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).
Install
/plugin marketplace add qualixar/superlocalmemoryThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add qualixar/superlocalmemory --skill slm-compressgit 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-compressPersonal 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` |Details
- Skill name
slm-compress- Repository
- qualixar/superlocalmemory
- Path
antigravity-plugin/skills/slm-compress/SKILL.md- License
- AGPL-3.0
- Repo updated
- 18 November 2026
- Listed in
- heilcheng/awesome-agent-skills
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
278qualixar/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.
Slm Cache
278qualixar/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.
Slm Getting Started Bot
278qualixar/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.
Multica Platform Jira
279it235/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.
Simplified Technical English
206thomast1906/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.
Multica Platform Jira
279it235/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。
Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.