Workflow

Fix findings

Fixes front-end audit findings by rule id - smallest correct change first, shared components before pages, the rule's own fix and source, re-running audit --changed after each fix, and never suppressing a finding without the rule id and a reason. Use when asked to fix audit findings, a rule id such as a11y/input-label, the problems in frontend-report.md, or "make the audit pass".

fe-fixevery web project2 rules90 tokens always loaded, 670 tokens when used, 814 tokens in references on demand.

Install

init installs this skill when the project uses every web project. Pick your agent to see where its files land.

npx github:dawidolko/frontend-skills init

Not tested yet with this runner. npx and pnpm dlx are tested; if this one fails, use one of them.

Without --agents, init finds the agents from what the project already has, and asks when it finds none:

How init finds each of the 17 agents

Agent	Found by
Claude Code	`CLAUDE.md` `.claude` `CLAUDE.local.md`
OpenAI Codex	`.codex` `AGENTS.override.md`
Cursor	`.cursor` `.cursorrules`
GitHub Copilot	`.github/copilot-instructions.md` `.github/instructions` `.github/skills` `.github/prompts`
Gemini CLI	`GEMINI.md` `.gemini`
Antigravity CLI	`.agents/rules` `.agent/rules`
Devin / Windsurf	`.devin` `.windsurf` `.windsurfrules`
OpenCode	`opencode.json` `opencode.jsonc` `.opencode`
Cline	`.clinerules` `.cline`
Zed	`.rules` `.zed`
JetBrains Junie	`.junie`
Kiro	`.kiro`
Augment	`.augment` `.augment-guidelines`
Trae	`.trae`
Continue	`.continue`
Amazon Q Developer	`.amazonq`
Aider	`.aider.conf.yml` `CONVENTIONS.md`

Where fe-fix lands for Claude Code

.claude/skills/fe-fix/SKILL.mdskill
.claude/skills/fe-fix/references/fixing.mdskill
.claude/rules/fe-fix.mdrule file
CLAUDE.mdinstruction block

For every agent also: .frontend-skills/profile.json, .frontend-skills/lessons.md and .frontend-skills/install.json.

Planned by the installer itself for the example React project in the repository.

.claude/rules/fe-fix.md

---
paths:
  - "**/frontend-report.md"
  - "**/.frontend-skills/**"
---

# Fix findings (frontend-skills)

Fixes front-end audit findings by rule id - smallest correct change first, shared components before pages, the rule's own fix and source, re-running audit --changed after each fix, and never suppressing a finding without the rule id and a reason. Use when asked to fix audit findings, a rule id such as a11y/input-label, the problems in frontend-report.md, or "make the audit pass".

- Work from the audit, by rule id: `npx github:dawidolko/frontend-skills audit --json`, then `explain <id>` for the fix and source.
- Fix the cause in the shared component, layout or token, not each page that uses it.
- Make the smallest change that fixes the rule; do not refactor or restyle around it.
- Use the project's helpers and components (`profile.helpers`, lessons) in the fix.
- After each fix, run `audit --changed` and the project's lint and tests (tooling/use-project-scripts).
- Never suppress to pass: an `fs-ignore` names the rule id and a reason, or the finding stays (tooling/ignore-with-reason).
- Never weaken `audit.failOn`, budgets or a rule to make the audit pass.
- A static fix that needs judgement (alt text wording, error message text, labels) gets a short note for the person to confirm.
- Fixing one finding must not create another: check the rule ids of the skill for that area.

Before larger changes, read the full skill: `.claude/skills/fe-fix/SKILL.md`. Explain any rule id with `npx github:dawidolko/frontend-skills explain <id>`.

The real file

Where fe-fix lands for OpenAI Codex

.agents/skills/fe-fix/SKILL.mdskill
.agents/skills/fe-fix/references/fixing.mdskill
AGENTS.mdinstruction block

For every agent also: .frontend-skills/profile.json, .frontend-skills/lessons.md and .frontend-skills/install.json.

OpenAI Codex has no rule files scoped to file types; it reads the skills and the instruction block.

Planned by the installer itself for the example React project in the repository.

