/writing-plans
Writing a rolling-wave phased implementation plan from a spec before coding: a phase-epic-task hierarchy where Phase 1 is detailed into dispatch-ready tasks and later phases stay epic-level for elaboration during execution. Use when a multi-file feature needs decomposition; runs
$ npx -y skills add LerianStudio/ring --skill writing-plans --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/writing-plans
Context preview
The summary Claude sees to decide when to auto-load this skill.
Writing a rolling-wave phased implementation plan from a spec before coding: a phase-epic-task hierarchy where Phase 1 is detailed into dispatch-ready tasks and later phases stay epic-level for elaboration during execution. Use when a multi-file feature needs decomposition; runs
SKILL.md
writing-plans.SKILL.mdname: ring:writing-plans
description: "Writing a rolling-wave phased implementation plan from a spec before coding: a phase-epic-task hierarchy where Phase 1 is detailed into dispatch-ready tasks and later phases stay epic-level for elaboration during execution. Use when a multi-file feature needs decomposition; runs after ring:exploring-codebases or pre-dev gates, hands off to ring:executing-plans or ring:running-dev-cycle. Skip for single-file changes or spikes."
Writing Plans
When to use
- Spec or requirements exist for a multi-step task and no implementation has started
- Feature spans multiple files/layers and needs decomposition before coding
- Handing off implementation to a separate session, agent, or human
Skip when
- Single-file change with obvious shape (just do it)
- Exploratory spike — phased plans assume known requirements
- Spec is still in brainstorming; the plan would lock premature decisions
Sequence
**Runs after:** ring:exploring-codebases, ring:planning-large-features (gates 0-6 artifacts) or ring:planning-small-features (gates 0-2 artifacts) — their outputs feed the spec **Runs before:** ring:executing-plans (rolling-wave execution) or ring:running-dev-cycle (gated subagent workflow)
Related
**Companion:** [plan-document-reviewer-prompt.md](plan-document-reviewer-prompt.md) — subagent dispatch template for thorough plan review
---
Write the plan assuming the implementer is skilled but has zero context for this codebase, toolset, or problem domain.
The plan is a **rolling-wave document**. Only the first phase is detailed to task level at plan time; later phases stay at epic level until execution reaches them. Detail decays: code written in Phase 1 invalidates assumptions baked into Phase 3 tasks, so do not write Phase 3 tasks yet. ring:executing-plans elaborates each subsequent phase against the codebase as it actually exists.
**Announce at start:** "Using ring:writing-plans to author the implementation plan."
**Default save path:** `docs/plans/YYYY-MM-DD-<feature-name>.md` (User preferences override.)
**Invoked from pre-dev:** when dispatched as the final gate of ring:planning-large-features or ring:planning-small-features, the spec inputs are the pre-dev artifacts — trd.md (plus feature-map.md, openapi.yaml, the schema file, and dependencies.md on the Large track). On Large, plan phases MUST mirror feature-map.md phases one-to-one. Output path is `docs/pre-dev/{feature}/plan.md`, overriding the default above; standalone invocations keep the default. plan.md is always a SINGLE document per feature: on multi-module topologies (monorepo fullstack / multi-repo), each epic carries one line `**Target:** backend | frontend | infra` (placed right before `**Status:**`); for multi-repo features the orchestrator copies plan.md into each repo and the local dev-cycle executes only epics whose Target matches that repo. No per-module plan splits.
Plan Language
Before authoring, ask which language the plan's **prose** should be written in — using the question/ask tool the harness provides (e.g. `AskUserQuestion` in Claude Code). Offer three options: **English** (default), **Brazilian Portuguese (pt-BR)**, **Spanish**. If the user skips or no question tool is available, default to English.
The choice covers narrative prose only — Goal, Architecture, Context, Implementation vision, and other descriptions. Everything a downstream skill or agent parses stays verbatim English regardless of choice: section headers and format keywords, `**Status:**` values (Pending/Doing/Done/Failed), Phase-Overview status cells (Detailed/Epic-level/Complete), `**Target:**` values, file paths, commands, code snippets, and identifiers. Translating those breaks ring:executing-plans and ring:running-dev-cycle status matching.
Standards
Do NOT fetch standards documents while planning — standards compliance is enforced by the implementation agents and reviewers downstream. Plans reference DRY, YAGNI, and TDD generically.
