implementation-plan
/implementation-plan
Breaks multi-step or cross-file work into small, independently verifiable slices with exact files, steps, commands, and risks, without editing code. Use when changes span several files or layers, migrations, or unclear scope. Execute slices with minimal-implementation.
- Author
- hugrverk ↗
- Repository
- riggverk ↗
- Licence
- MIT
- Last repository change
- 10.11.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 1
No signals detected. Repository changed on 10.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Breaks multi-step or cross-file work into small, independently verifiable slices with exact files, steps, commands, and risks, without editing code. Use when changes span several files or layers, migrations, or unclear scope. Execute slices with minimal-implementation.
Original author description
Breaks multi-step or cross-file work into small, independently verifiable slices with exact files, steps, commands, and risks, without editing code. Use when changes span several files or layers, migrations, or unclear scope. Execute slices with minimal-implementation.
How it works
- Process
- Output
- Guardrails
SKILL.md preview
---
name: implementation-plan
description: Breaks multi-step or cross-file work into small, independently verifiable slices with exact files, steps, commands, and risks, without editing code. Use when changes span several files or layers, migrations, or unclear scope. Execute slices with minimal-implementation.
license: MIT
metadata:
category: planning
risk: low
targets: codex, opencode, claude, cursor, copilot, pi, kilo, antigravity, grok
related: context-budget
source: https://github.com/obra/superpowers (writing-plans, MIT)
---
# Implementation Plan
Make the plan clear enough for a coding agent with no project memory to execute safely; optimize for small diffs, verification, and low rework.
Scale to the task: for one or two files, a short list (goal, files, verification) is enough; use the full Output sections only for multi-slice or high-risk work.
Done when: every slice lists its files and a falsifying verification command, and unknowns are listed as blockers instead of assumptions.
## Process
1. **Confirm scope.**
- Restate goal.
- Identify non-goals.
- Call out DB/migration status when relevant.
- Stop if the task is too broad and split it.
2. **Inspect repo reality.**
- Read relevant files before planning.
- Prefer existing patterns.
- List files likely to be changed.
- Do not invent APIs, routes, components, or commands.
3. **Slice the work.**
- Each slice should be independently useful and verifiable.
- Prefer small vertical slices over broad layer-by-layer work.
- Each slice should include:
- goal
- files to inspect or change
- exact implementation steps
- verification command or manual check
- commit message suggestion if useful
4. **Avoid placeholders.**
- Do not write placeholder markers or vague chores such as generic test or error-handling steps.
- If information is missing, name the missing fact and ask or mark it as a blocker.
- Do not say "similar to previous task"; repeat necessary detail.
5. **Verification plan.**
- Start with the narrowest useful command.
- Add broader checks only when risk justifies it.
- For frontend work, include route, viewport, and visual checks when possible.
- For DB or schema work, explicitly state migration and rollback considerations.
## Output
- Goal
- Non-goals
- Assumptions
- File map
- Slices
- Verification plan
- Risks and blockers
## Guardrails
- Do not plan broad rewrites unless explicitly requested.
- Do not bury risky changes inside a large slice.
- Do not treat the plan as verified implementation.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · hugrverk/riggverk | 90 | MIT |
| langri-sha/skills | 100 | MIT |
| Mozurok/fhorja.dev | 100 | MIT |
| navapbc/digital-service-orchestra | 91 | Apache-2.0 |
| Gattic/GatPi-Harness | 90 | MIT |
| itsofficialadi/boundiff | 90 | MIT |
| nasac0x/code-orchestrator | 90 | MIT |
| Neeeophytee/finding-unknowns-skills | 90 | MIT |
| EmbedBuild/specbox-engine | 86 | Apache-2.0 |
Database snapshot: 13.11.2026 · package version 779ef843004f (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100writing-plans
Use when the approach is agreed and the change takes more than a couple of steps. Breaks the work into small, independently verifiable tasks with exact files and verification commands, so execution needs no guesswork. - 98plan-to-tickets
Use when a large plan, PRD, feature, refactor, research plan, or multi-step coding task must be split into small ready-for-agent tickets with acceptance criteria, verification commands, blockers, and vertical tracer-bullet slices. Do not use for small tasks that should be… - 96principle-sequence-verifiable-units
Apply when doing multi-step work (sweeps, migrations, runs of similar edits) and when stacking commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer. - 90issue-plan-slicer
Convert a spec, roadmap item, or rough plan into independently implementable issue slices with scope, dependencies, acceptance criteria, and validation. Use when the user asks to split work into GitHub issues, local markdown tasks, or agent-ready implementation chunks. - 90roblox-to-issues
Break a Roblox game PRD, roadmap, or plan into small independently-playtestable vertical slices instead of building the whole game at once. Use when the user wants to turn a concept or PRD into buildable tickets, split work into slices, plan what to build next, or stop Claude… - 100052-design-hamburger-method
Use when a large feature, story, plan, or spec idea needs to be split into small vertical slices with the Hamburger Method. This should trigger for requests such as Split this oversized story; Find the smallest useful slice; Break this feature into vertical slices; Apply the…