AGENTS.md

## Front-end work (frontend-skills)

- Before front-end work, read `.frontend-skills/profile.json` (the stack) and `.frontend-skills/lessons.md` (confirmed conventions of this project; they win over any skill).
- Use the installed `fe-*` skill that matches the files you edit.
- After changing UI code, run `npx github:dawidolko/frontend-skills audit --changed --json` and fix findings at `serious` and above; `explain <rule id>` gives the reason, the source and the fix.
- Name rule ids (such as `a11y/img-alt`) in reviews and commit messages.

The real file

Where fe-fix lands for Cursor

.agents/skills/fe-fix/SKILL.mdskill
.agents/skills/fe-fix/references/fixing.mdskill
.cursor/rules/fe-fix.mdcrule file
AGENTS.mdinstruction block

For every agent also: .frontend-skills/profile.json, .frontend-skills/lessons.md and .frontend-skills/install.json.

Planned by the installer itself for the example React project in the repository.

.cursor/rules/fe-fix.mdc

---
description: Fixes front-end audit findings by rule id - smallest correct change first, shared components before pages, the rule's own fix and source, re-running audit --changed after each fix, and never suppressing a finding without the rule id and a reason. Use when asked to fix audit findings, a rule id such as a11y/input-label, the problems in frontend-report.md, or "make the audit pass".
globs: **/frontend-report.md, **/.frontend-skills/**
alwaysApply: false
---

# Fix findings (frontend-skills)

- Work from the audit, by rule id: `npx github:dawidolko/frontend-skills audit --json`, then `explain <id>` for the fix and source.
- Fix the cause in the shared component, layout or token, not each page that uses it.
- Make the smallest change that fixes the rule; do not refactor or restyle around it.
- Use the project's helpers and components (`profile.helpers`, lessons) in the fix.
- After each fix, run `audit --changed` and the project's lint and tests (tooling/use-project-scripts).
- Never suppress to pass: an `fs-ignore` names the rule id and a reason, or the finding stays (tooling/ignore-with-reason).
- Never weaken `audit.failOn`, budgets or a rule to make the audit pass.
- A static fix that needs judgement (alt text wording, error message text, labels) gets a short note for the person to confirm.
- Fixing one finding must not create another: check the rule ids of the skill for that area.

Before larger changes, read the full skill: `.agents/skills/fe-fix/SKILL.md`. Explain any rule id with `npx github:dawidolko/frontend-skills explain <id>`.

The real file

Where fe-fix lands for GitHub Copilot

.agents/skills/fe-fix/SKILL.mdskill
.agents/skills/fe-fix/references/fixing.mdskill
.github/instructions/fe-fix.instructions.mdrule file
AGENTS.mdinstruction block

For every agent also: .frontend-skills/profile.json, .frontend-skills/lessons.md and .frontend-skills/install.json.

Planned by the installer itself for the example React project in the repository.

.github/instructions/fe-fix.instructions.md

---
applyTo: "**/frontend-report.md,**/.frontend-skills/**"
description: "Fixes front-end audit findings by rule id - smallest correct change first, shared components before pages, the rule's own fix and source, re-running audit --changed after each fix, and never suppressing a finding without the rule id and a reason. Use when asked to fix audit findings, a rule id such as a11y/input-label, the problems in frontend-report.md, or \"make the audit pass\"."
---

# Fix findings (frontend-skills)

- Work from the audit, by rule id: `npx github:dawidolko/frontend-skills audit --json`, then `explain <id>` for the fix and source.
- Fix the cause in the shared component, layout or token, not each page that uses it.
- Make the smallest change that fixes the rule; do not refactor or restyle around it.
- Use the project's helpers and components (`profile.helpers`, lessons) in the fix.
- After each fix, run `audit --changed` and the project's lint and tests (tooling/use-project-scripts).
- Never suppress to pass: an `fs-ignore` names the rule id and a reason, or the finding stays (tooling/ignore-with-reason).
- Never weaken `audit.failOn`, budgets or a rule to make the audit pass.
- A static fix that needs judgement (alt text wording, error message text, labels) gets a short note for the person to confirm.
- Fixing one finding must not create another: check the rule ids of the skill for that area.

Before larger changes, read the full skill: `.agents/skills/fe-fix/SKILL.md`. Explain any rule id with `npx github:dawidolko/frontend-skills explain <id>`.

The real file

Where fe-fix lands for Gemini CLI

.agents/skills/fe-fix/SKILL.mdskill
.agents/skills/fe-fix/references/fixing.mdskill
GEMINI.mdinstruction block

For every agent also: .frontend-skills/profile.json, .frontend-skills/lessons.md and .frontend-skills/install.json.

