generic-automation-and-it/smooth-ai-stockanalysis / .agents/skills/ai-brain-dump
ai-brain-dump
VerifiedStart and run a listen-first braindump session for tickets, issues, ADRs, worktasks, PR descriptions, requirements, designs, or implementation plans. Use when the user says they want to braindump, think out loud, capture rough requirements, or provide context incrementally before asking the agent to synthesize, update a ticket, create docs, or perform implementation work.
| File | Kind | Size |
|---|---|---|
| AGENTS.md | markdown | 1.2 KB |
| README.md | markdown | 4.3 KB |
| SKILL.md | skill md | 8.1 KB |
| agents/openai.yaml | config | 263 B |
AGENTS.md
View on GitHub# ai-brain-dump — AGENTS.md
## TL;DR
Pure-prompt behavioral skill (no scripts): a listen-first capture session whose entire value is in NOT acting — never implement, modify, or synthesize until explicitly asked.
## Non-Negotiables
- **A braindump is never permission to implement.** Even with all switches on, only *grounding* (reading/searching) is widened — the no-modify rule holds until the user asks to synthesize.
- **Don't "optimize" the SKILL.md by deduplicating switch semantics.** The switch rules are intentionally restated in Modes, Listen, and Guardrails — reinforcement against the model's drift toward premature questioning/action is the point, not redundancy.
## Architecture Decisions
- **LADR-001** (2026-05, accepted): Default mode is tool-free, opt-in switches relax it. *Context:* file/web tool payloads are injected into context and re-billed every subsequent turn of a long capture session. *Decision:* default forbids tools; `--oktoreaddocs`/`--oktowebsearch` opt back in. *Consequence:* any edit that adds default tool use destroys the skill's cost profile — see the README cost table before changing switch behavior.
## Changelog
| Date | Change | Ref |
|:-----|:-------|:----|
| 2026-06-12 | Initial version. | |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |