Skip to main content
Manus에서 모든 스킬 실행
원클릭으로
392fyc
GitHub creator profile

392fyc

Repository-level view of 43 collected skills across 3 GitHub repositories, including approximate occupation coverage.

skills collected
43
repositories
3
occupation fields
3
updated
2026-05-10
occupation focus
Major fields detected across this creator.
repository explorer

Repositories and representative skills

#001
Mercury
37 skills61updated 2026-05-10
86% of creator
handoff
소프트웨어 개발자

Generate a structured handoff document + ready-to-paste starting prompt for the next session, preserving context across session boundaries. **Use `/handoff` whenever you reach context limits, need to hand off to a colleague, or want to continue in a fresh session.** Modes: `/handoff` (manual mode, output prompt), `/handoff auto` (auto-launch next session). Includes state summary, acceptance criteria, references — no manual reconstruction needed.

2026-05-10
dev-pipeline
소프트웨어 개발자

Mercury's preset Main → Dev → Acceptance chain for executing a single, well-scoped coding task end-to-end with blind acceptance review. **Use this skill proactively** whenever the user has a ready-to-implement task (instead of coding inline) — even if they don't explicitly ask for 'dev pipeline'. Say 'dev pipeline', 'dispatch task', '派发任务', 'blind review', or '完整开发链'. When the task is well-scoped, the skill spawns dev subagent to implement, acceptance subagent to blind-review, then loops or completes based on verdict. Independent of Mercury's other modules — works in any repo with .claude/agents/dev.md + .claude/agents/acceptance.md.

2026-05-09
autoresearch
경영 분석가

Autonomous iterative research with mechanical quality gates — multi-round loops, per-round verification, agent doesn't self-decide completion (gate does). **Use this proactively for ≥3 research questions or multi-source verification** — even if the user just says 'research X'. For quick lookups (1–2 questions, single source), use web-research instead. Triggers: 'autoresearch', '自动研究', '深度调研', 'deep research', '多轮调研', 'comprehensive research'. Works standalone or under Mercury dispatch.

2026-05-09
animate-frames
특수 효과 아티스트 및 애니메이터

Mercury's pixel-frame animation pipeline — generate a sprite frame sequence (e.g. 4-frame walking cycle, idle pose set, attack arc) from a character bible JSON + scenes JSON, with built-in verify rubric (frame count, dimension uniformity, palette quantization, dHash consistency, optional loop closure) and structured retry loop. **Use proactively whenever the user asks to generate any frame sequence, sprite sheet, walking cycle, or animated pixel asset** — even if they don't say "animate-frames" explicitly. Triggers: 'animate frames', 'sprite sheet', 'sprite frames', 'walking cycle', 'frame sequence', 'pixel animation', '生成精灵帧', '动画帧序列', '像素动画', '精灵表'. Wraps `scripts.image_gen` (Slice B) which in turn invokes the `adapters/gpt-image-2/` adapter (Slice A, MIT mount of `wuyoscar/gpt_image_2_skill` via uvx-pinned-SHA). Phase 2 Slice C of Mercury Issue #351.

2026-05-08
dual-verify
소프트웨어 품질 보증 분석가·테스터

Run Claude Code deep-review and Codex code-audit in parallel, then consolidate findings. **This is the mandatory pre-commit review step per Mercury CLAUDE.md** — use this instead of /code-review or /auto-verify. Trigger: 'dual verify', 'dual-verify', 'parallel review', 'run dual verify', '双路验证', '并行review', '代码审查', 'review before commit'. Use before any PR creation or direct commit to protected branches.

2026-04-28
gh-project-flow
프로젝트 관리 전문가

Task management for Mercury's own self-development via GitHub Project #3 — pulls next Phase + P0 Todo task, marks In Progress, links work products (PR/Issue), moves to Done. **Use this for Mercury work** — even for housekeeping tasks. Triggers: 'next task', '下一个任务', '拉任务', '认领任务', 'project status', '更新 project', 'Mercury 项目', 'Phase X'. DO NOT use for external projects (Phase 3 will replace this with Memory Layer + Dev Pipeline). BOOTSTRAP-ONLY: retires when Phase 3 ships.

