القائمة
Use when user wants to Creates a technical plan at .specs/{feature}/plan.md translating a spec's functional requirements into architecture, technology, and code decisions.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Execute a Trellis task list by dispatching each task to a Claude Code subagent in its own context window. Use when the user says "build with sub-agents", "build with subagents", or when a feature has 5-20 tasks with dependencies between them. Reads `.specs/<feature>/tasks.md` produced by the tasks skill. Each subagent gets focused context (guidelines + plan + task + learnings) and returns results to the orchestrating session. Supports parallel execution of independent tasks via background subagents with worktree isolation.
Execute a Trellis task list using Claude Code's /batch command for bulk, patterned changes across many files. Use when the user says "build with batch" or when a feature involves repetitive changes across dozens or hundreds of files (e.g., migrating from one library to another, applying naming conventions, adding error handling patterns). Reads `.specs/<feature>/tasks.md` produced by the tasks skill. Translates the task list into one or more /batch invocations with worktree-isolated parallel agents.
Creates or updates .specs/guidelines.md with project-wide stack, conventions, and principles. Use when starting a project or when a fundamental technology decision has changed.
Use when user wants to Creates a pitch document at .specs/{feature}/pitch.md defining a problem domain with constraints, appetite, and solution shape. Use to frame a feature before writing a spec.
Use when user wants to Creates a lightweight experiment document at .specs/sketches/{slug}.md to test a technical hypothesis before committing to a larger initiative.
Use when user wants to Creates a full functional specification at .specs/{feature}/spec.md defining what a system does and why. Use to write or revise feature requirements.
| name | trellis:plan |
| description | Use when user wants to Creates a technical plan at .specs/{feature}/plan.md translating a spec's functional requirements into architecture, technology, and code decisions. |
| allowed-tools | Read, Glob, Grep, Task |
Create a technical implementation plan at .specs/<feature-name>/plan.md.
Recommended effort: medium. Template-driven but references multiple input artifacts.
Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/validate-prereqs.py plan <feature-name> and use the specsDir value from the JSON output. Abort if the output reports missing prerequisites.
Before generating the plan, ensure the spec is ready. These steps run automatically — the user does not need to invoke them separately.
Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/extract-markers.py <specsDir>/<feature-name>/spec.md to check for unresolved [? ...] markers.
/clarify skill against the spec. Since clarify runs in a forked context (isolated, no user interaction), it resolves what it can and moves user-judgment items to §10 (Open Questions). Re-check markers after each pass. Loop limit: 3 passes. After 3, move any remaining markers to §10 and continue.Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/pipeline-status.py <feature-name> and check the complianceNeeded and complianceCompleted fields.
complianceNeeded is false: Skip compliance.complianceCompleted is true (compliance.md already exists): Skip compliance./compliance skill. Since compliance runs in a forked context, ensure any user-provided regulation context is embedded in the spec's §9 (Constraints) before invoking. If compliance recommends spec changes, apply them, re-run clarify on modified sections, then re-run compliance. Loop limit: 2. After 2 loops, document remaining gaps as residual risks in compliance.md and continue.After pre-steps complete, proceed to plan generation below.
If the user runs /plan without additional context, check if the prerequisites exist. Then ask:
After gathering all user input, spawn the planner agent. Pass it: the feature name, specs directory path, and all user-provided context. The agent will read prerequisite files and generate the plan document.