Run Tasks — Productivity skill for Claude Code
You are executing the /run-tasks command.
How to install Run Tasks
Installs to ~/.claude/skills/ekirton-poule-run-tasks/SKILL.md
mkdir -p ~/.claude/skills/ekirton-poule-run-tasks && curl -fsSL https://raw.githubusercontent.com/ekirton/Poule/HEAD/commands/run-tasks.md -o ~/.claude/skills/ekirton-poule-run-tasks/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Run Tasks does
You are executing the `/run-tasks` command. This command reads a task file containing slash commands, executes each one serially, and commits after each successful task.
Determine the task file
The user may provide a file path argument after `/run-tasks`. If no argument is given, default to `todo.md` in the current working directory.
Use `Read` to open the task file. If it does not exist, tell the user: "Task file not found: ``. Create it with `- [ ] /command args` entries and re-run
Alternatives in Productivity
- Claude Task Viewer — A web-based Kanban board for viewing Claude Code tasks 496 ★
- Chief — CLI that wraps Claude Code in a loop 396 ★
- Claudenightswatch — Autonomous task execution system for Claude CLI that monitors your usage windows and executes predefined tasks 352 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Proof Repair
You are executing the /proof-repair workflow. This command automates repair of Coq proofs that broke after a v
Agent Execute
SDD Phase 3 — Execute one task from TASKS.md in fresh context (Ralph loop pattern). Writes code, commits atomi
Run Todos
Implement [ready]-tagged TODO items with commits. Triggers after /list-todos marks items as [ready].
Massu CI Fix
When CI fails after push — auto-diagnoses failures, fixes, commits, and re-pushes. 'ci fix', 'fix ci', 'ci fai
Ve Vibe Board
Task board and session handoff for Claude Code agents. 14 MCP tools for projects, tasks, sessions, and activit
Find Unparked Items
Survey the workspace for RFDs and tasks that are actively being worked on — not shipped, not shelved, not aban
Related Agents
Pull Analyst
Post-pull advisory analyst subagent. Reads the new-commits range after a successful git pull --rebase and prod
Scaffold Inspect
Sets up inspect-ai evaluation configurations for all runs in a designed experiment. Reads experiment_summary.y
Sdd Implementer
Executes exactly one well-specified task from a spec's tasks.md, as dispatched by the orchestrating session —