Gemini CLI: Gemini CLI was replaced by Antigravity CLI for unpaid tiers on 2026-06-18; choose "antigravity" too if you use it.

Gemini CLI has no rule files scoped to file types; it reads the skills and the instruction block.

Planned by the installer itself for the example React project in the repository.

GEMINI.md

## Front-end work (frontend-skills)

- Before front-end work, read `.frontend-skills/profile.json` (the stack) and `.frontend-skills/lessons.md` (confirmed conventions of this project; they win over any skill).
- Use the installed `fe-*` skill that matches the files you edit.
- After changing UI code, run `npx github:dawidolko/frontend-skills audit --changed --json` and fix findings at `serious` and above; `explain <rule id>` gives the reason, the source and the fix.
- Name rule ids (such as `a11y/img-alt`) in reviews and commit messages.

The real file

Where fe-fix lands for Antigravity CLI

.agents/skills/fe-fix/SKILL.mdskill
.agents/skills/fe-fix/references/fixing.mdskill
.agents/rules/fe-fix.mdrule file
AGENTS.mdinstruction block

For every agent also: .frontend-skills/profile.json, .frontend-skills/lessons.md and .frontend-skills/install.json.

Planned by the installer itself for the example React project in the repository.

.agents/rules/fe-fix.md

---
trigger: glob
globs: "**/frontend-report.md, **/.frontend-skills/**"
description: "Fixes front-end audit findings by rule id - smallest correct change first, shared components before pages, the rule's own fix and source, re-running audit --changed after each fix, and never suppressing a finding without the rule id and a reason. Use when asked to fix audit findings, a rule id such as a11y/input-label, the problems in frontend-report.md, or \"make the audit pass\"."
---

# Fix findings (frontend-skills)

- Work from the audit, by rule id: `npx github:dawidolko/frontend-skills audit --json`, then `explain <id>` for the fix and source.
- Fix the cause in the shared component, layout or token, not each page that uses it.
- Make the smallest change that fixes the rule; do not refactor or restyle around it.
- Use the project's helpers and components (`profile.helpers`, lessons) in the fix.
- After each fix, run `audit --changed` and the project's lint and tests (tooling/use-project-scripts).
- Never suppress to pass: an `fs-ignore` names the rule id and a reason, or the finding stays (tooling/ignore-with-reason).
- Never weaken `audit.failOn`, budgets or a rule to make the audit pass.
- A static fix that needs judgement (alt text wording, error message text, labels) gets a short note for the person to confirm.
- Fixing one finding must not create another: check the rule ids of the skill for that area.

Before larger changes, read the full skill: `.agents/skills/fe-fix/SKILL.md`. Explain any rule id with `npx github:dawidolko/frontend-skills explain <id>`.

The real file

Where fe-fix lands for Devin / Windsurf

.agents/skills/fe-fix/SKILL.mdskill
.agents/skills/fe-fix/references/fixing.mdskill
.devin/rules/fe-fix.mdrule file
AGENTS.mdinstruction block

For every agent also: .frontend-skills/profile.json, .frontend-skills/lessons.md and .frontend-skills/install.json.

Devin / Windsurf: Devin CLI also reads .cursor/rules; with Cursor chosen too, the CLI sees both rule files of a skill.

Planned by the installer itself for the example React project in the repository.

.devin/rules/fe-fix.md

---
trigger: glob
globs: "**/frontend-report.md,**/.frontend-skills/**"
---

# Fix findings (frontend-skills)

Fixes front-end audit findings by rule id - smallest correct change first, shared components before pages, the rule's own fix and source, re-running audit --changed after each fix, and never suppressing a finding without the rule id and a reason. Use when asked to fix audit findings, a rule id such as a11y/input-label, the problems in frontend-report.md, or "make the audit pass".

- Work from the audit, by rule id: `npx github:dawidolko/frontend-skills audit --json`, then `explain <id>` for the fix and source.
- Fix the cause in the shared component, layout or token, not each page that uses it.
- Make the smallest change that fixes the rule; do not refactor or restyle around it.
- Use the project's helpers and components (`profile.helpers`, lessons) in the fix.
- After each fix, run `audit --changed` and the project's lint and tests (tooling/use-project-scripts).
- Never suppress to pass: an `fs-ignore` names the rule id and a reason, or the finding stays (tooling/ignore-with-reason).
- Never weaken `audit.failOn`, budgets or a rule to make the audit pass.
- A static fix that needs judgement (alt text wording, error message text, labels) gets a short note for the person to confirm.
- Fixing one finding must not create another: check the rule ids of the skill for that area.

