New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Poteto Mode

by sreichholf in sreichholf/dreamDroid

Lauren Tan-inspired rigorous engineering mode for concise communication, deliberate decomposition, simple code, independent review when available, and runtime verification.

GPL-3.0Auto-check passed

Install Poteto Mode

skills CLI
$ npx skills add sreichholf/dreamDroid --skill poteto-mode -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sreichholf/dreamDroid poteto-mode --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sreichholf/dreamDroid.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/poteto-mode .claude/skills/poteto-mode && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
poteto-mode
GitHub stars
116
Token cost
~2k tokens
SKILL.md length
955 words
Files
24
Skills in repo
12
Repo updated
First seen
Licence
GPL-3.0

At a glance

Lauren Tan-inspired rigorous engineering mode for concise communication, deliberate decomposition, simple code, independent review when available, and runtime verification.

  • Works in 10 steps: Classify before acting. Match the… → Name the data shape before non-trivial… → Resolve empirical forks empirically. If… → …
  • Non-trivial engineering tasks
  • SKILL.md covers Non-negotiables, Capability behavior, Routing and Execution, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Poteto Mode is an agent skill from sreichholf/dreamDroid. Lauren Tan-inspired rigorous engineering mode for concise communication, deliberate decomposition, simple code, independent review when available, and runtime verification. Use for non-trivial engineering tasks or when the user asks for Poteto Mode/pstack-style rigor.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 24 other files (for example `playbooks/authoring-a-skill.md`, `playbooks/autonomous-run.md` and `playbooks/autopilot-full.md`).

The repository describes itself as: DreamDroid is an open-source enigma2 client for android based devices. The licence is GPL-3.0.

When your agent uses it

  • Non-trivial engineering tasks
  • The user asks for Poteto Mode/pstack-style rigor

Example prompts

  • “/poteto-mode”

Workflow steps

10 steps, taken from the first numbered list in SKILL.md.

  1. Classify before acting. Match the request to one playbook below. For large cross-cutting work with no clean match, use figure-it-out. For…
  2. Name the data shape before non-trivial code. Load principle-model-the-domain when state/branching makes this meaningful.
  3. Resolve empirical forks empirically. If a reversible question can be answered by running a prototype or inspecting evidence, do that…
  4. Cross a boundary deliberately. Load architect before a non-trivial interface/module/process boundary changes.
  5. Use parallelism only when it is real. arena, swarm, and interrogate may use isolated delegate workers. When the host lacks isolation, run…
  6. Own delegated work. Review artifacts and evidence yourself. A worker's "done" is not proof.
  7. Finish with the real proof. Load principle-prove-it-works. Verify through the closest consumer-facing artifact available. Name any missing…
  8. Keep the change small. Load deletion/simplicity principles when they affect a concrete choice. Do not apply principles as decorative…
  9. Write plainly. For durable docs load technical-writing; for any prose, apply unslop.
  10. Respect host safety and permissions. Reversible workspace work can proceed. Irreversible/external actions follow the host's policy and the…

What it can do on your machine

Read from SKILL.md and the folder at commit 36f622a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Poteto Mode loads about 2k tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 955 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from sreichholf/dreamDroid at commit 36f622a, republished under its GPL-3.0 licence (© sreichholf). 955 words, ~2,000 tokens.

Download SKILL.mdSave it as .claude/skills/poteto-mode/SKILL.md (or your agent's skills folder). This skill also uses 23 other files; get the full folder from GitHub.
name
poteto-mode
description
Lauren Tan-inspired rigorous engineering mode for concise communication, deliberate decomposition, simple code, independent review when available, and runtime verification. Use for non-trivial engineering tasks or when the user asks for Poteto Mode/pstack-style rigor.

Poteto Mode, portable edition

This skill adapts the core workflow architecture of Lauren Tan's pstack to any capable AI agent. Credit and provenance live in .agents/NOTICE.md.

Non-negotiables

  1. Classify before acting. Match the request to one playbook below. For large cross-cutting work with no clean match, use figure-it-out. For program-scale standing work, use orchestrate.
  2. Name the data shape before non-trivial code. Load principle-model-the-domain when state/branching makes this meaningful.
  3. Resolve empirical forks empirically. If a reversible question can be answered by running a prototype or inspecting evidence, do that instead of asking the human.
  4. Cross a boundary deliberately. Load architect before a non-trivial interface/module/process boundary changes.
  5. Use parallelism only when it is real. arena, swarm, and interrogate may use isolated delegate workers. When the host lacks isolation, run labeled sequential passes and never claim independent consensus.
  6. Own delegated work. Review artifacts and evidence yourself. A worker's "done" is not proof.
  7. Finish with the real proof. Load principle-prove-it-works. Verify through the closest consumer-facing artifact available. Name any missing runtime surface.
  8. Keep the change small. Load deletion/simplicity principles when they affect a concrete choice. Do not apply principles as decorative slogans.
  9. Write plainly. For durable docs load technical-writing; for any prose, apply unslop.
  10. Respect host safety and permissions. Reversible workspace work can proceed. Irreversible/external actions follow the host's policy and the user's authorization.

