compress
Info-Compressor: compress text/context by 60-70% without losing meaning. Use when: (1) context pressure >50%, (2) user says "сжать", "compress", "compact", (3) need to fit more context into remaining window, (4) preparing handoff blob for next session.
Best use case
compress is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Info-Compressor: compress text/context by 60-70% without losing meaning. Use when: (1) context pressure >50%, (2) user says "сжать", "compress", "compact", (3) need to fit more context into remaining window, (4) preparing handoff blob for next session.
Teams using compress should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/compress/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How compress Compares
| Feature / Agent | compress | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Info-Compressor: compress text/context by 60-70% without losing meaning. Use when: (1) context pressure >50%, (2) user says "сжать", "compress", "compact", (3) need to fit more context into remaining window, (4) preparing handoff blob for next session.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Info-Compressor — 70% Context Compression
Compress text/context to ~30% of original size without losing meaning.
## Compression Techniques (apply ALL)
### 1. Structural
- **Prose → Tables** where data has patterns (comparisons, lists, specs)
- **Paragraphs → Bullet points** with 3-7 words each
- **Nested lists → Flat lists** with `→` for hierarchy
### 2. Linguistic
- **Remove filler:** "it should be noted that" → cut
- **Remove hedging:** "I think", "perhaps", "it seems" → cut
- **Active voice:** "was done by X" → "X did"
- **Imperative mood:** "you should run" → "run"
- **Present tense** everywhere
- **Remove articles** where meaning is clear: "the server" → "server"
### 3. Symbolic
- `→` for causality/flow ("X causes Y" → "X → Y")
- `|` for alternatives ("either A or B" → "A | B")
- `+` for additions ("also includes" → "+ includes")
- `=` for equivalence ("is the same as" → "=")
- `>` for preference ("better than" → ">")
- `✓/✗` for yes/no, done/not done
- `~` for approximation
### 4. Abbreviation
- Standard: cfg, env, srv, dir, repo, fn, arg, param, cmd, msg, req, res
- Context-specific: define at top if non-obvious
- **Never abbreviate:** file paths, entity names, error messages, URLs
### 5. Deduplication
- State each fact ONCE
- Remove repeated context from multiple messages
- Merge related items into single statement
## Modes
### `/compress context`
Compress the current conversation context, output a compressed summary.
Use as a "reset point" — paste at start of new session.
**Steps:**
1. Review full conversation
2. Extract: goals, decisions, progress, pending, files, gotchas
3. Apply all compression techniques
4. Output compressed blob (target: <2KB)
5. Show compression ratio: "Compressed: {original}K → {compressed}K ({ratio}%)"
### `/compress clipboard`
User will paste text. Compress it and return.
### `/compress file <path>`
Read file, compress content, return compressed version.
## Quality Check
After compression, verify:
- [ ] All file paths preserved exactly
- [ ] All numeric values preserved
- [ ] All entity/variable names preserved
- [ ] All error messages preserved
- [ ] Meaning is fully recoverable by someone who didn't read the original
- [ ] No ambiguity introduced by abbreviation
## Example
**Before (312 chars):**
> It should be noted that the server configuration was modified by the team yesterday. The main change was updating the database connection string from the old PostgreSQL server to the new one. Additionally, they also updated the Redis cache timeout from 300 seconds to 600 seconds.
**After (89 chars, 71% reduction):**
> Server cfg updated yesterday: DB conn string → new PostgreSQL srv, Redis cache timeout 300s → 600s
## Auto-Trigger on Context Pressure
At 🟡 50-72% context — **автоматически:**
1. Compress context (все техники сжатия)
2. `/session-save <auto-name>` (сохранить checkpoint)
3. Показать: "Context 🟡 — сжал и сохранил `<name>`. `/continue <name>` в новой сессии."