Before larger changes, read the full skill: `.agents/skills/fe-fix/SKILL.md`. Explain any rule id with `npx github:dawidolko/frontend-skills explain <id>`.

The real file

Where fe-fix lands for OpenCode

.agents/skills/fe-fix/SKILL.mdskill
.agents/skills/fe-fix/references/fixing.mdskill
AGENTS.mdinstruction block

For every agent also: .frontend-skills/profile.json, .frontend-skills/lessons.md and .frontend-skills/install.json.

OpenCode has no rule files scoped to file types; it reads the skills and the instruction block.

Planned by the installer itself for the example React project in the repository.

AGENTS.md

## Front-end work (frontend-skills)

- Before front-end work, read `.frontend-skills/profile.json` (the stack) and `.frontend-skills/lessons.md` (confirmed conventions of this project; they win over any skill).
- Use the installed `fe-*` skill that matches the files you edit.
- After changing UI code, run `npx github:dawidolko/frontend-skills audit --changed --json` and fix findings at `serious` and above; `explain <rule id>` gives the reason, the source and the fix.
- Name rule ids (such as `a11y/img-alt`) in reviews and commit messages.

The real file

Where fe-fix lands for Cline

.claude/skills/fe-fix/SKILL.mdskill
.claude/skills/fe-fix/references/fixing.mdskill
.clinerules/fe-fix.mdrule file
AGENTS.mdinstruction block

For every agent also: .frontend-skills/profile.json, .frontend-skills/lessons.md and .frontend-skills/install.json.

Cline: If .clinerules is a single file rather than a folder, Cline rule files are not written; skills still are.

Planned by the installer itself for the example React project in the repository.

.clinerules/fe-fix.md

---
paths:
  - "**/frontend-report.md"
  - "**/.frontend-skills/**"
---

# Fix findings (frontend-skills)

Fixes front-end audit findings by rule id - smallest correct change first, shared components before pages, the rule's own fix and source, re-running audit --changed after each fix, and never suppressing a finding without the rule id and a reason. Use when asked to fix audit findings, a rule id such as a11y/input-label, the problems in frontend-report.md, or "make the audit pass".

- Work from the audit, by rule id: `npx github:dawidolko/frontend-skills audit --json`, then `explain <id>` for the fix and source.
- Fix the cause in the shared component, layout or token, not each page that uses it.
- Make the smallest change that fixes the rule; do not refactor or restyle around it.
- Use the project's helpers and components (`profile.helpers`, lessons) in the fix.
- After each fix, run `audit --changed` and the project's lint and tests (tooling/use-project-scripts).
- Never suppress to pass: an `fs-ignore` names the rule id and a reason, or the finding stays (tooling/ignore-with-reason).
- Never weaken `audit.failOn`, budgets or a rule to make the audit pass.
- A static fix that needs judgement (alt text wording, error message text, labels) gets a short note for the person to confirm.
- Fixing one finding must not create another: check the rule ids of the skill for that area.

Before larger changes, read the full skill: `.claude/skills/fe-fix/SKILL.md`. Explain any rule id with `npx github:dawidolko/frontend-skills explain <id>`.

The real file

Where fe-fix lands for Zed

.agents/skills/fe-fix/SKILL.mdskill
.agents/skills/fe-fix/references/fixing.mdskill
CLAUDE.mdinstruction block

For every agent also: .frontend-skills/profile.json, .frontend-skills/lessons.md and .frontend-skills/install.json.

Zed: Zed reads only the first instruction file of its list; the block is placed in that file.

Zed has no rule files scoped to file types; it reads the skills and the instruction block.

Planned by the installer itself for the example React project in the repository.

CLAUDE.md

## Front-end work (frontend-skills)

- Before front-end work, read `.frontend-skills/profile.json` (the stack) and `.frontend-skills/lessons.md` (confirmed conventions of this project; they win over any skill).
- Use the installed `fe-*` skill that matches the files you edit.
- After changing UI code, run `npx github:dawidolko/frontend-skills audit --changed --json` and fix findings at `serious` and above; `explain <rule id>` gives the reason, the source and the fix.
- Name rule ids (such as `a11y/img-alt`) in reviews and commit messages.