Blocker — STOP and Report
Do not write a plan on a shaky foundation. STOP and ask when:
| Situation | Action | |-----------|--------| | Vague requirements ("make it better", "add feature") | STOP. Ask: "What specific behavior should change?" | | Missing success criteria | STOP. Ask: "How do we verify this works?" | | Unknown codebase structure (can't locate files) | STOP. Run ring:exploring-codebases first, then plan | | Conflicting constraints | STOP. Ask: "Which constraint takes priority?" | | Multiple valid architectures without guidance | STOP. Ask: "Which pattern should we use?" |
Scope Check
If the spec covers multiple independent subsystems, suggest breaking it into separate plans — one per subsystem. Each plan must produce working, testable software on its own.
If brainstorming already split the spec into sub-project specs, write one plan per sub-spec.
Plan Hierarchy
| Level | Granularity | When detailed | |-------|-------------|---------------| | **Phase** | Independently verifiable milestone — software works at the end of every phase | At plan time | | **Epic** | Cohesive unit of work inside a phase (one capability, one subsystem) | At plan time | | **Task** | Dispatch-ready unit: context + implementation vision + verification | Phase 1 at plan time; later phases during execution (rolling wave) |
Rules:
- Every phase ends with working, testable software. No phase ends mid-refactor.
- 2–5 epics per phase. An epic that needs more than a paragraph to describe is two epics.
- Order phases by dependency first, then by risk — front-load whatever invalidates the design if it turns out wrong.
Code Snippet Policy
Default is **prose, not code**. Describe intent, decisions, and shape; the implementer writes the code at execution time with the real codebase in front of them.
Include a snippet ONLY when prose cannot pin down the decision:
| Justified | Example | |-----------|---------| | Public contract other epics depend on | A
Read more
name: ring:writing-plans description: "Writing a rolling-wave phased implementation plan from a spec before coding: a phase-epic-task hierarchy where Phase 1 is detailed into dispatch-ready tasks and later phases stay epic-level for elaboration during execution. Use when a multi-file feature needs decomposition; runs after ring:exploring-codebases or pre-dev gates, hands off to ring:executing-plans or ring:running-dev-cycle. Skip for single-file changes or spikes."
Writing Plans
When to use
- Spec or requirements exist for a multi-step task and no implementation has started
- Feature spans multiple files/layers and needs decomposition before coding
- Handing off implementation to a separate session, agent, or human
Skip when
- Single-file change with obvious shape (just do it)
- Exploratory spike — phased plans assume known requirements
- Spec is still in brainstorming; the plan would lock premature decisions
Sequence
**Runs after:** ring:exploring-codebases, ring:planning-large-features (gates 0-6 artifacts) or ring:planning-small-features (gates 0-2 artifacts) — their outputs feed the spec **Runs before:** ring:executing-plans (rolling-wave execution) or ring:running-dev-cycle (gated subagent workflow)
Related
**Companion:** [plan-document-reviewer-prompt.md](plan-document-reviewer-prompt.md) — subagent dispatch template for thorough plan review
---
Write the plan assuming the implementer is skilled but has zero context for this codebase, toolset, or problem domain.
The plan is a **rolling-wave document**. Only the first phase is detailed to task level at plan time; later phases stay at epic level until execution reaches them. Detail decays: code written in Phase 1 invalidates assumptions baked into Phase 3 tasks, so do not write Phase 3 tasks yet. ring:executing-plans elaborates each subsequent phase against the codebase as it actually exists.
**Announce at start:** "Using ring:writing-plans to author the implementation plan."
**Default save path:** `docs/plans/YYYY-MM-DD-<feature-name>.md` (User preferences override.)
**Invoked from pre-dev:** when dispatched as the final gate of ring:planning-large-features or ring:planning-small-features, the spec inputs are the pre-dev artifacts — trd.md (plus feature-map.md, openapi.yaml, the schema file, and dependencies.md on the Large track). On Large, plan phases MUST mirror feature-map.md phases one-to-one. Output path is `docs/pre-dev/{feature}/plan.md`, overriding the default above; standalone invocations keep the default. plan.md is always a SINGLE document per feature: on multi-module topologies (monorepo fullstack / multi-repo), each epic carries one line `**Target:** backend | frontend | infra` (placed right before `**Status:**`); for multi-repo features the orchestrator copies plan.md into each repo and the local dev-cycle executes only epics whose Target matches that repo. No per-module plan splits.
