ccoalm

ccoalm/ccl-skills

Plugin Claude Code

Plugin marketplace listing 1 plugin: ccl-skills.

ccoalm/ccl-skills

Plugin Claude Code

CCL 研发技能全库（按交付物路由：product-rd-workflow / testing-strategy / test-artifact-management / defect-diagnosis / skill-extraction-workflow / tighten-doc / 各 -dev / -architecture …）+ 团队护栏（编辑隔离 PreToolUse hook + 研发路由 SessionStart bootstrap + worktree-isolation 技能）。.

ccoalm/ccl-skills

Command

Install or refresh CCL skills for OpenCode.

ccoalm/ccl-skills

Command

Refresh CCL skills for OpenCode and remind to restart.

ccoalm/ccl-skills

Command

Verify CCL skills and OpenCode local discovery.

ccoalm/ccl-skills

Command

Check whether current repository is safe for editing under repository worktree rules.

ccoalm/ccl-skills

Instructions file CodexOpenCode

A repository instruction file that tells coding agents how to work in the ccl-skills project. It defines shared rules, responsibilities, and checks for reusable agent skills.

ccoalm/ccl-skills

Hook

Runs when a session starts on startup, clear and compact, executing session-start.sh. From ccoalm/ccl-skills.

ccoalm/ccl-skills

Hook

Runs before the agent uses a tool for Edit, Write, MultiEdit, NotebookEdit, Edit, Write, MultiEdit, NotebookEdit, Bash, Bash, Bash, Task and Agent tool calls, executing guard-edit-isolation.sh, owner-dispatch-guard.sh, guard-merge-authorization.sh, remind-unverified-cli-flag.sh and guard-delegation-owner.sh (5…

ccoalm/ccl-skills

Hook

Runs after a tool call finishes for Bash tool calls, executing remind-post-merge-cleanup.sh. From ccoalm/ccl-skills.

ccoalm/ccl-skills

Hook

Runs when you submit a prompt, before the agent sees it, executing merge-authorization-prompt.sh. From ccoalm/ccl-skills.

ccoalm/ccl-skills

Hook

Runs when a subagent starts, executing subagent-start.sh. From ccoalm/ccl-skills.

ccoalm/ccl-skills

Hook

Runs when the agent finishes a response, executing owner-dispatch-stop.sh and skill-extraction-gate-stop.sh (2 commands). From ccoalm/ccl-skills.

ccoalm/ccl-skills

Hook

Runs when a subagent finishes, executing owner-dispatch-stop.sh. From ccoalm/ccl-skills.

ccoalm/ccl-skills

Skill Claude CodeCodex

A repository check for AGENTS.md files, which are local instructions that tell coding agents how to work in a directory. It scans the repository root and source-code directories and can add missing placeholder files.

ccoalm/ccl-skills

Skill Claude CodeCodex

Use when designing, implementing, reviewing, debugging, testing, or shipping mobile app client features across Flutter, React Native, native Android, and native iOS, including navigation, state, API integration, offline/cache, platform capabilities, accessibility, performance, app build/release, and rendered device…

ccoalm/ccl-skills

Skill Claude CodeCodex

Use when an implementation needs an independent CLI reviewer or adversarial challenger, routing across Claude Code, Kimi, OpenCode, or Codex according to local availability, model-family independence, and the user's client order; also covers Claude-only bounded consultation and requests such as code review, Claude…

ccoalm/ccl-skills

Skill Claude CodeCodex

Use this skill for the full defect discipline: diagnose the immediate failure, fix it with evidence, then decide whether root-cause prevention should update a product, architecture, development, testing, release, or tooling skill.

ccoalm/ccl-skills

Skill Claude CodeCodex

风险定级 / 要不要灰度 / 需要哪些 gate / 双人 review / 架构评审 / 安全审计 / 安全评审 / 威胁建模 / security audit / threat model / OWASP / pentest review / risky → classify a feature, fix, or change by risk tags (incl. a security-review gate) and name required design, arch, dev, test, review, security, launch, and rollout gates.

ccoalm/ccl-skills

Skill Claude CodeCodex

Design, review, or explain a new product's Go backend/microservice architecture using Kitex or similar RPC, Hertz or similar HTTP gateway, protobuf IDL, MySQL/GORM storage, Redis cache/locks/limits, service discovery, dynamic config, message queues, observability, DI, and code generation. Also owns multi-tenant…

ccoalm/ccl-skills

Skill Claude CodeCodex

Use when implementing, modifying, scaffolding, generating, or testing a new product's Go microservice, backend feature, or standalone Go CLI/tooling binary using protobuf IDL, Kitex or similar RPC, Hertz or similar HTTP, Wire/DI, MySQL/GORM-style DAL, Redis, MQ, dynamic config, code generation, and focused tests. For…

ccoalm/ccl-skills

Skill Claude CodeCodex

Use this when the user explicitly asks to grill, interview, challenge, or stress-test a plan before implementation.

ccoalm/ccl-skills

Skill Claude CodeCodex

Use when designing, implementing, reviewing, debugging, or operating LLM, agent, RAG, prompt, model-routing, streaming, evaluation, replay, shadow, token-cost, or batch inference features across backend products. Product-agnostic; do not depend on prior codebase names, paths, providers, or business domains. Triggers…

ccoalm/ccl-skills

Skill Claude CodeCodex

小程序 / Taro / 微信小程序 / 支付宝小程序 / 抖音小程序 / 小程序上线审核 → implement, debug, test, and ship mini-program client features: pages, state, API integration, auth, sharing, platform capabilities, review, and device verification. Triggers also include "重构这个小程序页面/组件(局部)", "refactor a mini-program page/component".