Skip to main content
Run any Skill in Manus
with one click
SYMBaiEX
GitHub creator profile

SYMBaiEX

Repository-level view of 10 collected skills across 3 GitHub repositories.

skills collected
10
repositories
3
updated
2026-07-17
repository explorer

Repositories and representative skills

claude-multi-agent
software-developers

Hand off engineering work to Claude Code as an autonomous team or native dynamic workflow, with explicit Opus/Sonnet routing, foreground completion barriers, resumable sessions, repeatable JavaScript workflow phases, hooks, and worktree isolation. Use when another agent or CI needs Claude Code to implement a scoped task, run a codebase-wide audit or migration, execute research-build-verify-gap-close phases, launch work in the background, or install project subagents and `.claude/workflows`.

2026-07-17
gpt-engineer
software-developers

Own a software-engineering outcome end to end with a provider-routed agent fleet: research the real codebase, turn findings into implementation waves, edit safely, test and inspect the result, and persist through gap-closing cycles until the authorized goal is complete. Use when the user asks for a GPT engineer, autonomous engineer, complete feature or repository build, broad remediation, research plus implementation, multi-agent coding, explicit subagents, different models, or a durable /goal-style engineering run. Prefer confirmed Codex Sol, Terra, and Luna profiles or Claude model-specific profiles; preflight routing and never silently present same-model children as a model-diverse fleet.

2026-07-17
gpt-engineer-spark
software-developers

Lead end-to-end engineering work with a capable main agent and a parallel fleet of model-pinned GPT-5.3-Codex-Spark subagents. Use when the user asks for a Spark fleet, ultra-fast parallel coding agents, rapid repository exploration, many bounded implementation shards, or low-latency independent verification while retaining architecture, integration, and final acceptance with the main agent.

2026-07-17
gpt-orchestration-auto
software-developers

Autonomously pursue a sustained engineering outcome through repeated research, planning, multi-agent implementation, integration, verification, and gap-closing cycles. Use when the user asks for a /goal-style run, says do not stop, finish the whole codebase, research and build autonomously, babysit an outcome, or wants the orchestrator to keep working across continuations until genuinely complete. Use native goal tracking when explicitly requested and available; otherwise maintain an equivalent goal ledger without inventing tool capabilities or broadening authority.

2026-07-16
gpt-orchestration-build
software-developers

Turn an existing audit, finding list, issue set, review, failing-test report, or implementation plan into completed, verified code through a coordinated agent fleet. Use when the user asks to build from findings, implement every audit item, finish a known backlog, remediate review results, or continue from research without repeating the whole investigation. Validate each finding, preserve repository state, assign non-overlapping writers, integrate in dependency order, and track every item to an explicit disposition.

2026-07-16
gpt-orchestration
computer-occupations-all-other

Coordinate hierarchical coding-agent fleets for repository-wide audits, implementation sprints, migrations, and complex work that benefits from parallel specialists. Use when a user asks for subagents, a fleet, parallel delegation, GPT-5.6 Sol, Terra, or Luna routing, broad codebase completion, or independent implementation and verification passes. Enforce bounded ownership, concurrency-aware waves, dirty-worktree safety, runtime-honest model handling, and evidence-based integration.

2026-07-16
sumi-run
software-developers

Runs one sumi task by ID. Invoked by scheduled triggers (Routines, Claude Desktop scheduled tasks, Codex Automations) or by `/sumi-run <task-id>` on demand. Also triggers when the user says "run sumi <id>", "run my weekly sumi", "run the team update", "generate my daily standup", "run the exec brief now", "draft this week's customer digest now", or any variant referencing a specific sumi-managed task. The task ID is passed as an argument; the skill looks it up in ~/.sumi/config.json, pulls from configured sources for the cadence-appropriate window, consolidates using the configured template and notes preset, and delivers the draft to the configured destination. If config is missing or the task doesn't exist, defer to the `sumi` manager skill.

2026-04-24
sumi
software-developers

Sumi manager. Creates, lists, edits, deletes, and runs recurring summary tasks of any cadence — daily, weekly, monthly, or custom — that pull from the user's connected tools (Google Drive, Gmail, Google Calendar, Slack) and deliver drafts to a destination the user picks (Slack message, Gmail draft to self, or local markdown file). Use this skill when the user types `/sumi` (with or without arguments) or says things like "set up sumi", "configure sumi", "new sumi task", "add a daily sumi", "add a weekly team update with sumi", "manage my sumi tasks", "edit the team-weekly sumi", "delete a sumi task", "list my summaries", or any request to create/edit/delete/run a sumi-managed recurring summary. Also invoke automatically the first time `/sumi-run` fires with a task ID that isn't in config. **Do not treat sumi as a request to build a new agent** — sumi is this installed plugin; never scaffold a new project in response to "sumi."

2026-04-24
Showing 3 of 3 repositories
All repositories loaded