现金管理主流程 — 整合余额监控 + 付款计划 + 缺口预警的完整资金管理周期。 适用情形：每日/每周/每月定期执行，整合资金余额监控、付款计划编排、 现金流预测全流程，输出完整的资金管理报告和下期待办。 核心：日监控 → 周计划 → 月预测的三层管理体系。
现金池配置 — 设计和管理公司现金池结构，包括跨境现金池、 境内现金池和透支额度优化。 适用情形：集团资金管理优化、新设子公司时，或用户要求"配置现金池"时执行。 核心：账户结构设计 + 归集规则 + 税务优化 + 银行协调。
资金余额监控 — 每日生成资金余额日报，核查三方数据一致性，识别资金风险。 适用情形：每日固定时间（如早 9 点）执行，从 [CASH]/[BANK]/[ERP] 获取各账户余额， 核查三方数据一致性，识别余额异常和资金风险，输出资金日报。 核心：三方核对（资金系统/网银/ERP）+ 余额异常识别 + 预警触发。
Guides Claude through discovering data source schemas and registering them in the insight-blueprint data catalog. Supports CSV, API, and SQL sources.
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized…
Watch a PR through CI and review feedback. Auto-fix high-confidence failures and address review comments. Use when the user says 'babysit
' or 'respond to PR comments'.
Ship changes. Simplify the diff, commit, review, push, and open or update a PR. Use when the user says 'ship it', 'commit and push', or wants a PR created or updated.
Implement a plan file or direct request end-to-end, validate, and ship via cb-ship. Use when the user says 'implement the plan' or clearly wants a change implemented and shipped.
CONTRIBUTOR TOOL - Track CC changelog, extract new versions since last check, analyze impact on plugin (breaking changes, opportunities, deprecations).
Session 4 demo skill — samples one inbox per sending domain on a campaign, triggers an inbox placement test via Instantly API, surfaces per-domain SpamAssassin scores and…
Triggers: 当你在 Codex 收到 `$cc-master:cc-master-as-master-orchestrator ...`（兼容 `$cc-master-as-master-orchestrator ...`、`$cc-master:as-master-orchestrator ...`）时，初始化或接管 orchestration…
Triggers: 当你在 Codex 收到 `$cc-master-handoff-to-new-session` 时，按接替流程 quiesce/drain、写 handoff 并归档 board；Do NOT 在未确认时直接结束或遗漏迁移信息。
Triggers: 当你在 Codex 收到 `$cc-master-retro [--home
] [--board ] [--out ]` 时，对一块 cc-master board（进行中或已归档均可）做只读复盘并把复盘文档写进被编排项目内；Do NOT 用它写 board、不用于替代 handoff…
Use this skill for semantic code search and codebase understanding. CCG-RAG provides intelligent retrieval using code embeddings and knowledge graphs. — from general/general-misc
Use this skill for multi-step development tasks. Latent Chain Mode reduces token usage by 70-80% through hidden-state reasoning with 4-phase workflow: analysis → plan → impl →…
Use this skill for semantic code search and codebase understanding. CCG-RAG provides intelligent retrieval using code embeddings and knowledge graphs. — from general/general-misc
Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Opus 4.8 default, full 1M context at standard price)
View and tune CCO's behavior thresholds — re-read warnings, cache staleness, prompt-coach length bands, and the /cco-pack budget cap
Share learned file patterns across a team — export an anonymized digest of what's usually waste/useful/co-edited, and import a teammate's so a fresh clone benefits day one
Organize work by task and track tokens/cost per task — start a task, list tasks, or mark the active one done. Pairs with /cco-pack to load minimal context per task.
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses
Hybrid orchestrator pattern for iterative development. Coordinator + specialized workers with batch wait support. Triggers on "ccw-loop-b".
Ride a running Chromium browser via Chrome DevTools Protocol. Access authenticated sessions (Gmail, Slack, etc.) without re-logging in.
Babysits or watches an open GitHub PR until merge-ready, continuously reacting to review comments, CI failures, and routine base movement throughout the PR's life.
