oma-brainstorm

first-fluke/oh-my-agentOther

oma-brainstorm is a skill in first-fluke/oh-my-agent, last changed 1 Nov 2026. It can run shell commands.

From the author
Explore goals, constraints, and alternative approaches before choosing a design. Use when the user requests ideation or design exploration.

At a glance

What it can touch

How much a skill can do, not whether it is risky.

Pattern check

Nothing flagged

That isn't proof the skill is harmless.

Commit 7b96e4b · 3 Nov 2026

How the check works

Pattern check: nothing flagged

That isn't proof the skill is harmless.

Install

Each tab says whether it installs commit 7b96e4b, the one we checked, or the latest version.

Read SKILL.md first
MIT
Licence
1.4k
Repo stars
Publisher

What it can touch

From the files and frontmatter at commit 7b96e4b. This is how much a skill can do, not whether it is risky.

  • Runs shell commands

    Its instructions or files give the agent commands to run on your computer.

Pattern check

Pattern check: nothing flagged · commit 7b96e4b · 3 Nov 2026

We checked every text file in this skill, at commit 7b96e4b on 3 Nov 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

  • Agent Skills specPasses

    The open format from agentskills.io, held to the strictest version of each rule among the agents we check.

    • Note

      There is no license field, so readers can't tell whether they may reuse the skill. O2

      Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.

    • Note

      Reference files that SKILL.md doesn't link: references/_shared/conditional/experiment-ledger.md, references/_shared/conditional/exploration-loop.md, references/_shared/conditional/quality-score.md, references/_shared/core/api-contracts/template.md, references/_shared/core/common-checklist.md and 10 more. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: references/_shared/runtime/memory-protocol.md (119 lines) and resources/triz-lite.md (118 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • Claude CodePasses

    Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.

    • Note

      Reference files that SKILL.md doesn't link: references/_shared/conditional/experiment-ledger.md, references/_shared/conditional/exploration-loop.md, references/_shared/conditional/quality-score.md, references/_shared/core/api-contracts/template.md, references/_shared/core/common-checklist.md and 10 more. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: references/_shared/runtime/memory-protocol.md (119 lines) and resources/triz-lite.md (118 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • Claude apps & API uploadPasses

    Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

    • Note

      Reference files that SKILL.md doesn't link: references/_shared/conditional/experiment-ledger.md, references/_shared/conditional/exploration-loop.md, references/_shared/conditional/quality-score.md, references/_shared/core/api-contracts/template.md, references/_shared/core/common-checklist.md and 10 more. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: references/_shared/runtime/memory-protocol.md (119 lines) and resources/triz-lite.md (118 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • OpenAI (Codex & API)Passes
  • VS Code & CopilotPasses

SKILL.md

Files

22 files

PathSize
SKILL.md (opens in a new tab)11.5 KB
references/_shared/conditional/experiment-ledger.md (opens in a new tab)2.2 KB
references/_shared/conditional/exploration-loop.md (opens in a new tab)2.8 KB
references/_shared/conditional/quality-score.md (opens in a new tab)2.9 KB
references/_shared/core/api-contracts/README.md (opens in a new tab)2.4 KB
references/_shared/core/api-contracts/template.md (opens in a new tab)2.1 KB
references/_shared/core/clarification-protocol.md (opens in a new tab)2.3 KB
references/_shared/core/common-checklist.md (opens in a new tab)1.7 KB
references/_shared/core/context-budget.md (opens in a new tab)2.1 KB
references/_shared/core/context-loading.md (opens in a new tab)2.7 KB
references/_shared/core/difficulty-guide.md (opens in a new tab)2 KB
references/_shared/core/execution-policy.md (opens in a new tab)4.6 KB
references/_shared/core/lessons-learned.md (opens in a new tab)2.9 KB
references/_shared/core/prompt-structure.md (opens in a new tab)1.3 KB
references/_shared/core/quality-principles.md (opens in a new tab)1.2 KB
references/_shared/core/session-metrics.md (opens in a new tab)3.6 KB
references/_shared/core/skill-routing.md (opens in a new tab)3 KB
references/_shared/core/test-approach.md (opens in a new tab)2.6 KB
references/_shared/core/vendor-detection.md (opens in a new tab)4.2 KB
references/_shared/runtime/memory-protocol.md (opens in a new tab)4.9 KB
Show 2 more

Copies

These share its SKILL.md or its name and description but not all its files, so we list them separately.

More from first-fluke/oh-my-agent

SkillWhat it can touchPattern checkLicenceUpdated
  • Runs shell commands
Pattern check: Nothing flaggedMIT1 Nov 2026
  • Instructions only
Pattern check: Nothing flaggedMIT28 Oct 2026
  • Instructions only
Pattern check: Nothing flaggedMIT29 Oct 2026
  • Runs shell commands
Pattern check: Nothing flaggedMIT2 Nov 2026
  • Runs shell commands
Pattern check: Nothing flaggedMIT2 Nov 2026
  • Runs shell commands
Pattern check: Nothing flaggedMIT2 Nov 2026
All skills in first-fluke/oh-my-agent

Other Other skills

Same category, most repo stars first.

SkillWhat it can touchPattern checkLicenceUpdated
  • Runs shell commands
  • Reaches the network
  • +1 more
Pattern check: Nothing flaggedMIT20 Oct 2026
dispatching-parallel-agentsUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

obra/superpowers

  • Instructions only

Pattern check: Nothing flaggedMITUpdated 23 Jul 2026

  • Instructions only
Pattern check: Nothing flaggedMIT23 Jul 2026
  • Instructions only
Pattern check: Nothing flaggedMIT27 Sept 2026
  • Names web addresses
Pattern check: Nothing flaggedApache 2.01 Oct 2026
  • Instructions only
Pattern check: Nothing flaggedMIT14 Oct 2026
  • Instructions only
Pattern check: Nothing flaggedMIT14 Oct 2026

Repo facts from GitHub on 3 Nov 2026. Files read at commit 7b96e4b.

QAI did not write these skills and is not affiliated with their authors unless a page says so. Logos and icons belong to their owners and are not a mark of approval. How we check