Claude Code Skills · page 61

Coordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.

System and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.

This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable processes, babysitter plugins, and reusable procedural insights. Searches GitHub for SKILL.md files, classifies repos by archetype, and maintains structured research under docs/reference-repos/.

>-

This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.

Discover public GitHub repositories that import defineTask from @a5c-ai/babysitter-sdk and maintain a deduplicated catalog of those repositories in docs/repo-with-babysitter-processes.md. Excludes any repo named "babysitter" (to filter out forks of this monorepo). Invoke when asked to find, discover, catalog, or refresh "repos using babysitter", "babysitter in the wild", or "who else is using babysitter".

Git-backed state management for safe rollback. Create and restore checkpoints with tagged commits and metadata tracking.

Minimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use Write/Edit tools only.

6-agent parallel code review orchestration covering architecture, security, performance, testing, quality, and documentation dimensions with weighted scoring.

Multi-dimensional code assessment across security, quality, performance, and maintainability with confidence-gated reporting (>=80%) and Router Contract generation.

Multi-dimensional code review across correctness, security, performance, and maintainability with confidence-gated reporting and remediation loops.

Automatic codebase indexing for invisible context injection. Catalogs project structure, file types, entry points, dependencies, and test layout.

Capture raw thoughts with automatic domain classification and vault routing

Generate personalized verified news briefs with 7-day freshness and 95%+ source accuracy

Build structured knowledge frameworks from scattered vault notes with source attribution

Process meeting recordings and transcripts into decisions, action items, and team dynamics

Personalize COG Second Brain workflow through role pack selection and vault initialization

Cross-reference GitHub, Linear, Slack, and PostHog with bidirectional sync for team briefs

Save URLs with auto-extracted insights, credibility scoring, and vault routing

Cross-domain pattern analysis with personal, professional, and project domain synthesis

Context window monitoring and budget management. Keeps orchestrator at 15-30% context usage while subagents get full 200k tokens. Provides warnings at thresholds, context-aware summarization triggers, and wave-level budget planning.

Pattern extraction, confidence-scored evaluation, skill creation, organization, versioning, and cross-project export pipeline.

Create, track, and land convoys of related beads as primary work orders in the Gas Town multi-agent orchestration framework.

Root cause analysis frameworks including log-first investigation, git bisect correlation, and pattern-based diagnosis with confidence scoring.

Evaluation harness for testing agent and skill quality through structured benchmarks, regression tests, and quality scoring.

PreToolUse protection blocking sensitive file access across 195+ patterns in 12 categories with bash pipeline analysis and multi-tool ignore support.

This skill should be used when the user asks to "fix pipelines", "fix CI", "check staging pipelines", "fix failing workflows", "fix failing actions", or wants to find and fix failing GitHub Actions workflows on the staging branch of the babysitter repo.

Author TOML-based Formula workflow templates that become Protomolecules and active Molecules in Gas Town's durable workflow system.

YAML frontmatter parsing and manipulation for .planning/ documents. Provides read, write, update, query, and validation operations on frontmatter blocks in GSD markdown artifacts.

Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.

Central utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates calls to other specialized skills. Acts as the unified entry point that the original gsd-tools.cjs provided via its lib/ modules (commands, config, core, init).

Session-scoped hook lifecycle management with enable/disable/status controls, execution profiling, and color-coded performance alerts.

Urgent issue classification, root cause analysis, and fast-path routing for production hotfixes

Track beads as git-backed issues with persistent attribution, supporting Gas Town's bead lifecycle and convoy progress monitoring.

Capture, validate, query, and sync architectural patterns and design decisions in the knowledge graph

Process the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.

Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/quality tradeoffs by selecting appropriate AI models for each agent role.

PM2 process management, backend/frontend cascade execution, parallel worktree builds, and cross-service integration testing.

Continuous monitoring using Deacon/Witness patterns for agent health checks, stuck detection, and automated recovery.

Structured planning methodology with research, brainstorming, phased plan creation, risk assessment, and plan-to-build continuity.

Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

Research-first development methodology that investigates existing solutions, brainstorms alternatives, and evaluates trade-offs before any implementation begins.

Parallel research agent orchestration dispatching 5-10 concurrent agents for comprehensive multi-source research with synthesis and validation.

For a repository in the babysitter-users catalog, locate its babysitter processes and any committed runs (.a5c/runs/<runId>/) and perform a retrospective on a chosen run -- what went well, what failed, process suggestions, quality of effect design, breakpoint patterns -- mirroring the /babysitter:retrospect workflow but applied to an external repo. Invoke when asked to "retrospect on repo X's run", "analyze how someone else used babysitter", or "review an external babysitter run".

