SYM01

@sym01 source repo

2 skills
0 followers
6 hours ago last updated

▌
Brainstorm · sym01
Explicit invocation only. Runs a deliberately expensive competitive multi-agent loop: three teammates each solve the WHOLE task independently, cross-review each other with blocking verdicts (MUST_REJECT / MUST_REVISE / PASS), iterate under that pressure, and the lead consolidates the survivors into one rated report. Load ONLY when the user names it: /brainstorm, "use the brainstorm skill", "run brainstorm on this". DO NOT load it because a task looks hard, ambiguous, high-stakes or design-shaped, and DO NOT load it for "explore options", "compare approaches", "what's the best approach", "give me alternatives", "red-team this", "get multiple opinions", plan mode, or the word brainstorm / 头脑风暴 appearing incidentally in conversation, a file, or a commit message. Those are ordinary work — do them directly. Spending three agents over multiple review rounds is the user's call, not an inference to draw.

0
installs
▌
Plan Doctor · sym01
Reviews and hardens an engineering plan against a standard checklist before any code is written. Use whenever the user enters plan mode, asks to "make a plan", "plan this out", "outline an approach", "break this down", "draft a roadmap", "how should we build X", or otherwise drafts multi-step engineering work — even if they never ask for a review. Also use before starting a complex coding task (3+ files, a new service, a cross-module refactor) that has no plan yet. Checks dependency and runtime currency, whether to parallelise across agents, a formatter/linter/type-check completion gate, an API contract when more than one module speaks HTTP, design tokens for UI work, and a tracked task file for long plans. DO NOT use for single-file edits, bug fixes, code review, questions that want an answer rather than a plan, or work already under way under an agreed plan.

0
installs

2 published skills