Capability behavior

Read .agents/PORTABILITY.md when present. Feature-detect run, vcs, delegate, search, observe, and track. Missing capabilities reduce the strength of proof; they never justify fabricating evidence.

Routing

  • investigation: Read-only investigation
  • bug-fix: Bug fix
  • perf-issue: Performance issue
  • hillclimb: Metric hillclimb
  • runtime-forensics: Runtime forensics
  • trace-forensics: Captured trace forensics
  • feature: Feature
  • refactoring: Refactoring
  • prototype: Prototype
  • visual-parity: Visual parity
  • authoring-a-skill: Authoring a skill
  • eval: Skill or prompt evaluation
  • babysit: Drive a PR to merge-ready
  • shipping: Verify and ship
  • autonomous-run: Autonomous run
  • orchestrate: Project orchestration
  • autopilot-full: Independent PR autopilot
  • autopilot-stack: Linear stack autopilot
  • session-pickup: Session pickup
  • pause-safely: Pause safely
  • multi-phase-plan: Multi-phase work
  • worktree-cleanup: Worktree and local-state cleanup
  • opening-a-pr: Open a pull request

The internal opening-a-pr playbook is normally a final step when the task includes creating a PR and the host can do so.

Execution

  1. Read the selected file in playbooks/ completely.
  2. If the host offers a todo/task tracker, copy the playbook steps into it. Otherwise keep a compact checklist in working notes. Skipped steps remain visible with skip: <reason> when they would normally apply.
  3. Load only supporting skills/principles that a concrete step triggers. Avoid loading the entire stack into context.
  4. Execute in verifiable units. For long/autonomous work, load show-me-your-work and maintain a durable checkpoint.
  5. Before finalizing code, run the smallest relevant targeted checks and then the broader checks justified by blast radius.
  6. Answer with impact first, then key implementation/design choices, verification evidence, and unresolved gaps. Do not forward raw worker summaries.
Show full SKILL.md (483 more words)Show less

Principle index

Load a leaf skill only when its rule changes a decision in this task.

  • principle-laziness-protocol: Bias toward deletion and the smallest change that fully solves the problem.
  • principle-foundational-thinking: Choose the core data structures, ownership, and sequencing first so downstream logic becomes simpler.
  • principle-redesign-from-first-principles: Design the shape you would choose if the requirement had existed from day one, then migrate toward that shape.
  • principle-attack-the-premise: Inventory who actually owns or exhibits the imbalance, then challenge the shared premise before writing another patch.
  • principle-subtract-before-you-add: Remove dead weight and obsolete paths first; build on the simpler remaining system.
  • principle-minimize-reader-load: Reduce indirection, mutable scope, and one-caller abstractions until the causal path is easy to hold in one mind.
  • principle-outcome-oriented-execution: Converge on the target architecture rather than preserving temporary compatibility states as permanent complexity.
  • principle-experience-first: Optimize for the end-user experience unless the cost violates an explicit constraint.
  • principle-exhaust-the-design-space: Build a few materially different cheap prototypes and compare evidence before committing to one design.
  • principle-build-the-lever: Prefer a script, codemod, generator, benchmark, or verifier that performs or proves the work repeatably over hand edits.
  • principle-model-the-domain: Encode the domain in the right structure: state machine, typed model, table, registry, reducer, boundary, or collection instead of scattered conditionals.
  • principle-boundary-discipline: Validate and normalize at boundaries, trust internal invariants, and keep business logic free of adapter noise.
  • principle-type-system-discipline: Make invalid states hard or impossible to represent and parse external primitives into meaningful internal types at the edge.
  • principle-make-operations-idempotent: Design repeated execution to converge on the same correct end state rather than multiplying side effects.
  • principle-migrate-callers-then-delete-legacy-apis: Move callers to the new shape and delete the old path in the same migration wave instead of carrying a compatibility layer.
  • principle-separate-before-serializing-shared-state: Eliminate unnecessary sharing or partition ownership before adding locks, queues, or coordination.
  • principle-prove-it-works: Verify the requested behavior against the real artifact or surface whenever possible; a proxy check only proves the proxy.
  • principle-fix-root-causes: Reproduce the symptom, trace causality until one mechanism explains it, and fix that mechanism rather than compensating for downstream effects.
  • principle-sequence-verifiable-units: Break work into small units that each end with a proof and order delivery so every next unit builds on verified state.
  • principle-test-behavior-not-implementation: Call the system the way its consumer does and assert meaningful observable output; avoid mocks or assertions that only mirror internal calls.
  • principle-guard-the-context-window: Route bulk exploration to isolated workers or files and bring back compact evidence summaries, not raw floods.
  • principle-never-block-on-the-human: Run the experiment or make the reversible best-effort change, then show the result. Ask only for genuine preference, authority, or irreversible decisions.
  • principle-encode-lessons-in-structure: Turn recurring guidance into a type, lint, test, metadata flag, generator, runtime check, or skill so the system carries the lesson.

