Menu
Create a detailed TDD implementation plan with parallel tasks from a feature spec or description.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | plan |
| description | Create a detailed TDD implementation plan with parallel tasks from a feature spec or description. |
| argument-hint | <feature spec or description> |
| user-invocable | true |
| disable-model-invocation | true |
Launch the planner agent in the foreground with the user's feature specification or description.
The planner may return a STATUS: NEEDS_INPUT response instead of a finished plan. This response can contain any combination of:
When this happens:
resume parameter with its agent ID) with the user's answersWhen the devline orchestrator invokes this skill during a multi-phase pipeline, it passes phase context to the planner:
.devline/plan-phase-1.md).devline/plan-phase-N.md instead of .devline/plan.mdPass this context through when launching the planner agent. The planner uses it to scope the plan to the current phase and avoid re-planning prior phases' work.
When no phase context is provided (the default), the planner writes to .devline/plan.md exactly as today — this path is unchanged.
Once the planner has all answers, it will:
.devline/plan.md (single-phase) or .devline/plan-phase-N.md (multi-phase)Present the summary to the user for approval. The full plan lives at the output path — implementers read it directly from disk.
This skill does NOT automatically continue into implementation. To proceed, run /devline:implement with the approved plan, or /devline for the full pipeline.
Grep-based reverse dependency analysis — injected into planner, reviewer, and deep-review agents. Computes which files are affected by changes to a set of seed files. Not invoked directly.
This skill should be used when the user asks to "brainstorm", "refine an idea", "flesh out a feature", "define requirements". Guides interactive refinement of rough ideas into concise, actionable feature specifications. Focuses on the "what" and architecture — never the "how".
This is the default skill for all development work. It orchestrates the entire development lifecycle from idea to merge-ready code, coordinating multiple agents for brainstorming, planning, implementation, review, documentation, and final approval. Use this for any development task that is non-trivial and could benefit from structured planning, parallel execution, and rigorous review or require more than 3 lines of code changed.
Retrieves authoritative, up-to-date technical documentation, API references, configuration details, and code examples for any developer technology. Use this skill whenever answering technical questions or writing code that interacts with external technologies. This includes libraries, frameworks, programming languages, SDKs, APIs, CLI tools, cloud services, infrastructure tools, and developer platforms. Common scenarios: - looking up API endpoints, classes, functions, or method parameters - checking configuration options or CLI commands - answering "how do I" technical questions - generating code that uses a specific library or service - debugging issues related to frameworks, SDKs, or APIs - retrieving setup instructions, examples, or migration guides - verifying version-specific behavior or breaking changes Prefer this skill whenever documentation accuracy matters or when model knowledge may be outdated.
Implement tasks using TDD. Accepts a plan or specific task description. Runs implementer agents in parallel where possible.
Design intelligence for UI/UX — injected into the frontend-planner agent. Provides BM25-searchable database of 67 styles, 161 color palettes, 57 font pairings, 160 animated component patterns, 161 industry rules, plus framework-agnostic design guidelines. Not invoked directly.