Agent Skills › daymade/claude-code-skills › continue-claude-code-work

continue-claude-code-work

GitHub

在Claude Code会话中断后,通过读取历史、重建任务契约并校验当前环境状态,无缝恢复未完成的业务执行。

daymade-claude-code/continue-claude-code-work/SKILL.md daymade/claude-code-skills

Trigger Scenarios

会话中断或压缩后需恢复工作 提供Session ID要求接管任务 被指示在不使用resume参数时继续之前工作

Install

npx skills add daymade/claude-code-skills --skill continue-claude-code-work -g -y
More Options

Non-standard path

npx skills add https://github.com/daymade/claude-code-skills/tree/main/daymade-claude-code/continue-claude-code-work -g -y

Use without installing

npx skills use daymade/claude-code-skills@continue-claude-code-work

指定 Agent (Claude Code)

npx skills add daymade/claude-code-skills --skill continue-claude-code-work -a claude-code -g -y

安装 repo 全部 skill

npx skills add daymade/claude-code-skills --all -g -y

预览 repo 内 skill

npx skills add daymade/claude-code-skills --list

SKILL.md

Frontmatter
{
    "name": "continue-claude-code-work",
    "description": "Continues interrupted Claude Code work after local history is read and reconciled — reconstructs the original outcome, unfulfilled requests, and the next action. Use when given a Claude Code Session ID, asked to pick up prior Claude work, told a run was interrupted or compacted, or asked to take over without `claude --resume`. Not for Codex sessions (use continue-codex-work).",
    "argument-hint": "[session-id]"
}

Continue Claude Code Work

Continue means execute the still-unfinished business task. It does not mean summarize the transcript, perfect the history tool, or start a new experiment.

Step 1: Obtain a verified read receipt

Invoke daymade-claude-code:read-claude-code-history for the exact Session. Ask that Skill for a chronological evidence briefing, not separate “last user” and “last assistant” buckets. If the Session ID is unknown, use its search/inventory route first.

Do not act until the receipt states:

  • exact Session ID and project;
  • sources and time coverage;
  • compaction and raw-chronology boundaries;
  • every retained human request, including queued prompts;
  • end reason, unresolved calls, files touched, and explicit gaps.

If a clipped section could contain the objective or a correction, re-read it with the reader's full mode. If identity, ancestry, or authorship is unresolved, stop; continuing from a guessed Session is worse than asking for the missing evidence.

Step 2: Rebuild the continuation contract

Before the first project-changing tool call, write this compact internal contract from evidence. Do not invent a value to fill a blank.

Field Evidence required
Original business outcome Earliest still-governing human request, not a later implementation detail
Current explicit request Latest human request that is not merely “继续”
Already completed Independent current-state verification, not the old Agent's claim
Still unfulfilled Requested result with no completion evidence
User corrections / do-not-repeat Human messages that rejected a route, output, or assumption
Proven assets and successful routes Existing code, docs, Skills, outputs, or commands that previously worked
Next direct action One action whose success visibly reduces the unfulfilled business result

When the latest message is only “继续,” inherit the objective from the verified chronology. Never treat the cue itself as the specification.

Step 3: Reconcile with current reality

  1. Read the target project's current AGENTS.md/CLAUDE.md and authoritative project state; historical instructions may be stale.
  2. Confirm the current cwd, branch, working tree, and relevant files.
  3. Verify whether prior writes, commits, external operations, or background jobs actually landed. A transcript records attempts as well as successes.
  4. Retrieve the proven asset or prior successful path before authoring a replacement.
  5. If another process may still complete the same transiently failed work, verify its current result before duplicating it.

Step 4: Execute the business task

Take the next direct action from the contract and verify its result. Skill edits, review expansion, documentation systems, and infrastructure cleanup remain subordinate unless the user explicitly made one of them the business outcome or they are strictly required to unblock it.

Before changing direction, ask mechanically: “If this succeeds, which original unfulfilled result becomes smaller?” If the answer is none, record it as a later proposal and return to the task.

Do not run claude --resume or claude --continue. Do not overwrite unrelated working-tree changes.

Step 5: Report against the contract

  • Recovered goal: Session and original business outcome.
  • Executed: actions and independent verification.
  • Now complete: contract rows that are actually closed.
  • Remaining: unfulfilled rows and exact blockers.
  • Not repeated: prior rejected routes deliberately avoided when relevant.

Do not say “continued successfully” when only context extraction or a process step completed; the business result is the completion unit.

Version History

  • c6903aa Current 2026-09-28 12:34

    精简技能描述以符合字符长度规范(#695)

  • 98c21cf 2026-08-28 22:48

Same Skill Collection

auto-repo-setup/SKILL.md
bilibili-source/SKILL.md
capture-screen/SKILL.md
cli-demo-generator/SKILL.md
cloudflare-troubleshooting/SKILL.md
codex-image-gallery/SKILL.md
competitors-analysis/SKILL.md
data-visualization-discipline/SKILL.md
daymade-audio/asr-transcribe-to-text/SKILL.md
daymade-audio/audio-router/SKILL.md
daymade-audio/meeting-minutes-taker/SKILL.md
daymade-audio/stepfun-asr/SKILL.md
daymade-audio/stepfun-tts/SKILL.md
daymade-audio/transcript-fixer/SKILL.md
daymade-claude-code/agent-web-search-setup/SKILL.md
daymade-claude-code/claude-code-hooks/SKILL.md
daymade-claude-code/claude-code-ops-router/SKILL.md
daymade-claude-code/claude-code-ping-start-5h-quota/SKILL.md
daymade-claude-code/claude-export-txt-better/SKILL.md
daymade-claude-code/claude-skills-troubleshooting/SKILL.md
daymade-claude-code/claude-switch-models-setup/SKILL.md
daymade-claude-code/claude-usage-analyst/SKILL.md
daymade-claude-code/continue-claude-work/SKILL.md
daymade-claude-code/continue-codex-work/SKILL.md
daymade-claude-code/lark-cli-router/SKILL.md
daymade-claude-code/local-conversation-history/SKILL.md
daymade-claude-code/marketplace-dev/SKILL.md
daymade-claude-code/prior-work-retrieval/SKILL.md
daymade-claude-code/read-claude-code-history/SKILL.md
daymade-claude-code/read-claude-web-conversation/SKILL.md
daymade-claude-code/read-codex-history/SKILL.md
daymade-claude-code/statusline-generator/SKILL.md
daymade-claude-code/tech-selection/SKILL.md
daymade-claude-code/terminal-screenshot/SKILL.md
daymade-codex/codex-1m-context-window-setup/SKILL.md
daymade-codex/codex-image-gallery/SKILL.md
daymade-codex/design-style-picker/SKILL.md
daymade-codex/interaction-design-board/SKILL.md
daymade-codex/local-codex/SKILL.md
daymade-docs/docs-router/SKILL.md
daymade-docs/docx-creator/SKILL.md
daymade-docs/excel-automation/SKILL.md
daymade-docs/mermaid-tools/SKILL.md
daymade-docs/pdf-creator/SKILL.md
daymade-docs/ppt-creator/SKILL.md
daymade-docs/read-docx-review/SKILL.md
daymade-financial/ashare-news-fetcher/SKILL.md
daymade-financial/benchmark-due-diligence/SKILL.md
daymade-financial/bigdata-skill/SKILL.md

Metadata

Files
0
Version
c6903aa
Hash
7fd51ed2
Indexed
2026-08-28 22:48

ホーム - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-09-29 02:00
浙ICP备14020137号-1