catoncat
- 10 skills
- 0 followers
- 6 hours ago last updated
- ▌ 0g Hk · catoncat bundleUse when the user wants a 0g.hk / og temporary public link, paste, Markdown note, code or prompt share, semantic short URL, curl-readable raw note, or wants to list, edit, renew, or find locally saved edit credentials for prior 0g.hk links. Do not use for permanent hosting, private access control, collaborative docs, SLA-backed publishing, or content over the configured limit (24KB by default; tunable in /admin/config).
- ▌ Anysearch · catoncat bundleProbe the web with AnySearch when current facts, source discovery, URL extraction, multi-angle comparison, or live vertical schemas are needed. Use a compact probe first, extract selected URLs only when evidence is needed, and recover through the key pool on auth/quota failures.
- ▌ Codex Conductor · catoncat bundleUse in Codex App when a complex task needs coordinated Codex Sessions, long-running milestones, cross-session state, worktrees, verification sessions, heartbeat continuation, project-specific constraints, or durable workflow artifacts. Assumes Codex Goal support; optional lifecycle capabilities and project profiles are discovered at runtime.
- ▌ Export Session · catoncatUse when the user says /export-session, $export-session, export-session, export current Codex session, save this conversation as Markdown, dump transcript, asks to export a Codex rollout/session to .md, or asks to publish/share that export to 0g.hk.
- ▌ Prepare Image Edit Mask · catoncat bundlePrepare and troubleshoot masks for OpenAI image edits. Use when a user needs help selecting an edit region, creating or converting an arbitrary raster selection, validating an existing mask, learning a software-specific workflow, or diagnosing an edit that changed the wrong area.
- ▌ Sherlog · catoncat bundleSearch local agent-session history to recover prior decisions, commands, configurations, and context from earlier sessions. Use for cross-session recall when the current task depends on what happened in a previous agent conversation, not for inspecting the current repository or summarizing the current session.
- ▌ Vox · catoncat bundleVox 语音工作流编排技能。用于 profile 管理、模型查询与准备、ASR 转写、TTS(clone/custom/design)、pipeline 执行、安装体检与故障排查。用户只描述目标且未给具体命令时使用。
- ▌ Xsearch · catoncat bundleWeb search and online research. Use xsearch for every request that needs current public information: simple online facts, latest developments, official-source verification, comparisons, research, multi-angle surveys, or explicit web/Grok search.
- ▌ Agent Red Team · catoncat使用双 Agent 左右互搏防止“目标坍缩/自圆其说”。当用户提到让另一个 Agent 挑刺、红队测试、反例驱动、边界场景攻击、验证测试是否有意义时触发。
- ▌ Auto Claim Issues · catoncat bundle为 browser-brain-loop 项目自动认领 backlog issue / slice。用于用户要求“认领 issue”“自动 claim backlog”“挑一个可并行的 slice 开工”“找下一个可做 issue”时触发。会读取 docs/backlog 和 next-development-slices 文档,优先认领依赖已满足且与当前 in-progress write_scope 不冲突的 open issue。