본문으로 건너뛰기
cccskills
무료GitHub에 공개

context-surfing

Monitors context window health throughout a session and rides peak context quality for maximum output fidelity. Activates automatically after plan-interview and intent-framed-agent. Stays active through execution and hands off cleanly to simplify-and-harden and self-improvement when the wave completes naturally or exits via handoff. Use this skill whenever a multi-step agent task is underway and session continuity or context drift is a concern. Especially important for long-running tasks, complex refactors, or any work where degraded context would silently corrupt the output. Trigger even if the user doesn't say 'context surfing' — if an agent task is running across multiple steps with intent and a plan already established, this skill is live.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

ProjectZeroDays/FreeAI_AI_Inference_Workstation스타 5(GitHub 5 + cccskills 0)

실행 점수 미검증

설치 방법 보기

포함된 파일(1)

  • SKILL.md5.4 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Context Surfing

The agent rides the wave of peak context. When the wave crests, it commits. When it detects drift, it pulls out cleanly — saving state, handing off, and letting the next session catch the next wave.

No wipeouts. No zombie sessions. Only intentional, high-fidelity execution.

Mental Model

Think of context like an ocean wave:

  • Paddling in = loading the intent frame, plan, and initial context. Energy is building.
  • The peak = full context coherence. The agent knows exactly what it's doing and why. This is when to execute.
  • The shoulder = context starting to flatten. Still rideable, but output density is dropping.
  • The close-out = drift. Contradiction, hedging, second-guessing, or hallucinated details. Wipe-out territory.

The skill's job: ride as long as the wave is good, exit before it closes out.

Lifecycle Position

[plan-interview] → [intent-framed-agent] → [context-surfing ACTIVE] → [verify-gate] → [simplify-and-harden] → [self-improvement]

Context Surfing is the execution layer. It wraps all work between intent capture and post-completion review.

Relationship with intent-framed-agent

Both skills are live during execution. They monitor different failure modes:

  • intent-framed-agent monitors scope drift — am I doing the right thing?
  • context-surfing monitors context quality drift — am I still capable of doing it well?

Precedence rule: If both fire simultaneously, context-surfing's exit takes precedence. Degraded context makes scope checks unreliable.

Activation

This skill is live the moment the intent frame and plan are established. No explicit invocation needed.

At activation, load whatever anchors are available:

  1. The intent frame (from intent-framed-agent output) — if available
  2. The plan (from plan-interview output) — if available
  3. Project context files (CLAUDE.md, AGENTS.md, README.md)

Drift Detection

Strong signals (exit immediately)

  • The agent contradicts a decision it already made
  • A detail appears in the output that was never in the original context (hallucination)
  • The agent re-opens a scope question that was explicitly resolved
  • Output starts re-explaining the task rather than executing it

Weak signals (trigger recovery)

  • Responses are getting longer without getting more useful
  • Hedging language increases: "it depends", "could be", "might want to consider"
  • The agent switches approaches mid-task without explicit user direction
  • References to the original intent become vague or paraphrased

Recovery Protocol (Wave Re-Anchor)

When weak signals accumulate, try to re-anchor first:

Step 1: Pause and re-read

Stop producing output. Re-read whatever wave anchor artifacts are available:

  1. If an intent frame exists, open and read it verbatim
  2. If a plan file exists, open and read the relevant section
  3. Re-read the user's original task description and project context files

Step 2: Reconcile

  • If the mismatch resolves — resume execution
  • If uncertainty remains — spawn a context-monitor subagent for a fresh perspective
  • If the subagent confirms strong drift — escalate to the user
  • If the user re-grounds you — integrate and resume
  • If the user can't resolve it — proceed to Exit Protocol

Exit Protocol (Wave Close-Out)

When a strong signal fires, or recovery fails:

Step 1: Stop executing

Immediately pause task execution.

Step 2: Write the handoff file

Create .context-surfing/handoff-[slug]-[timestamp].md:

# Context Surf Handoff

## Session Info
- Task: [task name / slug]
- Started: [timestamp]
- Ended: [timestamp]
- Exit reason: [what drift signal was detected]

## Intent Frame (if available)
[copy directly from intent-framed-agent artifact]

## Plan (if available)
[copy directly from plan-interview artifact]

## Completed Work
[what was done]

## In Progress at Exit
[what was active]

## Pending Work
[remaining tasks]

## Drift Notes
[what triggered the exit]

## Active Context Files
[list .md files loaded]

## Modified Context Files
[list .md files changed]

## Recommended Re-entry Point
[where to pick up]

Step 3: Notify the user

"Context wave is done. I've saved the session state to .context-surfing/[filename]. The next session should load that file and catch the next wave."

Principles

Ride the peak, not the whole ocean. A shorter session with high fidelity beats a long session with gradual corruption.

Exit is not failure. The wave close-out is a feature.

The handoff file is the continuity. It's what makes the next session as sharp as this one started.

Never hide the exit. Always be explicit with the user that a context exit happened and why.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

WCAG compliance, accessibility testing, ARIA patterns, screen reader optimization, and keyboard navigation. Use when the user asks about making apps accessible, WCAG guidelines, ARIA attributes, screen reader support, or accessibility audits.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

ProjectZeroDays/FreeAI_AI_Inference_Workstation52026년 9월 4일 업데이트

ace-music

무료

Generate AI music using ACE-Step 1.5 via ACE Music's free API. Use when the user asks to create, generate, or compose music, songs, beats, instrumentals, or audio tracks. Supports lyrics, style prompts, covers, and repainting. Free API, no cost.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

ProjectZeroDays/FreeAI_AI_Inference_Workstation52026년 9월 4일 업데이트

A continuously adaptive skill suite that empowers Clawdbot to act as a versatile coder, business analyst, project manager, web developer, data analyst, and NAS metadata scraper. It intelligently discovers free resources, adapts to user context, and ensures reliable, proven guidance across multiple domains.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

ProjectZeroDays/FreeAI_AI_Inference_Workstation52026년 9월 4일 업데이트

High-fidelity intelligence gathering and data assimilation. Focuses on synthesizing fragmented data into a comprehensive target operational picture.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

ProjectZeroDays/FreeAI_AI_Inference_Workstation52026년 9월 4일 업데이트

Use when Codex needs proactive task queues, heartbeat routines, scheduled follow-up, or continuous work loops instead of waiting for prompts.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

ProjectZeroDays/FreeAI_AI_Inference_Workstation52026년 9월 4일 업데이트

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

ProjectZeroDays/FreeAI_AI_Inference_Workstation52026년 9월 4일 업데이트

ProjectZeroDays의 스킬 모두 보기

이 스킬의 문제 신고