Prune bloated session with a prescription. Removes progress ticks, stale reads, duplicate content, and more.
Scanned 5/28/2026
Install via CLI
openskills install Ruya-AI/cozempic---
name: treat
description: Prune bloated session with a prescription. Removes progress ticks, stale reads, duplicate content, and more.
argument-hint: "[gentle|standard|aggressive]"
disable-model-invocation: true
allowed-tools: Bash(cozempic *), AskUserQuestion
---
Apply a pruning prescription to the current session. Default is `standard` if no argument given.
**When to use `treat` vs `reload`:** prefer the `reload` skill — it does the same prune plus auto-resume in one step (`/exit` → new terminal opens with the pruned session). Use `treat` only when the user explicitly wants to stay in the current session, work in a multi-pane setup, or resume manually.
## Steps
1. **Diagnose first** — show the user what they're working with:
```bash
cozempic current --diagnose
```
2. **Dry-run the treatment** — show savings without applying:
```bash
cozempic treat current -rx $ARGUMENTS
```
If no argument was provided, use `standard`:
```bash
cozempic treat current -rx standard
```
3. **Show results** — present the dry-run output including token savings (the `Tokens:` line). Always surface both byte and token savings.
4. **Ask confirmation** — use AskUserQuestion to confirm before applying.
5. **Apply on confirmation**:
```bash
cozempic treat current -rx $ARGUMENTS --execute
```
6. **Tell the user**: "Treatment applied. A backup was created automatically. To resume with the pruned session, exit and run `claude --resume`. (Tip: next time, the `reload` skill does this in one step — `/exit` and a fresh terminal opens automatically.)"
## Prescriptions
| Rx | Strategies | Typical Savings |
|----|-----------|----------------|
| `gentle` | progress-collapse, file-history-dedup, metadata-strip | 40-55% |
| `standard` | gentle + thinking-blocks, tool-output-trim, stale-reads, system-reminder-dedup | 50-70% |
| `aggressive` | standard + error-retry-collapse, document-dedup, mega-block-trim, envelope-strip | 70-95% |
## Safety
- Always dry-run first — never execute without showing the user what will change
- Backups are automatic (timestamped .bak files)
- Never touches uuid/parentUuid — conversation DAG stays intact
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...