At 🔴 >72% context (HANDOFF) — **немедленно:**
1. Compress + save checkpoint
2. **REFUSE further execution**
3. Output handoff blob with instructions to continue in new sessionRelated Skills
writing-content
Интерактивный процесс написания текстов для вайб-маркетинга на основе Julian Shapiro framework. **Новые возможности (v2.0):** - Research & Gap Analysis (Perplexity → WebSearch fallback) - Scoring 0-5 вместо binary (Novelty + Resonance + Hook + Clarity) - AI-Slop Detection на всех этапах (10 типов patterns) - 3 варианта intro с self-scoring - Markdown export всех промежуточных результатов **Русские triggers:** "напиши пост по шапиро", "написать статью по фреймворку шапиро", "создай текст в стиле julian shapiro", "помоги написать контент по методу shapiro", "контент по julian shapiro фреймворку", "пост по julian shapiro", "напиши в стиле шапиро" **English triggers:** "write content using julian shapiro framework", "create post with shapiro method", "write article shapiro style", "help with julian shapiro writing" **Generic triggers:** "напиши статью", "помоги написать контент", "создай текст", "начать писать", "хочу написать пост", "нужна помощь с текстом", "write content", "write article", "создай контент", "придумай идею для статьи", or requests help with content creation process.
YT Transcribe — YouTube → Whisper → Obsidian
Транскрибирует YouTube-видео через mlx-whisper (Apple Silicon, Metal-native) с параллельными чанками.
/tg-saved v2 — Telegram Saved Messages → Deep Analysis → Obsidian
## Назначение
summarize-comments
Делает LLM-выжимку из комментариев менеджеров об одном или нескольких подрядчиках. Используй этот скилл когда нужно понять что говорят менеджеры о конкретном подрядчике, или получить JSON с выжимкой для дальнейшей обработки.
skill-security
This skill activates when the user mentions "security audit", "skill audit", "проверка безопасности скилла", "аудит скилла", "skill-security", "проверить скилл", "пересобрать скилл", "rebuild skill", "security check", "dual memory audit", "credential isolation check". Also activates on /skill-security command. Use this skill when the user wants to audit, validate, or rebuild any Claude Code skill for security compliance.
session-status
Statusline shown in Claude Code UI status bar via settings.json. No action needed in responses.
session-save
Compress and save current session context for handoff to next session. Use when: (1) context pressure >50%, (2) user says "сохрани сессию", "session save", "checkpoint", (3) before ending a long productive session, (4) switching to a different task mid-session. Supports named sessions: /session-save vpn-fix
continue-session
Restore context from a named or latest session checkpoint. Use when: (1) user says "продолжи", "continue", "что было в прошлой сессии", (2) starting work after a crash or context overflow, (3) "resume", "восстанови контекст", "где я остановился". Supports named sessions: /continue vpn-fix
seo-strategist
Strategic SEO planning and analysis toolkit for site-wide optimization, keyword research, technical SEO audits, and competitive positioning. Complements content-creator's on-page SEO with strategic planning, topic cluster architecture, and SEO roadmap generation. Use for keyword strategy, technical SEO audits, SERP analysis, site architecture planning, or when user mentions SEO strategy, keyword research, technical SEO, or search rankings.
roi-razvitie-draft
Generates a draft meeting document for the weekly "Roi Развитие" (Wednesday, product Roi Navigator). Use when the user asks for a draft for the meeting, for Wednesday's doc, for "Roi Развитие", or for the weekly team meeting agenda.
project-knowledge-base
Collects, structures and maintains a Project Knowledge Base (PKB.md) in Obsidian for a marketing agency. Aggregates data from Google Drive, Gmail, Telegram (group chat and DMs via MTProto), moo.team tasks/comments, and local Obsidian meeting transcripts. Uses async parallel collection and a two-stage LLM pipeline for init. Use when the user wants to initialize, update or enrich a project's knowledge base, mentions PKB, project knowledge base, синхронизация проекта, база знаний проекта, init_project_knowledge, update_project_knowledge, or ad_hoc_add_context.
product-strategist
Strategic product leadership toolkit for Head of Product including OKR cascade generation, market analysis, vision setting, and team scaling. Use for strategic planning, goal alignment, competitive analysis, and organizational design.