Explore requirements and approaches through collaborative dialogue before planning implementation — from marcusrbrown/systematic
Capture a visual demo reel (GIF, terminal recording, screenshots) for PR descriptions. Use when shipping UI changes, CLI features, or any work with observable behavior that…
Review requirements or plan documents using parallel persona agents that surface role-specific issues.
Hands-off, diff-scoped browser QA of the active branch: maps user flows, drives a real browser, autonomously fixes small breakages with regression tests and commits, judges…
[BETA] Dogfood the active branch end-to-end as a QA engineer. Diffs the branch against main, builds an exhaustive browser test matrix of every change (full user journeys, not just…
Create a durable, visual teaching artifact — plus an optional check-in (predict-then-reveal for diffs, corrected exercises) that makes it stick — for something worth learning: a…
Write, audit, or debug Microsoft Fabric Real-Time Intelligence workflows: Eventhouse, KQL databases, Eventstreams, ingestion mappings, update policies, materialized views,…
Create or validate publication-ready scientific figures with JAMA-style typography, layout, and traceability checks.
Create a session handoff for another agent, or resume, find, and read any user-selected continuity source.
Generate and critically evaluate grounded ideas about a topic. Use when asking what to improve, requesting idea generation, exploring surprising directions, or wanting th — from…
Transform feature descriptions into well-structured project plans following conventions
Start the dev server, open the feature in a browser, and iterate on improvements together. Manual invocation only — type /ce-polish to run it.
[BETA] Start the dev server, open the feature in a browser, and iterate on improvements together.
Give a decisive, project-grounded point of view in the subject's own shape: a graded verdict on an external-adoption question, a holistic take on a document, or a position on a…
Summarize recent compound-engineering plugin releases, or answer a specific question about a past release with a version citation.
Resolve PR review feedback by evaluating validity and fixing issues in parallel. Use when addressing PR review comments, resolving review threads, or fixing code review feedback.
Retune a skill corpus for a new model, measurement-first: mine the run archive for a baseline, establish a noise floor, audit the corpus adversarially, then cut in measured passes…
Perform exhaustive code reviews using multi-agent analysis, ultra-thinking, and worktrees
[BETA] Structured code review using tiered persona agents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR.
Simplify and refine recently changed code for clarity, reuse, quality, and efficiency while preserving behavior.
Skill V2 strict de préparation d'une cession de droits patrimoniaux d'auteur. Il fixe un contrat d'entrée fermé, un seuil de préparation de cession, une branche bornée de…
Add a custom MCP connector — connect any API or service to ContentForge via .mcp.json configuration.
Track content quality scores, pipeline timing, and compliance trends with insights and alerts.
Audit content library for freshness decay, coverage gaps, and optimization opportunities.
Plan content calendars with scheduling, deadlines, team assignments, and Google Calendar sync.
Set up an MCP connector with step-by-step instructions. Use to connect Notion, Canva, Webflow, etc.
One-shot setup that wires ContentForge for team usage in Anthropic Cowork. Verifies Cowork environment, checks for a Google Drive integration, creates the canonical Drive folder…
Detect the runtime environment (Cowork sandbox vs local Claude Code) and report which ContentForge capabilities work in it.
Show the ContentForge user guide, available skills, pipeline overview, examples, and troubleshooting
Show active and available MCP connectors with workflow impact. Integration status dashboard.
Publish finished content to Webflow or WordPress via MCP connectors with preview, verification, and HTML export fallback
Collect and act on review results from an external AI agent. Reads the result file written by an external reviewer and presents findings, then offers to fix issues.
Generate a review prompt for an external AI agent. Creates a self-contained document that any AI (Gemini, Codex, ChatGPT, or even a human) can read and use to review your code…
Import brand voice profiles from documents or URLs. Use when setting up or updating a brand.
Create custom content type templates beyond the 5 built-in types with structure and quality standards.
Translate content into 15+ languages preserving brand voice, citations, and SEO. Three localization levels.