2026-04-23
kb-lint
소프트웨어 품질 보증 분석가·테스터

Run AgentKB knowledge base health checks (lint) — detects broken links, orphan pages, stale articles, contradictions. **Run this regularly to keep KB healthy, especially before major refactors or content merges.** Requires `$AGENTKB_DIR` env var. Triggers: 'lint KB', 'KB health check', '知识库检查', 'check KB', 'KB lint', 'knowledge base health'. Offers `/kb-lint structural` (fast) or `/kb-lint full` (with LLM contradiction detection).

2026-04-23
pr-flow
소프트웨어 개발자

Automate the full PR lifecycle with Argus review bot: create PR, poll for review, read findings, fix issues, push and wait for Argus incremental review, merge after approval. **Always use this skill when code is ready to PR** — even if the user only says 'push' or 'merge' — to avoid manual Argus polling. Trigger: 'PR', 'pull request', 'create PR', 'merge PR', '提PR', '合并', 'PR流程', 'check PR status'. Use after dev work reaches `implementation_done` and branch is pushed. Replaces manual C4-C7 steps in Mercury workflow.

2026-04-23
Showing top 8 of 37 collected skills in this repository.
#002
Argus
5 skills10updated 2026-04-07
12% of creator
autoresearch
시장조사 분석가·마케팅 전문가

Autonomous iterative research protocol with mechanical quality gates. Multi-round search loops with per-round verification -- the agent does NOT decide when to stop, only the gate does. Works standalone or under Mercury dispatch. Triggers: "autoresearch", "自动研究", "深度调研", "deep research", "comprehensive research", "多轮调研".

2026-04-07
dev-pipeline
소프트웨어 품질 보증 분석가·테스터

Mercury's preset Main → Dev → Acceptance chain for executing a single, well-scoped coding task end-to-end with blind acceptance review. Use this skill when the user says "dev pipeline", "dispatch task", "派发任务", "dev → acceptance", "跑完整开发流程", "dev pipeline 验证", "blind review", "完整开发链", or when a task is ready to be implemented and verified by separate agents (instead of doing it inline). The skill spawns the dev subagent to implement, then spawns the acceptance subagent to blind-review the result, then loops or completes based on the verdict. Independent of Mercury's other modules — works in any repo that has .claude/agents/dev.md + .claude/agents/acceptance.md defined.

2026-04-07
dual-verify
소프트웨어 품질 보증 분석가·테스터

Run parallel Claude Code deep-review and Codex code-audit, then consolidate findings before marking PR ready. Use instead of /code-review or auto-verify when doing pre-merge review. Trigger on: "dual verify", "dual-verify", "parallel review", "run dual verify", "双路验证", "双向验证", "并行review", "双路review".

2026-04-07
pr-flow
소프트웨어 개발자

Automate the full PR lifecycle with the Argus review bot: create PR, poll for review, read findings, fix issues, push and wait for Argus fix-detection resolve + incremental review, merge after approval. Use this skill when the user says "PR", "pull request", "create PR", "merge PR", "提PR", "合并", "PR流程", "开PR", "check PR status", "review comments", "标准PR流程". Use this skill after dev work reaches implementation-complete and the branch is pushed. Works in any GitHub repo that has Argus review bot wired up.

2026-04-07
web-research
소프트웨어 개발자

Mercury's mandatory web research protocol for verifying external SDK/API/CLI behavior before writing code. Use this skill whenever the task involves importing external packages, referencing API signatures, claiming package versions, using CLI flags, or integrating with third-party tools. Also use when the user says "研究", "验证", "审查", "查阅", "核实", "调查", "research", "verify", "validate", "check docs", "look up". This skill should be consulted proactively — even if the user doesn't explicitly ask for research, any code touching external dependencies needs verification first. Training data is frequently wrong about API signatures and versions; a 2-minute search prevents hours of debugging.

2026-04-07
저장소 3개 중 3개 표시
모든 저장소를 표시했습니다