Skills

Continue Claude Code Work

Continues interrupted Claude Code work after local history is read and reconciled, ...

Install

npx skills add daymade/claude-code-skills --skill continue-claude-code-work -g -a claude-code -y
Category
AI and agents
Updated
3d ago
License
MIT
Context cost
Lightabout 932 tokens
Runs scripts
No, instructions only

What it does

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).

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.

FieldEvidence required
Original business outcomeEarliest still-governing human request, not a later implementation detail
Current explicit requestLatest human request that is not merely “继续”
Already completedIndependent current-state verification, not the old Agent's claim
Still unfulfilledRequested result with no completion evidence
User corrections / do-not-repeatHuman messages that rejected a route, output, or assumption
Proven assets and successful routesExisting code, docs, Skills, outputs, or commands that previously worked
Next direct actionOne action whose success visibly reduces the unfulfilled business result
Read the whole SKILL.md on GitHub

More in AI and agents