fleet-intelligence
Automates the sharing of proven skill patterns and insights across the fleet.
Install
mkdir -p .claude/skills/fleet-intelligence && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14320" && unzip -o skill.zip -d .claude/skills/fleet-intelligence && rm skill.zipInstalls to .claude/skills/fleet-intelligence
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Cross-Rick compounding via the Hive. Exports proven skill variants + dream-insight patterns (PII-scrubbed, aggregate-only), imports global-best learnings from every other Rick back into the local pool. Daily 04:00, gated by RICK_FLEET_INTEL_LIVE=1.Key capabilities
- →Export proven skill variants
- →Export dream-insight patterns
- →Import global-best learnings from other Ricks
- →Scrub PII from exported data
- →Prevent re-posting unchanged rows within 30 days
- →Register imported variants and patterns
How it works
The skill runs daily scripts to select well-evidenced local winners, scrub PII, and export them to a central Hive. It then imports global-best learnings from the Hive and registers them locally.
Inputs & outputs
When to use fleet-intelligence
- →Share successful skill patterns
- →Import global best learnings
- →Sync fleet intelligence
About fleet-intelligence
Manages the export of local high-performance skills and the import of fleet-wide best practices, with strict PII scrubbing and anonymization.
Cross-Rick compounding via the Hive. Exports proven skill variants + dream-insight patterns (PII-scrubbed, aggregate-only), imports global-best learnings from every other Rick back into the local pool. Daily 04:00, gated by RICK_FLEET_INTEL_LIVE=1.
When not to use it
- →For live trade signals
- →When raw counts or customer content needs to be exported
Limitations
- →Exports only aggregate win_rate and n_runs, not raw counts
- →Does not export primary keys, tenant IDs, parent_variant_id, or customer content
- →Requires `RICK_FLEET_INTEL_LIVE=1` to run live, otherwise defaults to dry-run
How it compares
This skill automates the sharing and integration of best practices across multiple instances, providing a centralized learning mechanism that is not present in isolated, manual operations.
Compared to similar skills
fleet-intelligence side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| fleet-intelligence (this skill) | 0 | 3mo | Review | Intermediate |
| using-superpowers | 95 | 3mo | No flags | Beginner |
| ultrawork | 11 | 2mo | No flags | Advanced |
| clawhub | 25 | 2mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
using-superpowers
obra
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists
ultrawork
Yeachan-Heo
Parallel execution engine for high-throughput task completion
clawhub
openclaw
Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.
skill-installer
openai
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
continuous-learning
affaan-m
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
memory-keeper-proactive-context-maintenance
b4CU-R4U
Automatically detect and maintain memory freshness by monitoring context staleness, significant code changes, task completions, and phase transitions. Proactively suggests and executes memory sync operations with user confirmation. Use when the user says "sync memory", "update context", or when the Skill detects that context is stale (>2 hours), significant changes have occurred (new commits), tasks completed, or major milestones reached. Replaces passive "context is stale" warnings with active maintenance.