poteto-mode
poteto-mode is a skill in michael-denyer/pstack-claude, last changed 20 Nov 2026. It can change agent settings, run shell commands, reach the network, name web addresses and bundle scripts — read the findings before installing.
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.
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 97d2ba2 · 20 Nov 2026
How the check worksPattern check: nothing flagged
That isn't proof the skill is harmless.
QAI Index
We rate every listed skill the same way, from 0 to 100.
A guide to compare by, not a verdict on the skill.
How it's scoredGet an email when its check changes.
Keep it with the other skills you use, installed with one command.
Install
Sign in to see how to install it
Free with Google or an email link, no password needed. Then pick your agent and copy its steps.
What it can touch
Sign in to see the file and line behind each one
The summary at the top stays open to everyone. Signing in is free, with Google or an email link.
Pattern check
Pattern check: nothing flagged · commit 97d2ba2 · 20 Nov 2026
We checked every text file in this skill, at commit 97d2ba2 on 20 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
Outside links we did not follow
- https://code.claude.com/docs/en/tools-reference#task-tool-availability
- https://github.com/cursor/plugins/tree/e46364b8be46000b7df0f260550cd712afbb8d36/pstack
- https://github.com/cursor/plugins/tree/3fe2823ce17c1656c222d4b7c59d3f82fbf20143/pstack
- https://github.com/cursor/plugins/tree/4612556/pstack
- https://github.com/cursor/plugins/tree/7314f72/pstack
- https://github.com/cursor/plugins/tree/e46364b8be46000b7df0f260550cd712afbb8d36/cursor-team-kit
- https://github.com/cursor/plugins/tree/118e73b0e196e4d49d5aade7ce6dd8985a621f68/thermos
- https://github.com/michael-denyer/pstack-claude/blob/main/NOTICE.md
- https://github.com/michael-denyer/pstack-claude/blob/main/CHANGES.md
- https://github.com/michael-denyer/pstack-claude/blob/main/tools/forks.json
Show 7 more
- https://cli.github.com/manual/gh_pr_merge
- https://docs.github.com/en/graphql/reference/pulls
- https://docs.github.com/en/rest/pulls/pulls#merge-a-pull-request
- https://bun.sh
- https://github.com/owner/repo/pull/1
- https://github.com/$
- https://api.github.com/graphql
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 format our Agent Skills docs set out, 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: playbooks/authoring-a-skill.md (linked only from references/copilot-tools.md), playbooks/autonomous-run.md, playbooks/autopilot-full.md, playbooks/autopilot-stack.md (linked only from references/merge-safety.md), playbooks/babysit.md and 19 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/agy-tools.md (101 lines), references/bugbot-triage.md (143 lines), references/codex-tools.md (111 lines), references/copilot-tools.md (145 lines), references/muse-tools.md (106 lines) and 1 more. B5
Fix: Add a short list of the sections at the top of each.
- Note
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: playbooks/authoring-a-skill.md (linked only from references/copilot-tools.md), playbooks/autonomous-run.md, playbooks/autopilot-full.md, playbooks/autopilot-stack.md (linked only from references/merge-safety.md), playbooks/babysit.md and 19 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/agy-tools.md (101 lines), references/bugbot-triage.md (143 lines), references/codex-tools.md (111 lines), references/copilot-tools.md (145 lines), references/muse-tools.md (106 lines) and 1 more. B5
Fix: Add a short list of the sections at the top of each.
- Note
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: playbooks/authoring-a-skill.md (linked only from references/copilot-tools.md), playbooks/autonomous-run.md, playbooks/autopilot-full.md, playbooks/autopilot-stack.md (linked only from references/merge-safety.md), playbooks/babysit.md and 19 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/agy-tools.md (101 lines), references/bugbot-triage.md (143 lines), references/codex-tools.md (111 lines), references/copilot-tools.md (145 lines), references/muse-tools.md (106 lines) and 1 more. B5
Fix: Add a short list of the sections at the top of each.
- Note
- OpenAI (Codex & API)Passes
- VS Code & CopilotPasses
SKILL.md
Files
83 files
Show 63 more
Changelog
Newest first: each commit that changed its folder on GitHub, and each change to its listing here.
- Updated: Release 0.9.146 (#493) (97d2ba2 (opens in a new tab))
- Updated: Add --expect-app so watch-pr waits on a CI app's queued check suite (… (6904a7c (opens in a new tab))
- Updated: Stop watch-pr on the first read when a Claude Code cloud session refu… (37db305 (opens in a new tab))
- Updated: Map reflect's copy destinations to OMP's skill folders (#489) (ed29cc8 (opens in a new tab))
- Updated: Add skills-only DeepSeek Harness support (#429) (946a30c (opens in a new tab))
- Updated: Verify and attribute watch-pr check suite evidence; release 0.9.144 (… (1cadabb (opens in a new tab))
- Updated: Treat setext and tab-separated headings as headings in check-playbook… (25128ed (opens in a new tab))
- Updated: Block watch-pr on approval-gated Actions beside other checks (#473) (412990b (opens in a new tab))
- Updated: Write generated project skills to .omp/skills/ on OMP (#469) (139a9bf (opens in a new tab))
- Updated: Anchor playbook changes on paragraphs when a base has no numbered ste… (dbc378f (opens in a new tab))
- Updated: Stop watch-pr reading approval-gated fork CI as no CI (#460) (c944321 (opens in a new tab))
- Updated: Sync to upstream 2f87c85 (v0.15.43): shorter skills, worker.md, one-f… (e36d113 (opens in a new tab))
- Updated: Fix worktree cleanup, Pi resume, and playbook validation, and update … (f1209c0 (opens in a new tab))
- Updated: Read quoted and flow-list frontmatter in check-playbooks (#455) (f496834 (opens in a new tab))
- Updated: Show behind and diverged remotes in the worktree audit (#453) (36f4336 (opens in a new tab))
- Updated: Read project playbooks from ~/.agents/playbooks/ too (0.9.136) (#454) (d6d7788 (opens in a new tab))
- Updated: fix(worktree-audit): include compressed Codex rollouts in activity ch… (bc09365 (opens in a new tab))
- Updated: feat(pi): run fable on Fable 5.2 and make Pi 1.5.1 the oldest support… (a691bd3 (opens in a new tab))
- Updated: fix(codex): resolve effort from the selected rollout (#432) (ba33373 (opens in a new tab))
- Updated: test(watch-pr): move the port's own cases into port-only test files (… (42fcb61 (opens in a new tab))
- Updated: fix(tools): run validate-skills and sync when their path crosses a sy… (09835d6 (opens in a new tab))
- Updated: fix(pstack): add a focused bug-fix path and clearer handoffs (#438) (340961f (opens in a new tab))
- Listed on QAI
Copies
These share its SKILL.md or its name and description but not all its files, so we list them separately.
QAI Index badge
Show this skill's QAI Index in a README or on a website. It links back to this page and changes when we refresh the catalog.
[](https://qai.io/skills/michael-denyer/pstack-claude/poteto-mode)More from michael-denyer/pstack-claude
Other Writing & content skills
Same category, most repo stars first.