en un clic
save-task-list
Save current task list for reuse across sessions
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Menu
Save current task list for reuse across sessions
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Use when: User wants to run a SUBSTANTIAL multi-step coding task as a workflow (fix/implement a whole issue or feature, comprehensive review), CREATE workflows or commands, set up workflow automation, or manage workflow configuration. Triggers (run): "use workflow to", "run workflow", "with workflow", "workflow to", "workflow run", "use a workflow to", "run a workflow", and generic task-completion intents that imply a full coding deliverable: "실행해줘", "돌려줘", "구현해줘", "고쳐줘", "이슈 고쳐줘", "PR 만들어줘", "implement this", "fix this issue", "build this feature", "ship this". Triggers (create): "create a workflow", "write a workflow", "make a command", "author a workflow", "new workflow", "new command", "workflow yaml". Triggers (setup): "set up workflows", "install workflow automation", "how to use workflows", "configure workflows", "workflow setup", "get started with workflows". Triggers (config): "change my workflow config", "modify workflow config", "workflow
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Smelter deep interview for planning-first requirement discovery before /brainstorm, /implement, or /fix execution
Create a release from dev branch. Generates changelog entries from commits, bumps version, and creates a PR to main. TRIGGERS - Use this skill when user says: - "/release" - create a patch release (default) - "/release minor" - create a minor release - "/release major" - create a major release - "make a release", "cut a release", "ship it", "release to main"
Replicate and validate a GitHub issue by spinning up Smelter, analyzing the issue, and systematically testing all described symptoms using browser automation. Use when: User wants to reproduce a bug, validate a GitHub issue, confirm a reported problem, or investigate whether an issue is real before working on a fix. Triggers: "replicate issue", "reproduce issue", "validate issue", "confirm bug", "test issue", "can you reproduce", "try to replicate", "verify the bug". Capability: Checks out main, pulls latest, starts Smelter, reads the GitHub issue, then uses agent-browser to systematically test every symptom and produce a findings report. NOT for: Fixing issues (use /smelter or /exp-piv-loop:fix-issue), general UI testing (use /validate-ui).
Autonomous rule adherence checker. Scans the codebase for rule violations, fixes the highest-impact ones in an isolated worktree, runs full validation, creates a PR. Uses memory to track progress across runs.
| name | save-task-list |
| description | Save current task list for reuse across sessions |
| disable-model-invocation | true |
| hooks | {"Stop":[{"hooks":[{"type":"prompt","prompt":"A skill just finished saving a task list for session reuse.\nEvaluate the assistant's final message below.\n\n$ARGUMENTS\n\nVerify:\n1. A task list ID was found and displayed\n2. A startup command (CLAUDE_CODE_TASK_LIST_ID=<id> claude) was provided\n3. A task summary was shown\n\nReturn {\"ok\": true} if all three are present.\nReturn {\"ok\": false, \"reason\": \"Missing: <what>\"} if anything is missing.\n","statusMessage":"Verifying task list was saved..."}]}],"PostToolUse":[{"matcher":"Bash","hooks":[{"type":"command","command":"jq -r '[.tool_name, .tool_input.command // \"n/a\"] | join(\": \")' | head -1","statusMessage":"Logging tool use...","once":true}]}]} |
Save the current session's task list so it can be restored in future sessions.
ls -1t ~/.claude/tasks/ 2>/dev/null | head -5 || echo "none found"ls -1t ~/.claude/tasks/ 2>/dev/null | head -1 | xargs -I{} ls ~/.claude/tasks/{} 2>/dev/null | head -10 || echo "no tasks"Find the current task list ID by checking ~/.claude/tasks/ for the most
recently modified directory. List the directories sorted by modification time.
Verify the match — read the task files inside the directory and compare them to any tasks you know about from this session. Confirm you have the correct task list.
Log the session mapping — write the mapping to .claude/smelter/sessions/:
mkdir -p .claude/smelter/sessions
echo '{"session": "${CLAUDE_SESSION_ID}", "task_list": "<TASK_LIST_ID>", "saved_at": "'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' \
>> .claude/smelter/sessions/task-lists.jsonl
Verify the SessionStart hook is installed — the project-level
.claude/settings.json already includes a SessionStart hook that runs
verify-task-list.sh on every session start. Confirm it's present by
reading the file. If it's missing for some reason, add it back:
{
"hooks": {
"SessionStart": [
{
"hooks": [
{
"type": "command",
"command": ".claude/skills/save-task-list/hooks/verify-task-list.sh",
"statusMessage": "Checking for restored task list..."
}
]
}
]
}
}
Important: Merge — don't overwrite existing settings. If hooks or SessionStart
already exists, append to the array. If the hook is already installed, skip this step.
Output the startup command for the user:
To continue with this task list in a new session:
CLAUDE_CODE_TASK_LIST_ID=<task_list_id> claude
Explain: On startup, the SessionStart hook will verify the task list exists and show a confirmation message.
Show the current task summary so the user knows what's preserved (task subjects, statuses, and any dependencies).