The real file

Where fe-fix lands for JetBrains Junie

.agents/skills/fe-fix/SKILL.mdskill
.agents/skills/fe-fix/references/fixing.mdskill
AGENTS.mdinstruction block

For every agent also: .frontend-skills/profile.json, .frontend-skills/lessons.md and .frontend-skills/install.json.

JetBrains Junie: Junie reads .agents/skills only in a trusted project.

JetBrains Junie has no rule files scoped to file types; it reads the skills and the instruction block.

Planned by the installer itself for the example React project in the repository.

AGENTS.md

## Front-end work (frontend-skills)

- Before front-end work, read `.frontend-skills/profile.json` (the stack) and `.frontend-skills/lessons.md` (confirmed conventions of this project; they win over any skill).
- Use the installed `fe-*` skill that matches the files you edit.
- After changing UI code, run `npx github:dawidolko/frontend-skills audit --changed --json` and fix findings at `serious` and above; `explain <rule id>` gives the reason, the source and the fix.
- Name rule ids (such as `a11y/img-alt`) in reviews and commit messages.

The real file

Where fe-fix lands for Kiro

.kiro/skills/fe-fix/SKILL.mdskill
.kiro/skills/fe-fix/references/fixing.mdskill
.kiro/steering/fe-fix.mdrule file
AGENTS.mdinstruction block

For every agent also: .frontend-skills/profile.json, .frontend-skills/lessons.md and .frontend-skills/install.json.

Planned by the installer itself for the example React project in the repository.

.kiro/steering/fe-fix.md

---
inclusion: fileMatch
fileMatchPattern: ["**/frontend-report.md", "**/.frontend-skills/**"]
---

# Fix findings (frontend-skills)

Fixes front-end audit findings by rule id - smallest correct change first, shared components before pages, the rule's own fix and source, re-running audit --changed after each fix, and never suppressing a finding without the rule id and a reason. Use when asked to fix audit findings, a rule id such as a11y/input-label, the problems in frontend-report.md, or "make the audit pass".

- Work from the audit, by rule id: `npx github:dawidolko/frontend-skills audit --json`, then `explain <id>` for the fix and source.
- Fix the cause in the shared component, layout or token, not each page that uses it.
- Make the smallest change that fixes the rule; do not refactor or restyle around it.
- Use the project's helpers and components (`profile.helpers`, lessons) in the fix.
- After each fix, run `audit --changed` and the project's lint and tests (tooling/use-project-scripts).
- Never suppress to pass: an `fs-ignore` names the rule id and a reason, or the finding stays (tooling/ignore-with-reason).
- Never weaken `audit.failOn`, budgets or a rule to make the audit pass.
- A static fix that needs judgement (alt text wording, error message text, labels) gets a short note for the person to confirm.
- Fixing one finding must not create another: check the rule ids of the skill for that area.

Before larger changes, read the full skill: `.kiro/skills/fe-fix/SKILL.md`. Explain any rule id with `npx github:dawidolko/frontend-skills explain <id>`.

The real file

Where fe-fix lands for Augment

.agents/skills/fe-fix/SKILL.mdskill
.agents/skills/fe-fix/references/fixing.mdskill
AGENTS.mdinstruction block

For every agent also: .frontend-skills/profile.json, .frontend-skills/lessons.md and .frontend-skills/install.json.

Augment has no rule files scoped to file types; it reads the skills and the instruction block.

Planned by the installer itself for the example React project in the repository.

AGENTS.md

## Front-end work (frontend-skills)

- Before front-end work, read `.frontend-skills/profile.json` (the stack) and `.frontend-skills/lessons.md` (confirmed conventions of this project; they win over any skill).
- Use the installed `fe-*` skill that matches the files you edit.
- After changing UI code, run `npx github:dawidolko/frontend-skills audit --changed --json` and fix findings at `serious` and above; `explain <rule id>` gives the reason, the source and the fix.
- Name rule ids (such as `a11y/img-alt`) in reviews and commit messages.

The real file

Where fe-fix lands for Trae

.trae/skills/fe-fix/SKILL.mdskill
.trae/skills/fe-fix/references/fixing.mdskill
.trae/rules/fe-fix.mdrule file
AGENTS.mdinstruction block

For every agent also: .frontend-skills/profile.json, .frontend-skills/lessons.md and .frontend-skills/install.json.

