done
Done — Complete Current Task
Mark a task as completed in today's task file and show remaining work.
Configuration
persistence:
tasksDir: "~/.claude/daily-tasks"
Execution Steps
1. Load Task File
Read today's task file:
cat ~/.claude/daily-tasks/$(date +%Y-%m-%d).json 2>/dev/null
If no file exists: "No task file for today. Nothing to mark as done." Stop here.
Parse the JSON.
2. Identify Task to Complete
If $ARGUMENTS is a number: target that task ID.
If $ARGUMENTS matches a Jira key pattern (e.g., RGI-265): find the task with matching jira_key.
If $ARGUMENTS is empty: find the task with status: "in_progress".
- If multiple tasks are
in_progress, list them and ask which one to complete. - If no task is
in_progress: "No task currently in progress. Specify a task ID:/done 3" - Stop here if unable to identify a single task.
Validation:
- If the selected task has
status: "done": "Task #N is already done." - If the selected task ID doesn't exist: "Task #N not found. Today has tasks 1-M."
- If the selected task has
status: "pending"(never started): Mark as done anyway, but note: "Task #N was never started — marking as done directly."
3. Mark as Done
Read the current task file, update the target task:
- Set
statusto"done" - Set
completed_atto current ISO timestamp (usedate -u +%Y-%m-%dT%H:%M:%SZ) - Update
updated_aton the root object
Write the updated JSON back using the Write tool.
4. Show Completion Summary
Display:
✅ Task #N done: $JIRA_KEY — $SUMMARY
If started_at exists, calculate and show duration:
⏱️ Duration: Xh Ym
Show overall progress:
📋 Progress: N/M tasks done today
5. Show Next Task
List remaining pending tasks (compact, one line each):
Remaining:
#N. [TIER] $JIRA_KEY — $SUMMARY
#N. [TIER] $JIRA_KEY — $SUMMARY
Suggest the next task:
👉 Next up: Task #N ($JIRA_KEY) — $SUMMARY
Run /todo to pick it up, or /todo M for a different task.
6. All Done State
If no pending or in-progress tasks remain:
🎉 All tasks for today are done!
📋 Final: M/M complete
⏱️ Total tracked time: Xh Ym (sum of all tasks with started_at and completed_at)
Consider:
- Running /morning-standup to refresh and check for new items
- Checking Jira backlog for new work
Edge Cases
- Multiple
in_progresstasks, no argument: List all in-progress tasks with IDs and ask which to complete. Do not guess. - Task is
skipped: Allow marking asdone— change status fromskippedtodone. - File write fails: Report error, do not silently lose the update.
- Concurrent modification: Read-then-write is sufficient for single-user workflow. If the file was modified between read and write, the latest write wins.
More from benjaming/ai-skills
confluence-cli
Use confluence-cli (NPM package) to manage Confluence content, pages, and spaces from the command line. Ideal for documentation workflows, bulk content operations, page migration, and when users request CLI-based Confluence interactions. Trigger on requests like "use Confluence CLI", "create Confluence pages via CLI", "migrate Confluence content", "automate documentation workflows", or when users want to script Confluence operations.
43atlassian-cli-jira
Use Atlassian CLI (acli) to manage Jira work items, projects, and workflows from the command line. Ideal for bulk operations, automation, scripting, and when users request CLI-based Jira interactions. Trigger on requests like "use Jira CLI", "create Jira issues via CLI", "bulk update Jira tickets", "automate Jira workflows", or when users want to script Jira operations.
29ralph-loop
Create autonomous iterative loops (Ralph Wiggum pattern) for multi-step tasks. Use when setting up automated workflows that iterate over a backlog of tasks with clear acceptance criteria. Triggers on requests like "create a ralph loop", "set up an iterative agent", "automate this migration", or "create an autonomous loop".
21interview
Interview user to clarify any topic - exploring codebase, investigating issues, planning features, understanding requirements, or drilling into plans. Socratic questioning to uncover details.
20codex-cli
Use OpenAI Codex CLI in non-interactive mode for automated code analysis, review, and programmatic task execution. Trigger on requests like "use Codex to analyze", "run codex exec", "codex code review", or when users want AI-powered code analysis without interactive prompts. Ideal for automation workflows, code quality checks, and generating structured analysis reports.
19daily-standup
Daily standup assistant for Benjamin that compiles work priorities from Jira and Slack into a single prioritized task list. This skill should be used when Benjamin asks for morning standup, daily priorities, what to work on today, or needs to compile work items.
18