continuous-learning-v3
Continuous Learning v3
An agent-agnostic learning system that observes your AI coding sessions and creates reusable knowledge through atomic "instincts" — small learned behaviors with confidence scoring.
⚡ First-Time Setup (Automatic)
When this skill is first loaded, automatically perform these steps:
Step 1: Check if Plugin is Installed
# Check for the OpenCode plugin
ls ~/.config/opencode/plugins/continuous-learning.js
Step 2: If Not Installed, Install It
If the plugin file does not exist:
More from ericmjl/skills
agents-md-improver
Proposes updates to AGENTS.md so repo-local coding-agent instructions stay accurate, non-contradictory, and consolidated. Use when the user corrects the agent (e.g. do not do X, always do Y, from now on, remember this), asks to edit or sync AGENTS.md, CLAUDE.md, .claude/CLAUDE.md, or GEMINI.md, wants one canonical instruction file or to deduplicate agent docs, or flags conflicting or outdated repository agent rules.
22ml-experimentation
Conduct machine learning experiments from planning through evaluation and report writing. Use when running ML experiments, testing hypotheses, training models, or writing up results. Covers single-hypothesis scoping, fast iteration loops, targeted logging, JOURNAL.md protocol, data-backed diagnostic plots, and scientific report writing.
16youtube
Comprehensive YouTube operations using yt-dlp - download videos/audio, extract transcripts and subtitles, get metadata, work with playlists, download thumbnails, and inspect available formats. Use this for any YouTube content processing task.
7skill-installer
Install or update Agent Skills (skill folders with SKILL.md) across agent harnesses. Use when the user says install a skill, add this skill to my machine or repo, update a skill, move a skill between harnesses, or update a skill from a URL.
6pdf-form-filler
Fill static PDF forms (without fillable fields) using text search for text-based PDFs or Claude Vision for image-based/scanned PDFs. Use when: (1) User wants to fill out a PDF form, (2) PDF has no fillable form fields, (3) User asks to fill in or complete a PDF form. Auto-detects PDF type and uses appropriate method.
3mempalace
>
3