Trae: Trae reads AGENTS.md only after it is enabled in its settings.

Planned by the installer itself for the example React project in the repository.

.trae/rules/fe-fix.md

---
description: "Fixes front-end audit findings by rule id - smallest correct change first, shared components before pages, the rule's own fix and source, re-running audit --changed after each fix, and never suppressing a finding without the rule id and a reason. Use when asked to fix audit findings, a rule id such as a11y/input-label, the problems in frontend-report.md, or \"make the audit pass\"."
globs: **/frontend-report.md,**/.frontend-skills/**
alwaysApply: false
---

# Fix findings (frontend-skills)

- Work from the audit, by rule id: `npx github:dawidolko/frontend-skills audit --json`, then `explain <id>` for the fix and source.
- Fix the cause in the shared component, layout or token, not each page that uses it.
- Make the smallest change that fixes the rule; do not refactor or restyle around it.
- Use the project's helpers and components (`profile.helpers`, lessons) in the fix.
- After each fix, run `audit --changed` and the project's lint and tests (tooling/use-project-scripts).
- Never suppress to pass: an `fs-ignore` names the rule id and a reason, or the finding stays (tooling/ignore-with-reason).
- Never weaken `audit.failOn`, budgets or a rule to make the audit pass.
- A static fix that needs judgement (alt text wording, error message text, labels) gets a short note for the person to confirm.
- Fixing one finding must not create another: check the rule ids of the skill for that area.

Before larger changes, read the full skill: `.trae/skills/fe-fix/SKILL.md`. Explain any rule id with `npx github:dawidolko/frontend-skills explain <id>`.

The real file

Where fe-fix lands for Continue

.frontend-skills/skills/fe-fix/SKILL.mdskill
.frontend-skills/skills/fe-fix/references/fixing.mdskill
.continue/rules/fe-fix.mdrule file

For every agent also: .frontend-skills/profile.json, .frontend-skills/lessons.md and .frontend-skills/install.json.

Planned by the installer itself for the example React project in the repository.

.continue/rules/fe-fix.md

---
name: "Fix findings"
description: "Fixes front-end audit findings by rule id - smallest correct change first, shared components before pages, the rule's own fix and source, re-running audit --changed after each fix, and never suppressing a finding without the rule id and a reason. Use when asked to fix audit findings, a rule id such as a11y/input-label, the problems in frontend-report.md, or \"make the audit pass\"."
globs: ["**/frontend-report.md", "**/.frontend-skills/**"]
alwaysApply: false
---

# Fix findings (frontend-skills)

- Work from the audit, by rule id: `npx github:dawidolko/frontend-skills audit --json`, then `explain <id>` for the fix and source.
- Fix the cause in the shared component, layout or token, not each page that uses it.
- Make the smallest change that fixes the rule; do not refactor or restyle around it.
- Use the project's helpers and components (`profile.helpers`, lessons) in the fix.
- After each fix, run `audit --changed` and the project's lint and tests (tooling/use-project-scripts).
- Never suppress to pass: an `fs-ignore` names the rule id and a reason, or the finding stays (tooling/ignore-with-reason).
- Never weaken `audit.failOn`, budgets or a rule to make the audit pass.
- A static fix that needs judgement (alt text wording, error message text, labels) gets a short note for the person to confirm.
- Fixing one finding must not create another: check the rule ids of the skill for that area.

Before larger changes, read the full skill: `.frontend-skills/skills/fe-fix/SKILL.md`. Explain any rule id with `npx github:dawidolko/frontend-skills explain <id>`.

The real file

Where fe-fix lands for Amazon Q Developer

.frontend-skills/skills/fe-fix/SKILL.mdskill
.frontend-skills/skills/fe-fix/references/fixing.mdskill
.amazonq/rules/frontend-skills.mdinstruction block

For every agent also: .frontend-skills/profile.json, .frontend-skills/lessons.md and .frontend-skills/install.json.

Amazon Q Developer: Amazon Q Developer IDE plugins reach end of support on 2027-04-30; AWS points to Kiro.

Amazon Q Developer has no rule files scoped to file types; it reads the skills and the instruction block.

Planned by the installer itself for the example React project in the repository.

