Skip to content
cccskills
FreePublished on GitHub

context-transfer

Generate a state document (context transfer) that allows any fresh AI instance to resume work without conversation history. Use this skill whenever the user asks to checkpoint, create a state transfer, save state, generate a handoff document, create compaction insurance, or says anything like 'snapshot this', 'create a context transfer', 'checkpoint', 'save state for handoff', 'write a recovery doc', or 'transfer context'. Also trigger when the user mentions compaction concerns, session handoff, multi-session continuity, or wants to preserve the current conversation's state. Works for any conversation type: projects, research, debugging, investigations, design sessions, or long-running chats. This skill produces a structured markdown document optimized for AI cold-start recovery, not human notes.

The English summary is being prepared. Showing the original description.

See how to install

Files included (2)

  • SKILL.md4.7 KB
  • references/protocol_v2.4s.md7.7 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Context Transfer

Generate structured state documents for AI cold-start recovery across any conversation type.

When To Use

  • User asks to checkpoint, snapshot, or save state
  • Session is getting long and compaction insurance is needed
  • Work will continue in a new session (handoff)
  • Multi-session work needs persistent state
  • User mentions compaction, context loss, or continuity concerns
  • Any conversation where accumulated decisions, findings, or state would be costly to lose

Before Starting

Read the full protocol:

Read references/protocol_v2.4s.md

This contains the complete section definitions, templates, rules, and quality checklist.

Quick Reference

The context transfer has 11 sections. Scale to complexity — not every conversation needs all sections.

SectionPurposeRequired?
I. What This IsIdentity + "It is NOT" correctionAlways
II. Domain ContextProblem-space briefingMulti-session+
III. ArchitectureSystem structureBuild/engineering work
IV. DecisionsNumbered with narrative WHYWhen decisions exist
V. Current StateStep sequence or phase summaryAlways
VI. ArtifactsFile inventory with statusWhen files exist
VII. Anti-Drift WarningsObserved/predicted failure modesMulti-session+
VIII. What NOT To DoCatastrophic prohibitionsWhen applicable
IX. GlossaryContext-specific termsDomain-specific
X. Open QuestionsUnresolved issuesWhen they exist
XI. Recovery PointerExact restart location + pathAlways

Minimum viable: Sections I, V, XI.

Workflow

  1. Read the protocol (references/protocol_v2.4s.md) — understand all section rules
  2. Assess scope — use Scaling Guide to determine which sections are needed
  3. Gather state from conversation — extract decisions, current step, artifacts, open questions
  4. Write each section following the protocol templates exactly
  5. Apply critical rules:
    • §I must include "It is NOT..." correction sentence
    • §IV decisions must have narrative WHY (mark [inferred] if rationale not explicitly stated)
    • §VII every warning tagged [observed] or [predicted]
    • §XI must include Work lives in: (write UNKNOWN — ask user if path not known)
  6. Run Quality Checklist from protocol
  7. Save to /mnt/user-data/outputs/ and present to user

Output

Save as: [topic_or_project]_context_transfer.md in /mnt/user-data/outputs/

The document header should include:

# Context Transfer — [Topic or Project Name]

**Version:** [N]
**Updated:** [date]
**Purpose:** Compaction insurance. If you just got compacted, read this first.

Key Rules (from protocol)

These are the rules most likely to be missed. Full rules are in the protocol reference.

  • Single source of truth: One context transfer per conversation/project. Never maintain parallel state docs.
  • Correction sentence: §I must state what it IS then what it is NOT.
  • Narrative WHY: §IV uses prose, not tables. Tables compress reasoning too much for cold start.
  • Inferred rationale: If WHY isn't explicitly stated, mark as [inferred] — never present inference as ground truth.
  • Tag all warnings: §VII requires [observed] or [predicted] on every warning. No untagged.
  • Never fabricate paths: §XI Work lives in: must be real or UNKNOWN — ask user.
  • Update immediately: Write to file after each decision/state change. Don't batch.

Notes

  • This skill is validated across Claude, GPT, and Gemini cold instances (n=5 tests, zero operational failures)
  • The protocol is model-agnostic — works without cognitive scaffolding
  • Optimized for AI pattern recognition, not human readability
  • The context transfer IS the conversation's memory — treat it as critical infrastructure

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Complete architecture reference for the A3 insurance platform — file locations, data flow, conventions, microservice map, and fullstack patterns

The English summary is being prepared. Showing the original description.

FDU-INS/Insurance-Skills79Updated Jul 12, 2026

Drafts U.S. commercial real estate access and indemnity (right-of-entry) agreements for pre-closing due diligence. Covers license grants, non-invasive vs invasive testing gates, insurance/endorsement requirements, indemnity with discovery carve-outs, restoration and lien remedies, confidentiality, and anti-indemnity guardrails. Trigger: access agreement, right of entry, due diligence access, Phase I/II, invasive testing, pre-PSA site inspection.

The English summary is being prepared. Showing the original description.

FDU-INS/Insurance-Skills79Updated Jul 12, 2026

当用户需要对意外险投保问卷进行专业、结构化的核保审查,提取职业类别、工作环境、作业内容、危险活动参与情况、交通出行习惯、特殊工作暴露及其他可能影响意外险承保判断的高风险信息,并生成适合意外险核保、补问流转和风险分层处理的结构化分析结果时使用本 skill。

The English summary is being prepared. Showing the original description.

FDU-INS/Insurance-Skills79Updated Jul 12, 2026

Inspect, schema, and fill true AcroForm PDFs using sciClaw's pdf_form_inspect, pdf_form_schema, and pdf_form_fill tools. Use when: (1) checking whether a PDF is a real fillable AcroForm, (2) listing form field names, types, and choices, (3) filling a supported form from structured values, (4) preparing reviewable insurance, legal, administrative, or clinical form drafts, (5) reporting skipped fields or unused input keys after a fill. Do not use for scanned PDFs, OCR tasks, or XFA-only forms.

The English summary is being prepared. Showing the original description.

FDU-INS/Insurance-Skills79Updated Jul 12, 2026

Guide actuarial analysis for insurance pricing. TRIGGERS - Use when user needs help with actuarial-analysis related tasks.

The English summary is being prepared. Showing the original description.

FDU-INS/Insurance-Skills79Updated Jul 12, 2026

Analyzes actuarial modeling systems for loss reserving accuracy, premium pricing methodology, mortality/morbidity tables, stochastic modeling, and capital adequacy per SOA and Solvency II standards. USE THIS SKILL WHEN: - You need to review or audit actuarial models (reserving, pricing, capital) - Someone asks about loss triangle analysis or reserve adequacy - You are evaluating IBNR calculations, chain ladder methods, or Bornhuetter-Ferguson - A project involves insurance pricing, GLM rating models, or ratemaking - You need to assess Solvency II SCR calculations or RBC compliance - Someone mentions actuarial opinions, ASOP compliance, or SOA standards - You are reviewing stochastic models, ESG configurations, or DFA frameworks - A codebase uses actuarial libraries (chainladder, lifetables, ChainLadder R package) TRIGGER PHRASES: "actuarial", "loss reserving", "IBNR", "chain ladder", "premium pricing", "mortality table", "Solvency II", "capital adequacy", "ratemaking", "GLM pricing", "risk-based capital", "reserve analysis", "actuarial opinion"

The English summary is being prepared. Showing the original description.

FDU-INS/Insurance-Skills79Updated Jul 12, 2026

See all skills by FDU-INS

Report a problem with this skill