Miosa-osaMiosa-osaOfficialยท77 Agent Skills Included

canopy

Persistent terminal workspace with marketing, sales, and ads playbooks

Restores terminal sessions, working directories, and agent conversations after app restarts or reboots. Includes a large playbook library covering paid ads audits, sales scripts, offer design, launch planning, and content production. Eliminates lost terminal state and blank-page marketing work by giving agents ready-made, structured workflows.
npx skills add Miosa-osa/canopy --all -g -y
Available:

Tells the agent how to work in this monorepo: which directories each agent owns, the build order for session persistence, and the coding and testing rules to follow.

All Skills in This Repository (77)

Pure Emerald Level Indicators
๐Ÿ“ฆ In Repo
Miosa-osaMiosa-osa

learning-engine

Automate a continuous self-learning loop with memory consolidation and skill generation.

Official
Advanced
๐Ÿ“ฆ In Repo
Miosa-osaMiosa-osa

lats

Plan language agent actions using Monte Carlo Tree Search with LLM reasoning.

Official
Advanced
๐Ÿ“ฆ In Repo
Miosa-osaMiosa-osa

judge-prompt

Design binary pass/fail LLM-as-Judge evaluation prompts with scoring instructions and guardrails.

Official
Advanced
๐Ÿ“ฆ In Repo
Miosa-osaMiosa-osa

synthetic-data

Generate labeled synthetic test inputs via dimension-based combinatorics for ML eval pipelines.

Official
Advanced
๐Ÿ“ฆ In Repo
Miosa-osaMiosa-osa

skeleton-of-thought

Generate long-form content by outlining a skeleton and expanding points in parallel.

Official
Advanced
๐Ÿ“ฆ In Repo
Miosa-osaMiosa-osa

tree-of-thoughts

Coordinate multi-path reasoning with BFS, DFS, and Beam search strategies.

Official
Advanced
๐Ÿ“ฆ In Repo
Miosa-osaMiosa-osa

self-consistency

Sample multiple reasoning paths and select the most consistent final answer.

Official
Intermediate
๐Ÿ“ฆ In Repo
Miosa-osaMiosa-osa

validate-evaluator

Calibrate LLM evaluators against human-labeled datasets and generate Markdown calibration reports.

Official
Advanced
๐Ÿ“ฆ In Repo
Miosa-osaMiosa-osa

eval-rag

Evaluate RAG pipelines with retrieval and generation metrics plus bottleneck analysis.

Official
Advanced
๐Ÿ“ฆ In Repo
Miosa-osaMiosa-osa

meta-prompting

Improves AI prompts through iterative optimization, scoring, and versioned reuse.

Official
Advanced
๐Ÿ“ฆ In Repo
Miosa-osaMiosa-osa

prompt-cache-optimizer

Cache and compress prompts to reduce token costs in LLM interactions.

Official
Advanced
๐Ÿ“ฆ In Repo
Miosa-osaMiosa-osa

react-pattern

Automate Thought-Action-Observation loops for transparent AI agent reasoning.

Official
Intermediate

Frequently Asked Questions

FAQPage Schema
How to install Canopy?โ–ผ

Run `npx skills add Miosa-osa/canopy --all -g -y` in your terminal to install all skills in this suite globally.

What does Canopy actually do?โ–ผ

It is a desktop terminal workspace that survives restarts, restoring your sessions, directories, and agent conversations. It also ships a large library of marketing, sales, and paid-ads skills.

What marketing tasks can Canopy skills handle?โ–ผ

The library covers Google, Meta, TikTok, LinkedIn, and Microsoft ads audits, plus offer design, VSL scripts, sales scripts, launch plans, and content writing.

Does Canopy work with Claude Code and other agents?โ–ผ

Yes. All skills follow the standard SKILL.md format and run in Claude Code, Cursor, Codex, and similar agent runtimes.

Do I need coding experience to use the marketing skills?โ–ผ

No. You describe the task in plain English and the agent follows the skill's step-by-step playbook to produce the output.

Related Repositories in Marketing & Sales

View All in Marketing & Salesโ†’