.amazonq/rules/frontend-skills.md

## Front-end work (frontend-skills)

- Before front-end work, read `.frontend-skills/profile.json` (the stack) and `.frontend-skills/lessons.md` (confirmed conventions of this project; they win over any skill).
- Use the installed `fe-*` skill that matches the files you edit.
- After changing UI code, run `npx github:dawidolko/frontend-skills audit --changed --json` and fix findings at `serious` and above; `explain <rule id>` gives the reason, the source and the fix.
- Name rule ids (such as `a11y/img-alt`) in reviews and commit messages.

### Skills

- `fe-fix` (Fix findings): when editing `**/frontend-report.md`, `**/.frontend-skills/**`, first read `.frontend-skills/skills/fe-fix/SKILL.md`.

The real file

Where fe-fix lands for Aider

.frontend-skills/skills/fe-fix/SKILL.mdskill
.frontend-skills/skills/fe-fix/references/fixing.mdskill
CONVENTIONS.mdinstruction block
.aider.conf.ymlconfig

For every agent also: .frontend-skills/profile.json, .frontend-skills/lessons.md and .frontend-skills/install.json.

Aider has no rule files scoped to file types; it reads the skills and the instruction block.

Planned by the installer itself for the example React project in the repository.

CONVENTIONS.md

## Front-end work (frontend-skills)

- Before front-end work, read `.frontend-skills/profile.json` (the stack) and `.frontend-skills/lessons.md` (confirmed conventions of this project; they win over any skill).
- Use the installed `fe-*` skill that matches the files you edit.
- After changing UI code, run `npx github:dawidolko/frontend-skills audit --changed --json` and fix findings at `serious` and above; `explain <rule id>` gives the reason, the source and the fix.
- Name rule ids (such as `a11y/img-alt`) in reviews and commit messages.

### Skills

- `fe-fix` (Fix findings): when editing `**/frontend-report.md`, `**/.frontend-skills/**`, first read `.frontend-skills/skills/fe-fix/SKILL.md`.

The real file

How to use it

Once installed, the agent loads the skill by itself when a task matches its description. You can also ask for it in your own words, for example:

Phrases from the skill description that make the agent pick it:

make the audit pass

And to check and fix the work:

Use the fe-fix skill on this file.
Run the front-end audit on what I changed and fix everything serious.
Explain tooling/ignore-with-reason and fix it here.

Rules it teaches

tooling/ignore-with-reason
Every fs-ignore comment names the rule id it silences and says why; a bare fs-ignore silences every rule on the line.
moderatemanual
tooling/use-project-scripts
Run checks through the project's own scripts and package manager; never install tools globally or switch package managers.
minormanual

The rule digest

This part is copied into each agent's scoped rule file, so it stands on its own:

Work from the audit, by rule id: npx github:dawidolko/frontend-skills audit --json, then explain <id> for the fix and source.
Fix the cause in the shared component, layout or token, not each page that uses it.
Make the smallest change that fixes the rule; do not refactor or restyle around it.
Use the project's helpers and components (profile.helpers, lessons) in the fix.
After each fix, run audit --changed and the project's lint and tests (tooling/use-project-scripts).
Never suppress to pass: an fs-ignore names the rule id and a reason, or the finding stays (tooling/ignore-with-reason).
Never weaken audit.failOn, budgets or a rule to make the audit pass.
A static fix that needs judgement (alt text wording, error message text, labels) gets a short note for the person to confirm.
Fixing one finding must not create another: check the rule ids of the skill for that area.

Steps the agent follows

Run the audit and take findings in the order critical, serious, moderate, minor; within a level, the rule with the most locations first.
For each rule: explain <id>, open the first location, find whether it comes from a shared component, and fix it there.
Load the skill that owns the rule (its skill: in explain) for the patterns of this stack.
Run npx github:dawidolko/frontend-skills audit --changed --json and the project's lint and tests; repeat until the rule is gone.
Report: rule ids fixed, files changed, findings left with the reason, and anything a person must check (browser and manual rules).

How the agent checks the work

audit --changed shows no finding of the fixed rule ids in the changed files.
git diff shows only changes that serve the fixed rules.
Every new fs-ignore has a rule id and a reason.

Checked by the audit

The static checks of these rules run in audit; this is a real session on the example project:

Terminal recording: audit lists findings by severity with rule ids and file:line, and fails at serious. — `audit`: counts by severity, each rule with its first location, the exit code.

Reference files

references/fixing.md814 tokens

SKILL.md on GitHub