Plan Language
Before authoring, ask which language the plan's **prose** should be written in — using the question/ask tool the harness provides (e.g. `AskUserQuestion` in Claude Code). Offer three options: **English** (default), **Brazilian Portuguese (pt-BR)**, **Spanish**. If the user skips or no question tool is available, default to English.
The choice covers narrative prose only — Goal, Architecture, Context, Implementation vision, and other descriptions. Everything a downstream skill or agent parses stays verbatim English regardless of choice: section headers and format keywords, `**Status:**` values (Pending/Doing/Done/Failed), Phase-Overview status cells (Detailed/Epic-level/Complete), `**Target:**` values, file paths, commands, code snippets, and identifiers. Translating those breaks ring:executing-plans and ring:running-dev-cycle status matching.
Standards
Do NOT fetch standards documents while planning — standards compliance is enforced by the implementation agents and reviewers downstream. Plans reference DRY, YAGNI, and TDD generically.
Blocker — STOP and Report
Do not write a plan on a shaky foundation. STOP and ask when:
| Situation | Action | |-----------|--------| | Vague requirements ("make it better", "add feature") | STOP. Ask: "What specific behavior should change?" | | Missing success criteria | STOP. Ask: "How do we verify this works?" | | Unknown codebase structure (can't locate files) | STOP. Run ring:exploring-codebases first, then plan | | Conflicting constraints | STOP. Ask: "Which constraint takes priority?" | | Multiple valid architectures without guidance | STOP. Ask: "Which pattern should we use?" |
Scope Check
If the spec covers multiple independent subsystems, suggest breaking it into separate plans — one per subsystem. Each plan must produce working, testable software on its own.
If brainstorming already split the spec into sub-project specs, write one plan per sub-spec.
Plan Hierarchy
| Level | Granularity | When detailed | |-------|-------------|---------------| | **Phase** | Independently verifiable milestone — software works at the end of every phase | At plan time | | **Epic** | Cohesive unit of work inside a phase (one capability, one subsystem) | At plan time | | **Task** | Dispatch-ready unit: context + implementation vision + verification | Phase 1 at plan time; later phases during execution (rolling wave) |
Rules:
- Every phase ends with working, testable software. No phase ends mid-refactor.
- 2–5 epics per phase. An epic that needs more than a paragraph to describe is two epics.
- Order phases by dependency first, then by risk — front-load whatever invalidates the design if it turns out wrong.
Code Snippet Policy
Default is **prose, not code**. Describe intent, decisions, and shape; the implementer writes the code at execution time with the real codebase in front of them.
Include a snippet ONLY when prose cannot pin down the decision:
| Justified | Example | |-----------|---------| | Public contract other epics depend on | A
Proven engineering practices, enforced through skills. Ring is a comprehensive skills library and workflow system for AI agents that transforms how AI assistants approach software development.
Repo: LerianStudio/ring
Other skills on ring.
- /analyzing-options
Analyzing different approaches for a task or problem with structured comparisons, effort estimates, and recommendations. Use when facing strategic decisions, architecture choices, or multiple viable approaches. Skip when there's an obvious single approach or the decision is
Open skill - /auditing-production-readiness
Auditing a service's production readiness against Ring engineering standards across base dimensions plus a conditional multi-tenant dimension, then emitting a scored report and an HTML dashboard. Use before production deploy, periodic review, onboarding, or a major release. Skip
Open skill - /cleaning-comments
Cleaning redundant and obvious comments following clean code principles while preserving meaningful documentation. Supports git scope filtering (staged, unstaged, branch, commit-range). Use when code has excessive comments, during code review, or post-refactor cleanup. Skip when
Open skill - /committing-changes
Commit changes with scope allowlist enforcement, atomic grouping, GPG-signed conventional commits, and trailer management. Detects the repo's PR-validation scope policy before proposing any message. Use when the user asks to commit or has changes ready to record. Skip when the
Open skill - /creating-handoffs
Creating a handoff document that captures session state (completed work, decisions, open items, next steps) and delivering it via Plan Mode so the user gets the native 'clear context and continue implementing' resume option. Use when ending a session, when context grows large,
Open skill - /creating-worktrees
Creating an isolated git worktree for parallel branch work: selects the directory by priority order, verifies/adds .gitignore safety, auto-installs the detected toolchain's dependencies, runs a baseline test, and reports readiness. Use before a feature that needs isolation from
Open skill

