EvoSkill is an open-source framework that discovers and improves reusable skills and prompts for coding agents by testing variations against failed work and held-out tasks. It is for people evolving agents such as Claude Code, Codex CLI, OpenCode, OpenHands, Goose, and Harbor, and the catalogue entries are two of its agent skills.
Borrowing it
Nothing to install: this file belongs to sentient-agi/EvoSkill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sentient-agi/EvoSkill/main/.claude/skills/brainstorming/SKILL.mdgit clone --depth 1 https://github.com/sentient-agi/EvoSkillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sentient-agi/evoskill/brainstorming)<a href="https://agentmods.dev/skills/sentient-agi/evoskill/brainstorming"><img src="https://agentmods.dev/badge/skills/sentient-agi/evoskill/brainstorming/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sentient-agi/evoskill/brainstorming"><img src="https://agentmods.dev/badge/skills/sentient-agi/evoskill/brainstorming.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 31 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.00834 |
| Opus 5.5 | $0.00016 | $0.00334 |
| Sonnet 5.5 | $0.00008 | $0.00167 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
brainstorming scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Internal Design Thinking
Overview
Structured self-dialogue before answering any question or task. Analyze what's being asked, identify which skills apply, reason through the approach, then execute.
Core principle: Think first, execute second. Map the question to the right skill chain before acting.
The Process
Phase 1: Question Classification
Analyze the question to determine:
- Domain: What subject area does this fall into?
- Data type: What kind of data or input is involved?
- Time scope: Single point, time series, comparison, or not applicable?
- Operation type: Raw lookup, calculation, transformation, generation, analysis?
- Output format: What form should the answer take (number, text, code, list, etc.)?
- Key terms: If the question uses a specific term or method, explicitly state its definition/formula BEFORE proceeding
Phase 2: Skill Selection
Review available skills and determine which apply:
- List all skills currently available in
.claude/skills/ - For each skill, check if it is relevant to the question's domain and operation type
- If multiple skills apply, determine the order they should be chained
Skill chain reasoning:
- "This question requires [X], which maps to skill [Y]"
- "After [Y], I need to apply [Z] for the final transformation"
- "No existing skill covers [W] — proceed with general reasoning"
Phase 3: Approach Design
For the selected skills, map out the execution path:
- Data retrieval: Where does the relevant data live? What search patterns to use?
- Transformations: What processing or conversions are needed?
- Analysis: What computation, reasoning, or synthesis is required?
- Formula verification (if applicable):
- Write out the exact formula to be used
- Verify it matches the standard definition of the term in the question
- Confirm units and dimensions are consistent throughout
- Validation: How will you verify intermediate results are correct?
- Output: What format does the question expect?
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 108 lines · 40 tokens per session scan A 373b56084a7f
brainstorming is a skill published in the GitHub repository sentient-agi/EvoSkill (1,285 stars, last pushed 11d ago), licensed Apache-2.0. It adds 40 tokens to every session and 834 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
brainstorming compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| brainstormingsentient-agi/EvoSkill | Skill | 1.3k | 11d ago | Apache-2.0 | A | 40 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |