Agent skill

brainstorming

Ambiguity-reduction workflow for requests that are not yet plan-ready or implementation-ready. Use when there are multiple plausible approaches, the task is user-facing or design-shaping, requirements are fuzzy, or Codex needs to compare 2-3 options with trade-offs before choosing a direction.

Stars 9
Forks 0

Install this agent skill to your Project

npx add-skill https://github.com/i9wa4/dotfiles/tree/main/nix/home-manager/agents/skills/brainstorming

SKILL.md

Brainstorming

Use this skill to turn a fuzzy request into a concrete direction without pretending every task needs a full design exercise.

1. Core Defaults

  • Use this skill only when the task is genuinely ambiguous or multi-approach.
  • Do not block already-clear work behind extra ideation.
  • Ask at most one clarifying question at a time when interaction is needed.
  • In non-interactive lanes, make the safest explicit assumption and record it.
  • Produce 2-3 viable approaches with trade-offs before recommending one.
  • Stop brainstorming once the direction is stable enough for planning or implementation.

2. Workflow

  1. Restate the objective in plain language.

    • what success looks like
    • what must not change
  2. Pull out hard constraints.

    • repo rules
    • scope limits
    • approval boundaries
    • user or lane constraints
  3. Identify the real unknowns.

    • missing requirement
    • unresolved design choice
    • unclear audience or operator
  4. Resolve the next blocking unknown.

    • ask one concise clarifying question when interactive
    • otherwise state the least-risk assumption you will use
  5. Generate 2-3 approaches. For each approach, include:

    • shape of the solution
    • main benefit
    • main risk
    • why it fits or does not fit this repo
  6. Recommend one approach.

    • explain why it is the best local fit
    • name the next concrete step

3. Repo Fit

  • Use mkmd artifacts when the brainstorming output needs to persist as research or a plan input.
  • Hand off to plan-design when the outcome is a multi-phase execution plan.
  • Hand off directly to implementation when the scope is now narrow and stable.
  • Do not require tracked design docs or a universal approval loop.

4. Good Triggers

  • Multiple valid implementation shapes exist.
  • The request mixes product, UX, and technical choices.
  • The user asked for options, trade-offs, or a recommendation.
  • The task is user-facing and failure would come from solving the wrong problem.

5. Bad Triggers

  • The task already has a clear acceptance target.
  • The next step is obviously a small mechanical change.
  • The work is already in an approved plan with concrete milestones.

In those cases, skip this skill and proceed with the narrower workflow.

Expand your agent's capabilities with these related and highly-rated skills.

i9wa4/dotfiles

subagent-review

Argument-driven code/design review wrapper. Invokes reviewer sub-skills for each specified engine+tier label. Defaults to 'cc cx' (10 reviewers) if no arguments given. Argument format: space-separated labels from {cc, cc-deep, cx, cx-deep} Examples: 'cc cx' (default), 'cc-deep cx-deep', 'cc', 'cx-deep' Use when: - Running code reviews on PRs, commits, or branches - Running design reviews on issues or documents - Need multi-perspective review (security, architecture, code, QA, historian)

9 0
Explore
i9wa4/dotfiles

databricks-local

Databricks local additions - Queries API, VARIANT/JSON, Dashboard API, dbt integration, Jupyter kernel Supplements the official `databricks` skill with project-specific patterns. Use when: - Working with Databricks Queries API (saved queries) - Handling VARIANT type or JSON operations - Working with Lakeview Dashboard API - Integrating dbt with Databricks JSON/VARIANT columns - Running Jupyter notebooks with Databricks kernel

9 0
Explore
i9wa4/dotfiles

codex-prompting-local

Portable Codex prompt, review-contract, and resume-handoff guidance adapted from codex-plugin-cc for this repo's Nix-managed Codex CLI and Claude Code setup. Use when: - Composing prompts for Codex or GPT-5.4-based subagents - Designing structured review or adversarial-review prompt contracts - Writing resumable task prompts or result handoffs - Re-expressing useful old slash-command workflows on the skills side instead of reviving slash commands

9 0
Explore
i9wa4/dotfiles

nix

Nix commands and package management guide. Use when: - Using nurl for hash acquisition

9 0
Explore
i9wa4/dotfiles

bigquery-local

BigQuery local additions - cost-aware query patterns and project conventions. Supplements general BigQuery knowledge with guardrails. Use when: - Running bq commands - Writing GoogleSQL queries - Designing partitioned/clustered tables

9 0
Explore
i9wa4/dotfiles

tmux

tmux pane operations guide for debugging and monitoring separate panes Use when: - Sending commands to another tmux pane - Capturing output from another tmux pane - Monitoring long-running commands in separate panes - Debugging devcontainer build/up operations - Working with multiple panes in parallel

9 0
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results