← 返回 Skills 市场
sercanmetalore

Ai C Plan

作者 Sercan Boyraz · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
386
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install ai-c-plan
功能描述
AI-C plan klasöründeki MD/CSV planı okuyup dependency sırasına göre tamamen otomatik ilerler; geliştirir, test eder, raporlar.
使用说明 (SKILL.md)

Proje ve structure yapısını oluştur. Gerekli dosyaları oluştur. Teknoloji stack ve design referanslarına uygun şekilde kod yaz. Her step'te planlanan değişiklikleri uygula, test et, raporla. Gerektiğinde config dosyaları oluştur. Her step sonunda commit at. Eğer bir step eksik bilgi/erişim/bağımlılık nedeniyle yapılamıyorsa Blocked yap ve gereken aksiyonları açıkla.

PRE-EXECUTION RULE

Her step başlamadan önce:

  1. docs/architecture/AI_CONSULTANT_SYSTEM_PROMPT.md dosyasını oku
  2. Bu dokümandaki teknoloji stack ve monorepo yapısına uyduğunu doğrula
  3. Uymuyorsa step'i Blocked yap ve sapma nedenini açıkla 3.1 Minimum sapmayla uyumlandırmayı dene. 3.2 Gerekirse config dosyası üret. 3.3 Gerçekten imkansızsa Blocked yap. 4.Eksik klasörleri ve minimal dosyaları otomatik oluştur (packages/config gibi) ve devam et; sadece destructive işlemlerde dur.
  4. UI step başlamadan önce /home/adige/AI-C/desing klasöründeki ilgili ekran görseli/HTML dosyasını incele ve ekranı referansla birebir hizala.
  5. Database/schema değişikliği yapılıyorsa migration üret ve uygula.

ENV POLICY (No-Questions Mode)

Bu projede dış bağımlılıklar için tüm konfigürasyon .env üzerinden yönetilecek.

Kurallar:

  1. Agent gerçek secret üretmeye/uydurmaya çalışmaz.
  2. Agent her servis için .env.example ve ilgili alt-app .env.example dosyalarını oluşturur/günceller.
  3. Gerçek secret gerekli ise placeholder bırakır (örn: "REPLACE_ME") ve açıklama ekler.
  4. Eksik secret varsa:
    • Mümkünse "DEV_FALLBACK" moduna geç (mock provider / stub).
    • Uygulama boot edebilecek kadar default ile ilerle.
    • Sadece tamamen imkânsızsa Blocked yap.
  5. Tüm dış servis konfigürasyonları .env üzerinden yönetilir.
  6. .env.example dosyaları otomatik oluşturulur/güncellenir.
  7. Gerçek secret üretilmez, placeholder bırakılır.
  8. Eksik secret varsa DEV_FALLBACK_MODE ile mock provider kullanılır.

Zorunlu dosyalar:

  • .env.example (repo root)
  • apps/api/.env.example
  • apps/web/.env.example
  • apps/mobile/.env.example

Git kuralları:

  • .env* dosyalarını gitignore et (sadece *.example commit edilir).

Autopilot Modu

Bu skill, kullanıcıdan her adımda onay istemeden ilerler. Sadece şu durumlarda durur:

  • Bir step "Blocked" olursa (eksik bilgi/erişim/bağımlılık).
  • Güvenli olmayan/destructive bir işlem gerekiyorsa (silme, prod deploy, ödeme, gizli anahtar yazma).
  • Plan dosyaları bulunamazsa.

Plan Kaynakları (öncelik)

  1. plan/ai_consultant_mobile_project_plan.md
  2. Yoksa plan/ai_consultant_full_project_plan.md
  3. Md yoksa csv fallback dosyaları

Yürütme Algoritması

  1. Planı oku → tüm ST-* satırlarını çıkar.
  2. Bir DAG oluştur:
    • depends tamamlanmadan step başlamaz.
    • blocks bir sonraki hedefi gösterir (sıra/öncelik ipucu).
  3. Çalıştırma sırası:
    • Önce P0'lar, sonra P1/P2/P3
    • Aynı öncelikte dependency-ready olanları sırayla
  4. Her step için:
    • "Planlanan değişiklik" (kısa)
    • Uygulama: dosya değişiklikleri
    • Komutlar: lint/test/build (repo yapısına göre)
    • Schema değişikliği varsa: Prisma migration (apps/api içinde) + migration dosyaları
    • Doğrulama: acceptance kriteri yerine "plan hedefi + çalışır build/test"
    • Status: Done / Blocked
    • Blocked ise: neden + gereken aksiyonlar + hangi bilgi lazım
  5. Her tamamlanan step sonunda:
  • git add .
  • Conventional Commit formatında commit at
  • Commit mesajı: "feat(epic-01): initialize monorepo structure"

Repo/Çalışma Kuralları

  • Workspace dışına yazma.
  • Gizli anahtarları (API key, cert, signing key) dosyaya yazma; sadece env değişkeni olarak tarif et.
  • Progress kaydı tek kaynak olarak /home/adige/AI-C/progress.json üzerinde tutulur.
  • Bir step tamamlandığında ilgili step status alanını done/DONE olarak güncelle.
  • Kullanıcıdan onay istemeden sıradaki runnable maddeye geç.
  • Her 3-5 step’te bir veya büyük bir değişiklikte:
    • git status kontrol et
    • mümkünse küçük commit at (repo git ise)
  • Eğer repo yoksa güvenli şekilde git init yap ve devam et.

