Menu
Delegate tasks to parallel worktree agents.
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
Run nf-core bioinformatics pipelines (rnaseq, sarek, atacseq) on sequencing data. Use when analyzing RNA-seq, WGS/WES, or ATAC-seq data—either local FASTQs or public datasets from GEO/SRA. Triggers on nf-core, Nextflow, FASTQ analysis, variant calling, gene expression, differential expression, GEO reanalysis, GSE/GSM/SRR accessions, or samplesheet creation.
Simple task management using a shared TASKS.md file. Reference this when the user asks about their tasks, wants to add/complete tasks, or needs help tracking commitments.
Use when you need direct browser control - teaches Chrome DevTools Protocol for controlling existing browser sessions, multi-tab management, form automation, and content extraction via use_browser MCP tool
Use when working on Claude Code plugins (creating, modifying, testing, releasing, or maintaining) - provides streamlined workflows, patterns, and examples for the complete plugin lifecycle
Use when working with Claude Code CLI, plugins, hooks, MCP servers, skills, configuration, or any Claude Code feature - provides comprehensive official documentation for all aspects of Claude Code
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
| name | worktree |
| description | Delegate tasks to parallel worktree agents. |
| disable-model-invocation | true |
Launch one or more tasks in new git worktrees using workmux.
Tasks: $ARGUMENTS
FORBIDDEN: Do NOT read source files, edit code, or fix issues yourself. You
only write prompt files and run workmux add commands.
If tasks reference earlier conversation (e.g., "do option 2"), include all relevant context in each prompt you write.
If tasks reference a markdown file (e.g., a plan or spec), re-read the file to ensure you have the latest version before writing prompts.
For each task:
workmux add <worktree-name> -b -P <temp-file> to create the worktreeThe prompt file should:
If the user passes a skill reference (e.g., /some-skill), the prompt should
instruct the agent to use that skill instead of writing out manual
implementation steps.
Skills can have flags. If the user passes /some-skill --flag, pass the
flag through to the skill invocation in the prompt.
Example prompt:
[Task description here]
Use the skill: /skill-name [flags if any] [task description]
Do NOT write detailed implementation steps when a skill is specified - the skill handles that.
--merge: When passed, add instruction to use /merge skill at the end to
commit, rebase, and merge the branch.
...
Then use the /merge skill to commit, rebase, and merge the branch.
Write ALL temp files first, THEN run all workmux commands.
Step 1 - Write all prompt files (in parallel):
tmpfile=$(mktemp).md
cat > "$tmpfile" << 'EOF'
Implement feature X...
EOF
echo "$tmpfile" # Note the path for step 2
Step 2 - After ALL files are written, run workmux commands (in parallel):
workmux add feature-x -b -P /tmp/tmp.abc123.md
workmux add feature-y -b -P /tmp/tmp.def456.md
After creating the worktrees, inform the user which branches were created.
Remember: Your task is COMPLETE once worktrees are created. Do NOT implement anything yourself.