Roadmap parsing, analysis, and mutation operations for ROADMAP.md. Handles phase and milestone lifecycle including add, insert (decimal), remove, complete, and requirements coverage analysis.

AgentShield security audit with 5 scanning categories, 102 static analysis rules, and optional red-team simulation.

Manage agent sessions including initialization, handoffs, revival (seance), and persistent identity for Polecats and Crew agents.

Mandatory memory persistence system across session resets using three markdown surfaces in .claude/cc10x/. Iron law - every workflow must load at start and update at end.

Feature specification creation from codebase research. Produces requirements, acceptance criteria, architecture decisions, implementation plans, and risk analysis.

6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.

STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.

Red-Green-Refactor TDD methodology with mandatory failing tests, minimal implementation, quality refactoring, and 80% coverage gating.

Template loading, variable filling, and scaffolding for all GSD artifacts. Manages 22+ templates covering every document type in the GSD system, from PROJECT.md to milestone archives.

Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.

Evidence requirement enforcement ensuring all claims are backed by logs, test results, or exit codes. Zero = success, non-zero = failure. No guessing allowed.

Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.

Decompose goals into MEOWs (Molecular Expressions of Work) - trackable atomic units following Gas Town's bead-based work model.

>

Use when the user asks to draft, polish, translate, or reply to an email. Produces a clean draft with subject line, greeting, body, and sign-off, plus a pre-send self-check.

Use when the user mentions 飞书 / Feishu / Lark workspace operations: docx (云文档) read/write, bitable (多维表格) records / views / dashboards, drive (云盘) upload/download, wiki (知识库) link resolution, approval (审批) instance create/cancel/query, calendar (日历) event create/list/update + attendees, contact (联系人) user/department lookup, hire (招聘) job/talent/application listing. Trigger on phrases like 'OKR 周报', '把这份文档发到飞书云盘', '给团队拉个评审会议', '查 [姓名] 的联系方式', '撤销那条审批', '/wiki 链接', or any request that mentions a feishu / lark URL / token (doxcn.../bascn.../wikcn.../boxcn.../om_...).

Hope Agent browser automation — the standard `status → tabs → snapshot → act` loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the `browser` tool. Trigger on: user asks the agent to open / control / click / scrape / log into / verify something in a web app ('open X and click Y', '打开 X 然后点击 Y', 'log into my Gmail', 'scrape this page', 'fill out the form on X'); user reports a flow that requires real browser context (cookies, JS-rendered content, OAuth).

Hope-native review of uncommitted, staged, commit, branch, or PR changes: discover concrete regressions, independently verify candidates, and report actionable findings first without speculative noise.

Hope-native baseline for implementing, fixing, refactoring, and maintaining code: inspect the repository first, protect user changes, keep scope narrow, and finish with direct evidence.

Hope-native implementation planning for non-trivial code changes: ground the plan in repository evidence, order dependencies, name critical files and risks, define verification, then continue execution when allowed.

Hope-native local-first data analysis and Artifact reporting. Use for CSV/XLSX analysis, KPI readouts, metric diagnosis, product/business analysis, data-quality review, dashboards, charts, analytical reports, 数据分析, 指标诊断, 数据质量, 分析报告, or when the user wants a shareable offline HTML/ZIP/Markdown/PDF result. Produces the versioned AnalysisArtifactV1 contract and registers it with the artifact tool; never guesses missing data or requires public web deployment.

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger phrases: data stores, database path, sessions.db, memory.db, logs.db, background_jobs.db, knowledge index, where is data stored, query app data, 查数据库, 数据存储, 会话记录在哪, 记忆库在哪.

Hope-native debugging for code failures, regressions, crashes, flaky behavior, and bad output: reproduce or characterize, rank falsifiable hypotheses, fix the smallest root cause, and prove the failing path.

Discover and install third-party skills from external registries when the user needs a capability that no currently-active skill covers. Trigger when: (1) the user explicitly asks 'find a skill for X', 'is there a skill that does X', 'install a skill to X', (2) the user requests a well-known integration (Slack, Notion, Trello, GitHub, Hue, Sonos, iMessage, weather, TTS, transcription …) that isn't in the active skill catalog, (3) you are about to hand-write ad-hoc shell / API code for a domain that almost certainly has a published skill. Do NOT trigger if an active skill already covers the need — scan the visible skill catalog first.

