Slm Compress

Compress large text, tool output, or transcripts to reduce context-window usage while keeping the full 1M window intact — call slm_compress(content, mode, reversible, ttl_seconds) to shrink content; if the result is lossy a ccr_id is returned so you can call slm_retrieve(ccr_id) later to recover the exact original; always fail-open (ok:false → continue with the original).

278 stars 36 forksWriting & Content Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add qualixar/superlocalmemory

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add qualixar/superlocalmemory --skill slm-compress
Manual install
git clone --depth 1 https://github.com/qualixar/superlocalmemory.git /tmp/superlocalmemory
mkdir -p ~/.claude/skills
cp -r /tmp/superlocalmemory/antigravity-plugin/skills/slm-compress ~/.claude/skills/slm-compress

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# slm-compress — Reversible Context Compression (Surface B)

## Purpose

When a tool output, transcript, or accumulated context grows large enough to crowd out working space, `slm_compress` reduces it in-place. The compressed form is used for the remainder of the session; the exact original is recoverable on demand via `slm_retrieve`. This works without a proxy and without touching `ANTHROPIC_BASE_URL`, so the full 1M context window is never sacrificed.

## Primary MCP Tool: slm_compress

```
slm_compress(
    content:      str,          # required — text to compress (max 1 MB)
    mode:         str = "auto",  # "normalize" | "auto" | "aggressive"
    reversible:   bool = True,  # store original in CCR for later retrieval
    ttl_seconds:  int = 86400,  # CCR lifetime in seconds (default 24 h)
) -> dict
```

### Return dict (all keys always present)

| Key | Type | Meaning |
|-----|------|---------|
| `ok` | bool | `True` on success; `False` on internal error or empty input |
| `compressed` | str | Compressed text (or original on failure) |
| `strategy` | str | Which strategy was applied (e.g. `"normalize"`, `"none"`) |
| `tokens_before` | int | Word-count estimate of the input |
| `tokens_after` | int | Word-count estimate of the output |
| `ratio` | float | `tokens_after / tokens_before` (lower = more compact) |
| `lossy` | bool | Whether information was removed |
| `ccr_id` | str \| None | UUID4 session token; present only when `lossy=True` and `reversible=True` |
Read the full skill on GitHub

Details

Skill name
slm-compress
Path
antigravity-plugin/skills/slm-compress/SKILL.md
License
AGPL-3.0
Repo updated
18 November 2026

FAQ

What does the Slm Compress skill do?

Compress large text, tool output, or transcripts to reduce context-window usage while keeping the full 1M window intact — call slm_compress(content, mode, reversible, ttl_seconds) to shrink content; if the result is lossy a ccr_id is returned so you can call slm_retrieve(ccr_id) later to recover the exact original; always fail-open (ok:false → continue with the original).

How do I install the Slm Compress skill?

Claude Code plugin: /plugin marketplace add qualixar/superlocalmemory. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Slm Compress popular?

It lives in qualixar/superlocalmemory, which has 278 GitHub stars and 36 forks, and is included in 1 curated skill list.

Related skills

Slm Bot Memory

278

qualixar/superlocalmemory

Cross-bot memory on a shared computer (Grok Bot, Cursor plugin, any host where several agents share one machine). Explains agent_id attribution vs. profile/scope access, how to namespace by agent_id + profile + scope, and what must never be written to memory. Read this before the first remember/recall on a new Grok-Bot-style host.

Productivity & NotesIn 1 list36

Slm Cache

278

qualixar/superlocalmemory

KV cache for repeated reads — call slm_cache_get(key) first; on a miss do the expensive operation then slm_cache_set(key, value, ttl_seconds) to store it; on a hit use the returned value directly; always fail-open (hit:false on any error, never raises); saves tokens when the same file, query result, or tool output is read more than once in a session.

OtherIn 1 list36

Slm Getting Started Bot

278

qualixar/superlocalmemory

First-session orientation for SuperLocalMemory on a headless bot host (Grok Bot, or any Cursor-format plugin install with no hooks, no dashboard, and no interactive setup wizard). What is different here vs. Claude Code/Codex, which 19 tools are actually available, and the first three calls to make.

Software DevelopmentIn 1 list36

Multica Platform Jira

279

it235/multica-best-practices

Platform-layer skill (placeholder shell): read/write capability for Issue-tracking systems (JIRA-class) — Issue query, upstream-Wiki-link parsing, Story creation, transition, scheduling, description write-back, notification. Decoupled from the Wiki platform; called by artifact-orchestration skills. Concrete URLs / projects / fields live in config.yaml, never in role prompts.

Writing & Content33

Simplified Technical English

206

thomast1906/github-copilot-agent-skills

Writes and rewrites technical text in Simplified Technical English (ASD-STE100), a controlled language for clear technical documentation. Use when the user asks for STE, Simplified Technical English, controlled language, or plain technical writing, or asks to write, rewrite, simplify, clarify, review, or check technical documentation, procedures, manuals, instructions, warnings, error messages, or reports. Do NOT use for marketing copy, creative writing, or general prose simplification outside a technical context.

Writing & Content54

Multica Platform Jira

279

it235/multica-best-practices

JIRA 读写:Issue 查询、Confluence 链接解析、Story 创建、流转、排期、描述回写、钉钉。平台 skill,与 Confluence 解耦。跨平台优先 jira_cli.py。

Writing & Content33

Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.