code-ai-review
Skill0 starsChanged 5 months agoMITView on GitHub
Performs strict AI code review following code-review-ai-assistant.mdc standards. Reviews current branch changes from merge-base by default, including both committed and local uncommitted changes. Use when: code review requested, checking branch changes, reviewing implementation quality.
In this repository76 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- autodoc-analystSkill
- autodoc-architectSkill
- autodoc-assemblerSkill
- autodoc-orchestratorSkill
- autodoc-scannerSkill
- autodoc-writerSkill
- brainstormSkill
- brd-creatorSkill
- caveman-modeSkill
- changelogSkill
- claude-md-managementSkill
- code-boss-reviewSkill
- code-mobx-store-reviewSkill
- code-reviewSkill
- code-style-reviewSkill
- code-verifierSkill
- commitSkill
- constraint-driven-developmentSkill
- context-collectorSkill
- db-migrateSkill
- dependency-updateSkill
- deploySkill
- doubt-driven-developmentSkill
- feature-analyzerSkill
- feature-devSkill
- fsd-creatorSkill
- gproject-consistency-checkerSkill
- gproject-discoverySkill
- gproject-orchestratorSkill
- gproject-patterns-researcherSkill
- gproject-plannerSkill
- gproject-problem-definerSkill
- gproject-spec-writerSkill
- gproject-stack-advisorSkill
- hookifySkill
- iagoSkill
- interviewerSkill
- interviewSkill
- issue-analyzerSkill
- job-documenterSkill
- job-orchestratorSkill
- perf-checkSkill
- plan-gatekeeperSkill
- prd-creatorSkill
- pr-issue-documenterSkill
- pr-review-commentsSkill
- prSkill
- pushSkill
- review-architectureSkill
- review-backendSkill
- review-clean-codeSkill
- review-core-boundariesSkill
- review-flow-graphSkill
- review-frontend-conventionsSkill
- review-frontendSkill
- review-greptileSkill
- review-highloadSkill
- review-logicSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 61
Run the script from that file to determine MERGE_BASE and SCOPE before proceeding with the review.
- Distinctive: line 102
Avoid noise; focus on actionable, high-signal findings.
- Distinctive: line 103
Do not request large refactors unless explicitly asked.
- Very specific: line 190
When dispatched by job-orchestrator as part of a job pipeline, the prompt MAY include:
- Distinctive: line 197
If provided and the file exists, read the context document before starting the review.
- Distinctive: line 199
Avoid flagging correct library usage as issues (e.g., if context documents the API pattern)
- Distinctive: line 203
If the file does not exist or is not provided, proceed normally — context is optional and non-blocking.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Code AI Review (только текущая ветка)
Workflow
Copy this checklist and track progress:
Code Review Progress:
- [ ] Step 1: Determine parent branch and calculate merge-base
- [ ] Step 2: Collect git diff (committed + local changes)
- [ ] Step 3: Identify changed files and categorize
- [ ] Step 4: Review each file following standards
- [ ] Step 5: Document findings with severity and location
- [ ] Step 6: Generate report with patchesScope Boundaries
This skill focuses on:
- Correctness and logic bugs
- Type safety and TypeScript contract violations
- Security and null-safety issues
- Error handling completeness
- Performance anti-patterns
This skill does NOT duplicate:
- MobX store-specific patterns → covered by code-mobx-store-review
- Naming/formatting/import organization → covered by code-style-review
- Architecture opinions and persona-specific insights → covered by code-boss-review
Главное правило: скоуп ревью
Ревьюй только изменения, внесённые в текущей ветке с момента её ответвления от родительской.
- Если пользователь не передал commit hash/range, включай весь срез ветки от merge-base до рабочего дерева:
- закоммиченные (
BASE_SHA..HEAD) - локальные незакоммиченные (
staged/unstaged/untracked)
- закоммиченные (
- Если пользователь явно передал commit hash/range, ревьюй только запрошенный диапазон; локальные незакоммиченные изменения не добавляй, если это отдельно не попросили.
- Не ревьюй не связанные с веткой части репозитория.
