Support (New)

Convert all 345 skills to 9 AI coding tools with a single script:

ToolFormatInstall
Cursor.mdc rules./scripts/install.sh --tool cursor --target .
AiderCONVENTIONS.md./scripts/install.sh --tool aider --target .
Kilo Code.kilocode/rules/./scripts/install.sh --tool kilocode --target .
Windsurf.windsurf/skills/./scripts/install.sh --tool windsurf --target .
OpenCode.opencode/skills/./scripts/install.sh --tool opencode --target .
Augment.augment/rules/./scripts/install.sh --tool augment --target .
Antigravity~/.gemini/antigravity/skills/./scripts/install.sh --tool antigravity
Hermes Agent~/.hermes/skills/python scripts/sync-hermes-skills.py --verbose
Mistral Vibe~/.vibe/skills/./scripts/vibe-install.sh

How it works:

# 1. Convert all skills to all tools (takes ~15 seconds)
./scripts/convert.sh --tool all

# 2. Install into your project (with confirmation)
./scripts/install.sh --tool cursor --target /path/to/project

# Or use --force to skip confirmation:
./scripts/install.sh --tool aider --target . --force

# 3. Verify
find .cursor/rules -name "*.mdc" | wc -l  # Should show 346

Each tool gets:

  • ✅ All 345 skills converted to native format
  • ✅ Per-tool README with install/verify/update steps
  • ✅ Support for scripts, references, templates where applicable
  • ✅ Zero manual conversion work

Run ./scripts/convert.sh --tool all to generate tool-specific outputs locally.


Skills Overview

345 skills across 17 domains:

DomainSkillsHighlightsDetails
🔧 Engineering — Core51Architecture, frontend, backend, fullstack, QA, DevOps, SecOps, AI/ML, data, Playwright Pro (test gen, flaky fix, migrations), self-improving agent (auto-memory curation), security suite, a11y auditengineering-team/
⚡ Engineering — POWERFUL78Agent designer, RAG architect, database designer, CI/CD builder, security auditor, MCP builder, AgentHub, Helm charts, Terraform, self-eval, llm-wiki, tc-tracker, autoresearch-agent, reliability portfolio (feature-flags-architect, kubernetes-operator, chaos-engineering, slo-architect), ship-gate, security-guidance PreToolUse hook, Matt Pocock skills (write-a-skill, caveman, grill-me, handoff, grill-with-docs)engineering/
🎯 Product17Product manager, agile PO, strategist, UX researcher, UI design, landing pages, SaaS scaffolder, analytics, experiment designer, discovery, roadmap communicator, code-to-prd, apple-hig-expertproduct-team/
📣 Marketing468 pods: Content, SEO + AEO (aeo — E-E-A-T audit, citation tracking across 5 LLMs), CRO, Channels, Growth, Intelligence, Sales + context foundation + orchestration routermarketing-skill/
🚀 Productivity6capture (brain-dump-to-action), email pair (inbox-setup + inbox-triage), reflect (journal), handoff (Matt Pocock-inspired), andreessen (market-first decision mode)productivity/
🎨 Marketing (top-level)1landing — single-file HTML landing-page generator (4 design styles, GSAP patterns, brand palette validator)marketing/
🔬 Research (academic)8research orchestrator (hybrid router + fallback) + 7 specialists: pulse, litreview, grants (NIH), dossier, patent, syllabus, notebooklmresearch/
🧪 Research Operations ✨v2.9.05Enterprise/cross-functional research: orchestrator + clinical-research (study design), research-finance (R&D program finance), market-research (sizing/survey/segmentation), product-research (user research) — each with onboarding + customization + opt-in autoresearch bridgeresearch-ops/
📋 Project Management9Senior PM, scrum master, Jira, Confluence, Atlassian admin, templates + bundled Atlassian Remote MCPproject-management/
🏥 Regulatory & QM18ISO 13485, MDR 2017/745, FDA, ISO 27001, GDPR, SOC 2, CAPA, risk managementra-qm-team/
🛡️ Compliance OS9Compliance operating system — controls, evidence, audit-readiness workflowscompliance-os/
💼 C-Level Advisory66Full C-suite (CEO/CTO/CFO/CMO/CRO/CPO/COO/CHRO/CISO/GC/CDO/CAIO/CCO/VPE) + founder-mode agents + orchestration + board meetings + culture & collaborationc-level-advisor/
📈 Business & Growth5Customer success, sales engineer, revenue ops, contracts & proposals, BizDev toolkitbusiness-growth/
🏭 Business Operations7Orchestrator + process-mapper, vendor-management, capacity-planner, internal-comms, knowledge-ops, procurement-optimizerbusiness-operations/
🤝 Commercial8Orchestrator + pricing-strategist, deal-desk, partnerships-architect, channel-economics, commercial-policy, rfp-responder, commercial-forecastercommercial/
💰 Finance4Financial analyst (DCF, budgeting, forecasting), SaaS metrics coach, business investment advisorfinance/

Personas

Pre-configured agent identities with curated skill loadouts, workflows, and distinct communication styles. Personas go beyond "use these skills" — they define how an agent thinks, prioritizes, and communicates.

PersonaDomainBest For
Startup CTOEngineering + StrategyArchitecture decisions, tech stack selection, team building, technical due diligence
Growth MarketerMarketing + GrowthContent-led growth, launch strategy, channel optimization, bootstrapped marketing
Solo FounderCross-domainOne-person sta

Footnotes

  1. Hermes Agent is BYO-sync tier: the repo ships a pre-generated .hermes/skills/claude-skills/ tree, but you run python scripts/sync-hermes-skills.py once locally to install into ~/.hermes/skills/. Uses the same agentskills.io SKILL.md standard — no format conversion.

  2. Mistral Vibe is also BYO-sync tier: the repo ships a pre-generated .vibe/skills/claude-skills/ tree, run ./scripts/vibe-install.sh once locally to install into ~/.vibe/skills/. Same agentskills.io SKILL.md standard — no format conversion. Docs: https://docs.mistral.ai/mistral-vibe/agents-skills.

View source on GitHub