skills.rest
rajivpant
rajivpantCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

synthesis-context-lifecycle

Separate working memory, reference facts, and session archives into CONTEXT.md, REFERENCE.md, and sessions/.

15|2|Updated Mar 17, 2026
Search Tags:#git#archival#context-management#project-lifecycle#reference-docs#working-memory#session-archive
One-click install
npx skills add https://github.com/rajivpant/synthesis-skills --skill synthesis-context-lifecycle
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: synthesis-context-lifecycle
Source: https://github.com/rajivpant/synthesis-skills/tree/main/synthesis-context-lifecycle
Command: npx skills add https://github.com/rajivpant/synthesis-skills --skill synthesis-context-lifecycle

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Long-running AI collaborations accumulate unwieldy context files that degrade agent performance and create continuity failures across sessions. This Skill prescribes a three-tier context architecture (working memory, semantic reference, episodic archive) and a disciplined archival-first workflow so projects remain discoverable, performant, and auditable.

Core Features & Use Cases

  • Three-tier architecture: Separate CONTEXT.md for session working memory, REFERENCE.md for stable facts, and sessions/YYYY-MM.md for monthly archives to limit growth and improve retrieval.
  • Archival-first protocol: Two-phase commit pattern that writes archives before removing source content, with verification steps and strict per-repo commit scoping to avoid lost context.
  • Operational templates & budgets: Clear templates and line-count budgets (CONTEXT.md ≤150 lines, REFERENCE.md ≤300 lines) plus migration guidance for projects of varying sizes.
  • Commit protocol & scope rules: Enforce committing and pushing context changes at point-of-modification and never running workspace-wide sweep commits, making context changes visible across machines immediately.
  • Use Case: Maintain continuity for a multi-week engineering project where session logs, decisions, and active tasks must be kept compact, auditable, and shareable between human and AI collaborators.

Quick Start

Open the project's CONTEXT.md, extract session logs older than one week to sessions/YYYY-MM.md, move stable facts into REFERENCE.md, trim CONTEXT.md to the working-memory budget, then commit and push only the modified files.

Frequently Asked Questions about synthesis-context-lifecycle

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I manage AI project context for long-running, multi-session collaborations?▼

Manage AI project context by separating working memory, semantic reference, and episodic archives into CONTEXT.md, REFERENCE.md, and monthly session files. This three-tier architecture keeps context compact and auditable across repeated sessions.

What is the best way to archive AI session logs without losing project continuity?▼

Archival-first context management writes session logs to monthly archive files before removing source content. This two-phase commit pattern verifies archives and scopes git commits per repository to prevent lost context during long-running projects.

How do I stop context files from degrading agent performance in repository-based projects?▼

Stop context file degradation by enforcing line-count budgets: keep CONTEXT.md under 150 lines for working memory and REFERENCE.md under 300 lines for stable facts. Extract older session logs to monthly archive files to maintain performance.

Does this context lifecycle workflow require git for committing changes?▼

Yes, the context lifecycle workflow requires git to enforce per-repo scoped commits and pushes at the point of modification. This strict scoping prevents workspace-wide sweep commits and makes context changes visible across machines immediately.

When should I migrate stable facts out of my working memory context file?▼

Migrate stable facts out of working memory when your CONTEXT.md exceeds its 150-line budget or when phase changes occur. Move stable facts into REFERENCE.md for semantic reference and extract older session logs to monthly archive files.

What is the two-phase commit pattern for AI context archival?▼

The two-phase commit pattern for context archival writes episodic archives to sessions/YYYY-MM.md before removing source content from working memory. It includes verification steps and strict per-repo git commit scoping to ensure no context is lost.

Related Skills

Explore More Software Engineering Skills→
chaimtchaimt

speckit-git-initialize

Initialize a Git repository with an initial commit in the current directory.

Community
Intermediate
niraclerniracler
11

code-sync

Synchronize Git repositories under ~/code with automated fetch, status, and batch actions.

Community
Advanced
rajivpantrajivpant
15

synthesis-project-management

Manage multi-session projects with index.yaml, CONTEXT.md, REFERENCE.md, and sessions/.

Community
Advanced
synthesisengineeringsynthesisengineering
15

synthesis-project-management

Coordinate multi-session projects with persistent context via CONTEXT.md, REFERENCE.md, and sessions/.

Official
Advanced