Çıktı Formatı

Her step için:

Step \x3CID>: \x3CTitle>

  • Priority:
  • Depends:
  • Changes:
  • Files changed:
  • Commands run:
  • Verification:
  • Status: Done/Blocked
安全使用建议
This skill will autonomously read and modify a local project tree, create configuration files, run build/test commands and database migrations, and make git commits. Before installing or running it: - Do not run against a production machine or repository. Test in an isolated VM/container or a forked repo. - Ensure backups and database snapshots exist (migrations can change data). Require explicit confirmation before applying migrations to any real DB. - Inspect plan files and the architecture/UI documents it will read (plan/* and docs/architecture/* and /home/adige/AI-C/desing) — these are referenced by absolute paths. Fix the '/desing' typo if necessary. - Verify the environment: the skill expects tools such as git, Node/npm or yarn, Prisma/DB tools, test runners and possibly docker, but it does not declare them. Add checks or declare required binaries and versions. - Confirm that .env files in your workspace do not contain production secrets. The skill will create .env.example files and tries to avoid writing real secrets, but you should still ensure the agent cannot access live credentials. - Prefer changing the skill to ask for explicit per-step user approval for any potentially destructive action (git push, DB migrate, deleting files, prod deploy). - If you plan to proceed, request the maintainer to: (1) declare required binaries and env vars in the metadata, (2) remove hard-coded absolute paths or make them configurable, (3) disable fully-autonomous actions for migrations and commits or require user consent, and (4) add preflight checks that detect and refuse to operate on production remotes/DBs. Given these issues, treat the skill as suspicious until the above inconsistencies are addressed.
功能分析
Type: OpenClaw Skill Name: ai-c-plan Version: 1.0.0 The skill is classified as suspicious due to instructions in `SKILL.md` that direct the AI agent to interact with the file system outside its presumed workspace using absolute paths. Specifically, it instructs the agent to read from `/home/adige/AI-C/desing` and write to `/home/adige/AI-C/progress.json`. While the skill includes a general rule 'Workspace dışına yazma' (Do not write outside the workspace), the explicit instruction to write to an absolute path creates an exception, indicating a potential prompt injection vulnerability that allows the agent to operate beyond its intended sandbox. This represents a risky capability without clear malicious intent (e.g., data exfiltration to external endpoints or installing backdoors), thus classifying it as suspicious rather than malicious.
能力评估
ℹ Purpose & Capability
The declared purpose (automatically execute a project plan from MD/CSV, implement, test, report) is plausible for the instructions. However, the skill does not declare any required binaries, tools, or environment variables even though the runtime instructions explicitly expect git, build/test/lint tooling, Prisma migrations, Node/JS toolchain, and filesystem access under /home/adige/AI-C. This mismatch (no declared binaries/envs despite demanding build/migration steps) is an inconsistency that should be fixed.
⚠ Instruction Scope
SKILL.md instructs the agent to read and enforce a local architecture doc and UI files at hard-coded absolute paths (e.g., /home/adige/AI-C/docs/..., /home/adige/AI-C/desing and /home/adige/AI-C/progress.json), auto-create folders/files, run database/schema migrations and run lint/test/build commands, and commit changes. These are broad, privileged operations on the user's filesystem and potentially on databases; they go beyond a simple 'read a plan' skill and could have destructive side effects if run against a production database or repository. The SKILL.md also contains a likely-typo path (/desing) which may cause unexpected behavior.
ℹ Install Mechanism
This is instruction-only (no install spec), which limits written code risk. However, not declaring required tooling is problematic: the instructions expect runtime tools (git, node/npm/yarn, prisma/migration tooling, test runners, possibly docker) but provide no guidance or checks. That mismatch increases the chance the agent will fail unpredictably or attempt actions assuming tools exist.
⚠ Credentials
The skill declares no required environment variables or credentials, yet the ENV POLICY section places heavy emphasis on .env files, creating .env.example files, and using .env to control external services. The skill will read/write .env.example and expects to use DEV_FALLBACK_MODE for missing secrets. This is inconsistent: the skill will interact with secrets/config but does not declare them, and it uses absolute repo paths that may contain sensitive data. Requesting no env vars while instructing access to environment-managed secrets is disproportionate.
⚠ Persistence & Privilege
The skill will persist progress to a hard-coded path (/home/adige/AI-C/progress.json), auto-init git if no repo exists, and write files/configs inside the workspace. While it is not 'always: true', its Autopilot Mode explicitly proceeds without per-step user approval (unless blocked). Autonomous execution combined with filesystem writes and DB migrations increases risk—especially because the skill can run schema migrations, commit changes, and modify repo structure without explicit approval.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install ai-c-plan
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /ai-c-plan 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release – fully automated project plan execution based on MD/CSV with dependency management and environment config policies. - Reads and executes plan files step-by-step, auto-generates required folders/files, and applies changes according to dependency order. - Ensures compliance with referenced architecture and technology stack by reading AI_CONSULTANT_SYSTEM_PROMPT.md before each step. - Handles .env configuration for all services, auto-creating .env.example files and using placeholders for secrets. - Runs in autopilot mode, committing after every step, and reports or blocks only when required by missing info, destructive action, or plan file absence. - Logs all progress to a single progress.json, updating step status automatically.
元数据
Slug ai-c-plan
版本 1.0.0
许可证 —
累计安装 1
当前安装数 1
历史版本数 1
常见问题

Ai C Plan 是什么？

AI-C plan klasöründeki MD/CSV planı okuyup dependency sırasına göre tamamen otomatik ilerler; geliştirir, test eder, raporlar. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 386 次。

如何安装 Ai C Plan？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install ai-c-plan」即可一键安装，无需额外配置。

Ai C Plan 是免费的吗？

是的，Ai C Plan 完全免费（开源免费），可自由下载、安装和使用。

Ai C Plan 支持哪些平台？

Ai C Plan 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Ai C Plan？

由 Sercan Boyraz（@sercanmetalore）开发并维护，当前版本 v1.0.0。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论