Agent skill

Aidd Fix

by paralleldrive in paralleldrive/aidd

Fix a bug or implement review feedback following the AIDD fix process.

MITAuto-check passedTesting & QA

Install Aidd Fix

skills CLI
$ npx skills add paralleldrive/aidd --skill aidd-fix -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install paralleldrive/aidd aidd-fix --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/paralleldrive/aidd.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ai/skills/aidd-fix .claude/skills/aidd-fix && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
aidd-fix
GitHub stars
384
Token cost
~886 tokens
SKILL.md length
432 words
Files
2
Skills in repo
35
Repo updated
First seen
Licence
MIT

At a glance

Fix a bug or implement review feedback following the AIDD fix process.

  • Works in 6 steps: Gain Context and Validate → Document the Requirement in the Epic → TDD: Write a Failing Test First → …
  • A bug has been reported
  • SKILL.md covers Step 1 — Gain Context and…, Step 2 — Document the…, Step 3 — TDD: Write a Failing… and Step 4 — Implement the Fix, plus 2 more sections
  • Calls npm and git

What it does

Aidd Fix is an agent skill from paralleldrive/aidd. Fix a bug or implement review feedback following the AIDD fix process. Use when a bug has been reported, a failing test needs investigation, or a code review has returned feedback that requires a code change.

Its SKILL.md is about 890 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `README.md`). Compatibility notes: Requires git, npm, and a test runner (vitest) available in the project.

It sits in Testing & QA, covering Failing and flaky tests and Test-driven development. The repository describes itself as: The standard framework for AI Driven Development. The licence is MIT.

When your agent uses it

  • A bug has been reported
  • A failing test needs investigation
  • A code review has returned feedback that requires a code change

Example prompts

  • “/aidd-fix”

Requirements

  • Compatibility (from SKILL.md): Requires git, npm, and a test runner (vitest) available in the project.

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Gain Context and Validate
  2. Document the Requirement in the Epic
  3. TDD: Write a Failing Test First
  4. Implement the Fix
  5. Self-Review and Run All Tests
  6. Commit and Push

What it can do on your machine

Read from SKILL.md and the folder at commit 9a7c8e3. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires git, npm, and a test runner (vitest) available in the project.

    From compatibility in the SKILL.md frontmatter.

Context cost

Aidd Fix loads about 886 tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 432 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~886

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from paralleldrive/aidd at commit 9a7c8e3, republished under its MIT licence (© paralleldrive). 432 words, ~886 tokens.

Download SKILL.mdSave it as .claude/skills/aidd-fix/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
aidd-fix
description
Fix a bug or implement review feedback following the AIDD fix process. Use when a bug has been reported, a failing test needs investigation, or a code review has returned feedback that requires a code change.
compatibility
Requires git, npm, and a test runner (vitest) available in the project.

🐛 aidd-fix

Act as a top-tier software quality engineer to diagnose and fix bugs following a disciplined TDD process.

Competencies { root cause analysis test-driven development (failing test before implementation) minimal targeted fixes (no scope creep) regression prevention conventional commit discipline }

Constraints { Do ONE step at a time. Do not skip steps or reorder them. Run lint and unit tests prior to committing code. Planning and documentation (epics, /plan files, /docs, etc) are exempt. Run e2e tests prior to committing only if aidd-custom/config.yml sets e2eBeforeCommit: true. Never implement before writing a failing test. Never write a test after implementing — that is not TDD. Communicate each step to the user as friendly markdown prose with numbered lists — not raw SudoLang syntax. }

Step 1 — Gain Context and Validate

gainContext(bugReport | reviewFeedback) => confirmedIssue | stop {

  1. Read the relevant source file(s) and colocated test file(s)
  2. Read the task epic in $projectRoot/tasks/ that covers this area
  3. Reproduce or reason through the issue to confirm it exists
  4. no change needed => summarize findings; stop — do not modify any files }

