Core Context Compressor

Use when the user asks to compress context, summarize the conversation, save tokens, fit the context window, set a context budget or condense a long session. Produces a structured compressed summary of the session state to carry forward. Not for writing project docs (use dev-loop-readme-writer).

45 stars 6 forksWriting & Content

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add j4flmao/agent-skills --skill core-context-compressor
Manual install
git clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/core/context-compressor ~/.claude/skills/core-context-compressor

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

From the SKILL.md

# Core Context Compressor

## Purpose
Compress long conversation histories into structured, token-efficient summaries for continuing work within context window limits. Extracts decisions, file changes, configuration values, and next steps into bullet-point format optimized for AI agent consumption.

LLMs have finite context windows (~32K-200K tokens). As conversations grow over dozens of exchanges, quality degrades because relevant information is buried. This skill produces a lossy-but-critical compression sacrificing implementation detail while preserving every decision, file change, configuration value, and unresolved question.

## Agent Protocol

### Trigger
"compress context", "context summary", "token save", "compression", "condense", "summarize conversation", "context budget", "reduce tokens", "context window"

### Input Context
- Full conversation history up to this point
- List of files modified with absolute or relative paths and change descriptions
- Key decisions with rationale and alternatives considered and rejected
- Configuration values: env vars, port numbers, URLs, feature flags
- User preferences: code style, naming conventions, formatting rules
- Current task state: what phase is complete, what is in progress
- Blocking issues and unresolved open questions
- Next steps stated or implied at the end of last exchange

### Output Artifact
Read the full skill on GitHub

Details

Skill name
core-context-compressor
Path
skills/core/context-compressor/SKILL.md
License
MIT
Repo updated
17 November 2026

FAQ

What does the Core Context Compressor skill do?

Use when the user asks to compress context, summarize the conversation, save tokens, fit the context window, set a context budget or condense a long session. Produces a structured compressed summary of the session state to carry forward. Not for writing project docs (use dev-loop-readme-writer).

How do I install the Core Context Compressor skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill core-context-compressor. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Core Context Compressor popular?

It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.

Related skills

Agent Observability

45

j4flmao/agent-skills

Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).

DevOps & Cloud

AI Agent Architectures

45

j4flmao/agent-skills

Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).

AI, LLMs & Agents

AI Agent Core Loop

45

j4flmao/agent-skills

Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).

AI, LLMs & Agents

Core Onboarding

45

j4flmao/agent-skills

Use when the user asks about onboarding a new developer, new team member or new joiner, a getting started guide, dev environment setup, ramp-up plan or first-week checklist. Produces an onboarding plan and environment setup guide. Not for scaffolding a new repository (use project-init) or writing the README (use dev-loop-readme-writer).

Writing & Content

Backend Openapi Documentation

45

j4flmao/agent-skills

Use when the user asks about OpenAPI, writing an OpenAPI spec, Swagger, openapi.yaml, spec-first design, Spectral linting, code generation or API docs hosting. Produces OpenAPI 3.1 documents with lint and CI checks. Not for endpoint semantics (use backend-api-design).

Writing & Content

Data Data Lake

45

j4flmao/agent-skills

Use when the user asks to choose between Iceberg, Delta Lake and Hudi, ACID tables on object storage, time travel, schema evolution, compaction, vacuum, Z-order, merge-on-read vs copy-on-write or data lake architecture. Produces table-format choice and table maintenance plan. Not for medallion and Unity Catalog platform design (use data-data-lakehouse).

Writing & Content

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