Best use case
shark-loop is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Run shark.ps1/shark.sh loop enforcer with OS-level timeout per turn
Teams using shark-loop should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/shark-loop/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How shark-loop Compares
| Feature / Agent | shark-loop | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Run shark.ps1/shark.sh loop enforcer with OS-level timeout per turn
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Shark Loop (External Enforcer) Run the shark loop enforcer script which wraps `claude --print` with a hard OS-level timeout per turn. ## Instructions Parse the arguments: - The main text is the TASK_DESCRIPTION - `--max-loops N` sets SHARK_MAX_LOOPS (default: 50) - `--timeout S` sets SHARK_LOOP_TIMEOUT in seconds (default: 25) On Windows (PowerShell), run: ```powershell $env:SHARK_MAX_LOOPS = "<N>" $env:SHARK_LOOP_TIMEOUT = "<S>" & "$SKILL_DIR\..\shark.ps1" "<TASK_DESCRIPTION>" ``` On Linux/Mac, run: ``` SHARK_MAX_LOOPS=<N> SHARK_LOOP_TIMEOUT=<S> bash "$SKILL_DIR/../shark.sh" "<TASK_DESCRIPTION>" ``` Report the result when complete.
Related Skills
shark-exec
No description provided.
shark-status
Check status of shark-exec background jobs, .shark-done, and SHARK_LOG.md
shark-clean
Clean up shark state files (.shark-done, SHARK_LOG.md, pending.json, timings.jsonl)
shark-autotune
Analyse shark timing history and recommend optimal SHARK_LOOP_TIMEOUT and SHARK_MAX_LOOPS settings
shark
No description provided.
performing-network-traffic-analysis-with-tshark
Automate network traffic analysis using tshark and pyshark for protocol statistics, suspicious flow detection, DNS anomaly identification, and IOC extraction from PCAP files
performing-network-forensics-with-wireshark
Capture and analyze network traffic using Wireshark and tshark to reconstruct network events, extract artifacts, and identify malicious communications.
catcolab-causal-loop
CatColab Causal Loop Diagrams - systems dynamics modeling with reinforcing (R) and balancing (B) feedback loops, delays, and Lotka-Volterra semantics for strategic analysis.
analyzing-network-traffic-with-wireshark
Captures and analyzes network packet data using Wireshark and tshark to identify malicious traffic patterns, diagnose protocol issues, extract artifacts, and support incident response investigations on authorized network segments.
self-validation-loop
Run self-validation loops for triadic color systems using prediction vs observation and error minimization.
repo-change-loop
Runs the standard Robota change loop by identifying impact, building affected scope, running targeted verification, and summarizing residual risk. Use when making or reviewing repository changes that should end in an explicit verification result.
cfn-loop-validation
Multi-layer validation and quality gates for CFN Loop workflows. Use when implementing gate checks, consensus validation, or enforcing clean agent exit patterns.