Step 2 — Document the Requirement in the Epic

documentRequirement(confirmedIssue) => requirement {

  1. Locate the existing epic; no matching epic => create one at $projectRoot/tasks/<name>-epic.md using /task
  2. Add a requirement in "Given X, should Y" format describing the correct observable behavior
  3. Epic update is a discrete step — commit it separately or include it in the fix commit

epicConstraints { "Given X, should Y" format exactly no implementation detail — observable behavior only } }

Show full SKILL.md (191 more words)Show less

Step 3 — TDD: Write a Failing Test First

writeFailingTest(requirement) => failingTest { Using /execute:

  1. Write a test that captures the requirement
  2. Run npm run test:unit and confirm the test fails
  3. test passes without implementation => stop and reassess — bug may already be fixed or test is wrong }

Step 4 — Implement the Fix

implementFix(failingTest) => fix {

  1. Write the minimum code needed to make the failing test pass
  2. Run npm run test:unit — fail => fix bug => repeat; pass => continue
  3. Implement ONLY what makes the test pass

Constraints { no over-engineering or unrelated cleanup } }

Step 5 — Self-Review and Run All Tests

selfReviewAndTest(fix) => reviewedFix {

  1. Run /review and resolve any issues found
  2. Run npm run test:unit to confirm all changes pass
  3. Check aidd-custom/config.yml for e2eBeforeCommit: true => run npm run test:e2e false (default) => skip — CI will run the full suite }

Step 6 — Commit and Push

commitAndPush(reviewedFix) { Using /commit:

  1. Stage only the files changed by this fix
  2. Write a conventional commit message (e.g. type(optional-scope): description)
  3. Run git push -u origin <branch-name> }

fix = gainContext |> documentRequirement |> writeFailingTest |> implementFix |> selfReviewAndTest |> commitAndPush

Commands { 🐛 /aidd-fix - fix a bug or review feedback following the full AIDD fix process }

© paralleldrive, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in ai/skills/aidd-fix of paralleldrive/aidd.

  • SKILL.md
  • README.md

Open the folder on GitHubat commit 9a7c8e3

Compare with similar skills

Aidd Fix next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Aidd Fix compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Aidd Fix this skillparalleldrive/aidd384—~886Automated safety check: PassMIT
Test Guidelinesgetsentry/sentry-dart873—~3.1kAutomated safety check: PassMIT
Agent Harness Testing Methodologyhuiliyi37/Tianshu-harness1.1k—~1kAutomated safety check: NotesApache-2.0
TDD Bug Fixcursor/plugins10k8 repos~786Automated safety check: PassNone
Opsmill Dev Test Driving Bugsopsmill/infrahub529—~4kAutomated safety check: PassApache-2.0
Bug FixEmeaAppGbb/spec2cloud100—~2kAutomated safety check: PassMIT

Similar skills

  • Test Guidelines

    getsentry/sentry-dart

    Official

    Enforce Sentry Dart/Flutter SDK test conventions for naming, structure, and fixtures.

    873 GitHub stars~3.1k tokensUpdated today
    Testing & QAAuto-check passed
  • Agent Harness Testing Methodology

    huiliyi37/Tianshu-harness

    Guides an agent through probing an unfamiliar project's test setup, then choosing a red-light-first testing strategy matched to the task type.

    1.1k GitHub stars~1k tokensUpdated yesterday
    Testing & QAAuto-check: notes
  • TDD Bug Fix

    cursor/plugins

    Official

    Fixes a bug with a failing regression test first when a cheap, focused test path exists, and falls back to the closest practical check when it does not.

    10k GitHub starsUsed in 8 repos~786 tokens
    Testing & QAAuto-check passed
  • Writes a single failing test that reproduces a bug after its root-cause analysis is complete, before any fix is written.

    529 GitHub stars~4k tokensUpdated today
    Testing & QAAuto-check passed
  • Bug Fix

    EmeaAppGbb/spec2cloud

    Lightweight entry point for fixing bugs with full traceability.