Working method for the Hope Agent knowledge space — how to capture, organize, link, retrieve, and maintain Markdown notes well with the `note_*` tools. Load whenever you are reading or writing notes in an attached knowledge base. Trigger on: user asks to take / save / organize / restructure notes, build or grow a knowledge base / vault / second brain, link related notes, find related or similar notes, distill a long note into atomic notes, build a map-of-content (MOC) / index, clean up broken links or orphans, or turn a conversation into a note. Chinese triggers: 记笔记, 整理笔记, 知识库, 知识空间, 笔记网络, 关联笔记, 拆成原子笔记, 建索引/MOC, 清理断链, 把对话存成笔记.

Self-service diagnostics — query Hope Agent's local SQLite databases (logs / sessions / background jobs) directly via the `exec` tool to investigate problems, analyze usage, and locate root causes. Trigger on: user reports something broken / failing / slow / stuck / not responding ('X 不工作', 'X 报错', 'X 卡住', '为什么 X 失败', 'why did X fail', 'show me the logs', 'check what happened'); ad-hoc data analysis ('this week's token usage', '最近调用最多的工具', 'how many subagent runs failed', 'tool error rate', 'find sessions where X happened'); verifying a fix ('did the error stop after I changed Y'). Use BEFORE asking the user to paste log snippets — the data is on disk, query it directly. Read-only — SELECT only, never UPDATE/DELETE/INSERT/DROP.

Hope Agent native macOS desktop control — the standard `mac_control` status / diagnostics / apps / dock / spaces / snapshot / visual / windows / menu / clipboard / dialog loop, target-first action rules, no-blind-coordinate policy, and recovery for stale AX/window/menu/dialog state. Load whenever using `mac_control`, or when the user asks to control local Mac apps, Dock, Spaces, click/type/menu/window/dialog/clipboard, automate Finder/TextEdit/System Settings, visually locate UI, or says 控制 Mac, macOS 自动化, 点按钮, 打开应用, Dock, Space, 关闭窗口, 菜单点击, 视觉定位.

Answer 'how do I use X / where is setting Y / what does panel Z do' questions about Hope Agent from the built-in bilingual user guide instead of guessing from memory. Trigger on: 怎么用, 在哪设置, 怎么开启, 如何配置, 使用手册, 用户手册, 功能说明, how to use, where is the setting, how do I enable, user guide, manual. The guide covers install & onboarding, models & providers, chat & sessions, memory, knowledge space, design space, tools & permissions, autonomous tasks, multi-agent & cron, IM channels, MCP/hooks/skills, projects & insights, settings & security. NOT for: internal implementation questions (ha-self-diagnosis), error/log investigation (ha-logs), actually changing settings (ha-settings).

Hope-native multi-agent coding orchestration: fan out only independent valuable work, enforce bounded scope and isolation, consume structured results progressively, steer or cancel, and keep synthesis with the main Agent.

Safely import, select, switch, or enable a compatible desktop pet in Hope Agent. Resolve packages from any origin, including local folders, zip archives, pet.json plus a sprite, PNG/WebP atlases, chat attachments, repository or cloud files, direct HTTPS artifact URLs, and download pages. Use whenever a user asks to install, add, migrate, import, activate, use, select, switch to, wake, or enable a pet in Hope, regardless of which website, tool, or community produced it.

Self-understanding and issue reporting for Hope Agent itself. Use when the user asks how Hope Agent works internally, asks about its own source code/docs/runtime behavior, reports a bug/failure/slowness/crash, asks to diagnose logs, or asks to create/submit a GitHub issue for a bug, feature request, or improvement (including when there is no bug). Chinese triggers: 自查, 了解自己, 自我诊断, 排查 Hope Agent, 提交 issue, 需求 issue, 功能改进.

Check for and install Hope Agent updates through conversation. Use whenever the user asks about upgrades, new versions, release notes, or reports a bug that might already be fixed upstream — phrases like 'upgrade Hope Agent', 'update hope agent', 'check for new version', '升级一下', '有新版本吗', '帮我升级', 'is there a newer build', 'check release notes', 'install the latest'. Also use proactively when an `app_update(action=\"check\")` result shows `has_update: true` and the user hasn't been told yet. Covers all three formfactors: desktop GUI bundle (DMG/MSI/AppImage), `hope-agent server` daemon installed via Homebrew/Scoop/AUR/apt/dnf, and headless single-binary deployments. The upgrade is always user-confirmed via `ask_user_question` — never silent.