Skills Explorer Add Skills

continue-claude-code-work

An agent skill by daymade, from daymade/claude-code-skills. Tags: analysis, local-workflow, resilience, triage, workflow.

What it does

Continues interrupted Claude Code work only after local history has been read and reconciled. Use when the user provides a Claude Code Session ID, asks to pick up prior Claude work, says a Claude run was interrupted or compacted, or wants the current Agent to take over without `claude --resume`. Reconstructs the original business outcome, unfulfilled requests, user corrections, successful prior assets, current workspace truth, and the next action that directly advances the goal. For Codex sessions use continue-codex-work.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add daymade/claude-code-skills --skill continue-claude-code-work

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/daymade/claude-code-skills
cp -r claude-code-skills/daymade-claude-code/continue-claude-code-work ~/.claude/skills/continue-claude-code-work

Safety box score

Grade B, low risk: 18 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill resumes prior Claude Code work by reading local session history, reconstructing the unfinished task, and then continuing the project from the current working tree. The main risk is exposure of prior transcript contents, including anything the user may have said or pasted in that session, plus project-file edits made while resuming work.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution0 (none)`SKILL.md` does not define any shell script, code evaluator, or native executable; it only instructs the agent to use other skills and not to run `claude --resume`/`--continue`.
Network access0 (none)No downloads, uploads, remote API calls, or external posting are specified in `SKILL.md`.
Filesystem reach1 (low)It explicitly tells the agent to inspect the current `cwd`, branch, working tree, and relevant files, and then take the next direct action, which may include edits but is scoped to the project.
Secrets & credentials2 (moderate)Step 1 requires a chronological read of Claude Code history and says to include "every retained human request, including queued prompts," which can surface sensitive transcript contents.
Privilege & persistence0 (none)There is no request to use `sudo`, install globally, change services, or modify shell/OS settings.
Instruction hijack surface0 (none)The skill contains no hidden payloads or instructions to ignore higher-priority rules; it actually adds guardrails like waiting for a verified receipt and reconciling with current project state.
Irreversible actions1 (low)It directs the agent to "execute the still-unfinished business task" and "Take the next direct action," so it can continue work on its own, but it does not itself publish, deploy, send, or delete externally.
Transparency0 (none)The skill file is plain markdown with no binaries, obfuscated blobs, or remotely fetched code.

Before installing

Rated 2026-10-20 by an automated review of 1 file from the skill's repository.

Source

Repository
daymade/claude-code-skills (all skills from this repository)
Path
daymade-claude-code/continue-claude-code-work/SKILL.md
Branch
main
Updated
2026-09-20