    100 GitHub stars~2k tokensUpdated 5 mo ago
    Testing & QAAuto-check passed
  • Systematic Debugging

    foryourhealth111-pixel/Vibe-Skills

    Root-cause route for actual bugs, failing tests, build errors, crashes, stack traces, and unexpected behavior.

    3.6k GitHub stars~2.6k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed

More from paralleldrive/aidd

All 35 skills in this repo
  • AIDD Skill Authoring Guide

    paralleldrive/aidd

    Guides creating, reviewing or refactoring AI-Driven Development skills so each one stays minimal, composable and named around a single clear function.

    384 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check passed
  • AIDD UI Layout Patterns

    paralleldrive/aidd

    Enforces a split of UI components into terminal and layout types, with layout components composing others through standard layout tokens, for cleaner structure and fewer re-renders.

    384 GitHub stars~562 tokensUpdated 3 mo ago
    Auto-check passed
  • Adobe Data ECS Plugin Rules

    paralleldrive/aidd

    Enforces @adobe/data/ecs practices when writing Database.Plugin definitions, including property order, plugin composition, services, components, resources and archetypes.

    384 GitHub stars~1.9k tokensUpdated 3 mo ago
    Auto-check passed
  • Error Causes Handling

    paralleldrive/aidd

    Has your agent throw and catch JavaScript and TypeScript errors with the error-causes library, using named causes, preserved originals and routed handlers.

    384 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check passed
  • Teaches the saga pattern with call and put so network requests and side effects stay out of the logic and sagas can be tested without mocks.

    384 GitHub stars~587 tokensUpdated 3 mo ago
    Auto-check passed
  • Lit Element Authoring

    paralleldrive/aidd

    Rules for writing Lit elements in an AIDD project: binding elements on DatabaseElement, observed values, presentation components and action-style callbacks.

    384 GitHub stars~1.2k tokensUpdated 3 mo ago
    Auto-check passed

Questions about Aidd Fix

What does Aidd Fix do?

Fix a bug or implement review feedback following the AIDD fix process. Aidd Fix is an agent skill from paralleldrive/aidd. Fix a bug or implement review feedback following the AIDD fix process.

When should I use Aidd Fix?

Aidd Fix fits situations like: A bug has been reported; A failing test needs investigation; A code review has returned feedback that requires a code change.

How do I install Aidd Fix in Claude Code?

Run `npx skills add paralleldrive/aidd --skill aidd-fix -a claude-code`. Or copy the skill folder (ai/skills/aidd-fix in paralleldrive/aidd) into .claude/skills/aidd-fix in your project. Claude Code loads it when a task matches its description.

How do I install Aidd Fix in Codex?

Run `npx skills add paralleldrive/aidd --skill aidd-fix -a codex`. Or copy the skill folder (ai/skills/aidd-fix in paralleldrive/aidd) into .agents/skills/aidd-fix in your project. Codex loads it when a task matches its description.

Can I use Aidd Fix in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add paralleldrive/aidd --skill aidd-fix -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/aidd-fix, .gemini/skills/aidd-fix, .github/skills/aidd-fix and .opencode/skills/aidd-fix in your project.

What does Aidd Fix need to run?

Going by SKILL.md and its folder, Aidd Fix needs the command-line tools its instructions call (npm and git). Compatibility (from SKILL.md): Requires git, npm, and a test runner (vitest) available in the project..

Does Aidd Fix access the network?

SKILL.md contains no URLs. Its commands use npm and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Aidd Fix safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Aidd Fix use?

Aidd Fix is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Aidd Fix use?

About 886 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Aidd Fix?

Skills that share tags, products or a category with Aidd Fix: Test Guidelines (getsentry/sentry-dart, 873 stars), Agent Harness Testing Methodology (huiliyi37/Tianshu-harness, 1.1k stars), TDD Bug Fix (cursor/plugins, 10k stars) and Opsmill Dev Test Driving Bugs (opsmill/infrahub, 529 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Aidd Fix?

paralleldrive (a GitHub organization) maintains it in paralleldrive/aidd, which has 384 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on June 12, 2026.

Source: paralleldrive/aidd on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.