Scope Detection
See shared script: skills/shared/git-merge-base.md
Run the script from that file to determine MERGE_BASE and SCOPE before proceeding with the review.
Команды, чтобы собрать “срез” для ревью
A) Режим по умолчанию (пользователь НЕ дал hash/range)
git status
# Закоммиченная часть ветки
git log --oneline "${BASE_SHA}..HEAD"
git diff --stat "${BASE_SHA}..HEAD"
git diff --name-status "${BASE_SHA}..HEAD"
git diff "${BASE_SHA}..HEAD"
# Полный текущий срез от merge-base до рабочего дерева:
# включает commit'ы + staged + unstaged
# (untracked смотри через git status / git ls-files)
git diff --stat "${BASE_SHA}"
git diff --name-status "${BASE_SHA}"
git diff "${BASE_SHA}"
git ls-files --others --exclude-standardB) Режим с явным hash/range
# Примеры:
git show --stat --name-status --patch <COMMIT_SHA>
git log --oneline <FROM_SHA>..<TO_SHA>
git diff --stat <FROM_SHA>..<TO_SHA>
git diff --name-status <FROM_SHA>..<TO_SHA>
git diff <FROM_SHA>..<TO_SHA>Правила ревью (обязательно)
Ты обязан следовать стандарту ревью из ~/goodai-base/rules/core/code-review-ai-assistant.mdc:
- Structure output as: short summary -> structured findings by category -> concrete suggestions / optional patches.
- Prioritize correctness and safety over style.
- Avoid noise; focus on actionable, high-signal findings.
- Do not request large refactors unless explicitly asked.
Формат вывода (шаблон подробного отчёта)
Пиши ревью по структуре ниже:
## Краткое резюме
<1-3 предложения: что сделано и общий вердикт (OK / needs work).>
## Скоуп ревью (только текущая ветка)
- Ветка: `<BRANCH>`
- Parent ref: `<PARENT>`
- Merge-base: `<BASE_SHA>`
- Режим скоупа: `<default-with-uncommitted | explicit-hash-range>`
- Коммиты (merge-base..HEAD): <N>
- Изменённые файлы: <список или количество>
## Находки
### Correctness
<находки>
### Types & Safety
<находки>
### Architecture & State
<находки>
### Readability & Style
<находки>
### Performance
<находки>
### UX/UI
<находки>
### A11y
<находки>
### Tests
<находки>
## Предложенные исправления (patches)
<минимальные, точечные диффы для самых очевидных фиксов>Формат каждой находки (обязательно)
Для каждой находки укажи:
- Severity:
blocker/major/minor - Location: file path + relevant lines/hunk (from the diff)
- Problem: what is wrong
- Why it matters: correctness/safety/perf/maintainability impact
- Suggested fix: concrete change
- Optional patch: provide a minimal unified diff when straightforward
Пример блока патча:
diff --git a/path/file.ts b/path/file.ts
index 0000000..1111111 100644
--- a/path/file.ts
+++ b/path/file.ts
@@ -1,3 +1,3 @@
-const x = 1;
+const x = 2;Scope Boundaries
This skill covers general AI code quality review following code-review-ai-assistant.mdc.
| Concern | This skill | Use instead |
| Types, safety, architecture, readability, performance, tests | ✅ YES | — |
| MobX store internals (actions, computed, reactions, async) | ⚠️ surface-level only | code-mobx-store-review for deep store analysis |
| boss-style direct feedback, logic-layer enforcement | ❌ NO | code-boss-review |
| Pure style/naming/pattern audit | ❌ NO | code-style-review |
Job Context Awareness
When dispatched by job-orchestrator as part of a job pipeline, the prompt MAY include:
JOB_NAME: <job-name>
CONTEXT_PATH: <JOBS_ROOT>/<job-name>/ai/context.mdIf provided and the file exists, read the context document before starting the review. Use it to:
- Understand which libraries and patterns were intentionally chosen for the implementation
- Avoid flagging correct library usage as issues (e.g., if context documents the API pattern)
- Provide more accurate findings by understanding the project's architectural decisions
- Reference context when justifying suggestions
If the file does not exist or is not provided, proceed normally — context is optional and non-blocking.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

