fix-planner — Claude Code skill: plans and installation
fix-planner is a Claude Code skill that turns a confirmed finding into a bounded change plan. It ties proposed fixes to project evidence and approved design decisions.
MIT ★ 529 updated 2026-11-17
npx skills add ShuaiMXu/happyhands --skill fix-planner -a claude-codeWhat fix-planner does
fix-planner turns a selected problem into an intent, constraints, and acceptance criteria. Each plan keeps to one confirmed repair scope; related findings can share a plan when they have a demonstrated common cause. Changes should be small and reversible, with uncertainty recorded.
The skill uses evidence about the finding, approved tokens, components and patterns, plus working product paths. It examines reading order, information groups, primary actions, and relevant interface states. Then it compares the proposed approach with a lighter change or keeping the existing design, and records expected benefit, cost, risk, and evidence that could challenge the decision.
Repository inspection is required before naming exact files or consumers. Under policy task-design-review@1, submit the decision with experience --phase decision --input FILE before planning; the confirmed scope must match the diagnostic record. If the defect has not been demonstrated, the candidate stays unadmitted and no change is made.
What it helps with
- turn a confirmed finding into a bounded repair plan
- set acceptance criteria and record uncertainty
- compare an interface change with a lighter option
- capture the risks and evidence behind a design decision
Example prompts for the agent
- Create a repair plan from this confirmed finding and define its acceptance criteria.
- Compare the proposed interface change with a smaller change and keeping the current design.
- Identify the project evidence needed before naming files to edit.
How to install fix-planner
1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill fix-planner -a claude-code2Manually: put the files in place
~/.claude/skills/fix-planner/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/fix-planner/
1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill fix-planner -a codex2Manually: put the files in place
.agents/skills/fix-planner/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill fix-planner -a cursor2Manually: put the files in place
.cursor/skills/fix-planner/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install ShuaiMXu/happyhands skills/product-design/fix-planner2Manually: put the files in place
.github/skills/fix-planner/SKILL.md1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill fix-planner -a gemini-cli2Platform CLI
gemini skills install https://github.com/ShuaiMXu/happyhands --path skills/product-design/fix-plannerManually: put the files in place
.devin/skills/fix-planner/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.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 fix-planner
How do I install fix-planner in Claude Code?
Run npx skills add ShuaiMXu/happyhands --skill fix-planner -a claude-code. The skill file is at ~/.claude/skills/fix-planner/SKILL.md.
What does fix-planner do?
It converts a confirmed problem into a bounded change plan with intent, constraints, and acceptance criteria. The plan draws on project evidence and approved design decisions.
What information does fix-planner need to make a plan?
It needs evidence for the finding, approved tokens, components and patterns, and working product paths. The repository and its consumers must be inspected before exact files are named.
Source text
SKILL.md · MIT
--- name: fix-planner description: "Turn a confirmed finding into a scoped, reversible change plan constrained by project evidence and approved design foundations." --- # Fix Planner Translate the selected problem into intent, constraints and acceptance criteria. ## Required evidence - finding evidence - approved tokens, components and patterns - working product paths ## Decisions - Keep one confirmed repair scope per plan; related delegated findings may share a demonstrated root cause. - Prefer the smallest reversible change - State acceptance criteria and uncertainty ## Boundary Repository inspection is still required before naming exact files. Return structured evidence, findings, proposed updates and limitations. Use `needs-evidence` when required inputs or professional review are missing. Never invent an Experience Score or promote a project observation into a universal rule. ## Task-specific design decision Read the current Run's complete experience audit, actual user constraints, original screenshots and selected design sources. Separate a user's outcome from an operator's preferred solution. A missing label, table or card is not a defect merely because someone proposed it. Before implementation, record the reading order and information grouping that answer the user's immediate questions; identify the primary action and what content must be shown, combined or deferred. Explain component relationships, known consumers and actual default/open/selected/focus/error states as applicable. For layout, preserve the adopted container, alignment, columns, gutter and spacing relationships; do not substitute a reference's grid without task-specific justification. Compare the chosen approach with a lighter change or preserving the existing design. State the expected task benefit, cost, risk and what evidence could refute it. For every selected Design.md or design-system source, identify a real section, the target problem, adoption/rejection, implementation location and verification. Colors, fonts and field counts alone do not constitute adaptation. Keep incomplete discovery explicit and resolve it before editing. For policy `task-design-review@1`, deliver the decision through `experience --phase decision --input FILE` before `plan`. The confirmed scope and diagnostic record must match. A decision is an operator hypothesis subject to independent challenge, never a new user requirement or human acceptance. If the best supported decision is no change, report that outcome rather than creating work to satisfy the pipeline. ## Execution contract and admission The bounded handler supplies: A candidate plan from the selected evidence-supported finding and existing constraints. The professional method still requires: Inspect exact source consumers and record the existing experience decision before implementation. A generated plan is not a verified file patch or acceptance. Deliver into the current Run's existing experience audit or decision; do not create a competing report. Cite the frozen Skill path and exact rule, original state and source, observed failure, task consequence and the reasoning connecting them. Record preservation/counterevidence. With no demonstrated defect, keep the candidate unadmitted and make no change. `complete` describes this handler's bounded output, not professional review or human acceptance.
© ShuaiMXu · MIT · ShuaiMXu/happyhands