implementation-plan — Claude Code skill: planning and setup
This skill puts changeable decisions ahead of implementation chores in a build plan. Use it before development, especially after a brainstorm or requirements interview.
npx skills add Neeeophytee/finding-unknowns-skills --skill implementation-plan -a claude-codeWhat implementation-plan does
The plan opens with what is being built, the chosen approach, and its riskiest assumption. It then brings data models, type interfaces, and API shapes to the front. For each decision, the plan records an alternative and the cost of changing course later. Remaining ambiguities get a working default and a signal that would trigger a pivot.
Refactors, wiring, migrations, and tests go in a compressed section near the bottom. The plan ends by asking for approval or a choice on specific items before work starts. For a long plan, or when visual output is preferred, the skill offers one self-contained HTML page with collapsible sections and decisions pinned at the top. A change of approach during planning must appear as a separate decision; the plan shouldn’t shift silently.
What it helps with
- Order plan decisions by likelihood of revision
- Compare a chosen option with an alternative and its later cost
- Record open questions and signals for changing direction
- Condense routine refactors, wiring, migrations, and tests
- Get specific approvals before implementation begins
Example prompts for the agent
- Draft an implementation plan for this feature, putting decisions I may change first.
- Turn our requirements discussion into a plan with open questions and pivot signals.
- Make the long plan a single HTML page with collapsible sections.
How to install implementation-plan
1Skills CLI (Vercel)
npx skills add Neeeophytee/finding-unknowns-skills --skill implementation-plan -a claude-code2Manually: put the files in place
~/.claude/skills/implementation-plan/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/implementation-plan/
1Skills CLI (Vercel)
npx skills add Neeeophytee/finding-unknowns-skills --skill implementation-plan -a codex2Manually: put the files in place
.agents/skills/implementation-plan/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Neeeophytee/finding-unknowns-skills --skill implementation-plan -a cursor2Manually: put the files in place
.cursor/skills/implementation-plan/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Neeeophytee/finding-unknowns-skills implementation-plan2Manually: put the files in place
.github/skills/implementation-plan/SKILL.md1Skills CLI (Vercel)
npx skills add Neeeophytee/finding-unknowns-skills --skill implementation-plan -a gemini-cli2Platform CLI
gemini skills install https://github.com/Neeeophytee/finding-unknowns-skills --path skills/implementation-planManually: put the files in place
.devin/skills/implementation-plan/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add Neeeophytee/finding-unknowns-skills --skill implementation-plan -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about implementation-plan
How do I install implementation-plan in Claude Code?
Run npx skills add Neeeophytee/finding-unknowns-skills --skill implementation-plan -a claude-code. The skill file is at ~/.claude/skills/implementation-plan/SKILL.md.
What does implementation-plan do?
It structures a build plan around decisions that are likely to change, then places routine implementation tasks later. It also asks for specific approvals before work begins.
Can it produce an HTML plan?
Yes. For a long plan or a request for visual output, it offers a standalone HTML page with collapsible sections and key decisions pinned at the top.
Source text
SKILL.md · MIT
--- name: implementation-plan description: Write an implementation plan that leads with the decisions the user is most likely to change, and buries the mechanical work at the bottom. Use when planning is requested before a build, especially after brainstorming or an interview. --- # Implementation plan A plan's job is not to prove you thought of everything. It's to put the reversible-but-expensive decisions in front of the user while changing them is still free. Order the plan by likelihood-of-tweaking, not by build order. ## Steps 1. Open with a three-line summary: what is being built, the approach chosen, and the single riskiest assumption. 2. **Section 1 — Decisions you'll probably want to tweak.** Data model changes, new type interfaces, API shapes, anything user-facing. For each: the choice made, one alternative considered, and what changing it later would cost. 3. **Section 2 — Known unknowns and how the plan absorbs them.** Where ambiguity remains, state the default that will be taken and the signal that would trigger a pivot. A plan that admits its unknowns survives contact with the territory; one that doesn't just breaks quietly. 4. **Section 3 — The mechanical work.** Refactors, wiring, migrations, tests. Compress this; the user trusts you here and reviewing it is a waste of their attention. 5. End with the review request: the 2-4 specific items you want a yes/no or a pick on before starting. 6. If the plan is more than a screenful or the user prefers visual artifacts, offer it as a single self-contained HTML page — sections collapsible, tweakable decisions pinned to the top. ## Guardrails - If a genuinely better approach appears mid-planning, present the pivot as its own decision — don't silently re-plan. - Keep it reviewable in minutes. A plan too long to read gets skimmed, and skimmed plans hide bad decisions. - The plan should leave room for improvisation during implementation; over-specified plans fail exactly where the territory disagrees with the map.
© Neeeophytee · MIT · Neeeophytee/finding-unknowns-skills