Autonomy

Prefer action over clarification for reversible work whose correct answer can be observed. Ask when the missing input is genuinely subjective, authoritative, security-sensitive, or required for an irreversible action. A recommendation may be "no" when added scope does not earn its complexity.

© sreichholf, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 23 other files in .agents/skills/poteto-mode of sreichholf/dreamDroid.

  • SKILL.md
  • playbooks/authoring-a-skill.md
  • playbooks/autonomous-run.md
  • playbooks/autopilot-full.md
  • playbooks/autopilot-stack.md
  • playbooks/babysit.md
  • playbooks/bug-fix.md
  • playbooks/eval.md
  • playbooks/feature.md
  • playbooks/hillclimb.md
  • playbooks/investigation.md
  • playbooks/multi-phase-plan.md
  • playbooks/opening-a-pr.md
  • playbooks/orchestrate.md
  • playbooks/pause-safely.md
  • playbooks/perf-issue.md
  • playbooks/prototype.md
  • playbooks/refactoring.md
  • playbooks/runtime-forensics.md
  • playbooks/session-pickup.md
  • … and 4 more

Open the folder on GitHubat commit 36f622a

Compare with similar skills

Poteto Mode next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Poteto Mode compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Poteto Mode this skillsreichholf/dreamDroid116—~2kAutomated safety check: PassGPL-3.0
Communicating ConciselyGanyuanRan/Aegis1.3k1 repos~556Automated safety check: PassMIT
How To Communicatedatabasus/databasus8.8k—~3.9kAutomated safety check: PassMIT
Twilio Communicationssickn33/agentic-awesome-skills47k2 repos~453Automated safety check: PassMIT
Internal Communicationsickn33/agentic-awesome-skills47k1 repos~3.4kAutomated safety check: PassMIT
Twilio Communicationsdavila7/claude-code-templates32k5 repos~2.3kAutomated safety check: PassMIT

Similar skills

  • Communicating Concisely

    GanyuanRan/Aegis

    A skill your agent uses when the user asks for caveman mode, fewer tokens, brief responses, compressed communication, or otherwise explicitly requests a much shorter answer.

    1.3k GitHub starsUsed in 1 repo~556 tokens
    DevelopmentAuto-check passed

  • How To Communicate

    databasus/databasus

    Communicate clearly in every response, progress update and agent-authored document.

    8.8k GitHub stars~3.9k tokensUpdated 17 days ago
    DatabasesAuto-check passed

  • Twilio Communications

    sickn33/agentic-awesome-skills

    Build communication features with Twilio: SMS messaging, voice calls, WhatsApp Business API, and user verification (2FA).

    47k GitHub starsUsed in 2 repos~453 tokens
    Backend & APIsAuto-check passed

  • Internal Communication

    sickn33/agentic-awesome-skills

    Internal communication log: title, type, date, department, host and attendees, agenda, action items, follow-up date, meeting link and delivery status.

    47k GitHub starsUsed in 1 repo~3.4k tokens
    Writing & ContentAuto-check passed

  • Twilio Communications

    davila7/claude-code-templates

    Build communication features with Twilio: SMS messaging, voice calls, WhatsApp Business API, and user verification (2FA).

    32k GitHub starsUsed in 5 repos~2.3k tokens
    Backend & APIsAuto-check passed

  • Team Communications

    alirezarezvani/claude-skills

    Write internal company communications — 3P updates (Progress/Plans/Problems), company-wide newsletters, FAQ roundups, incident reports, leadership updates, status reports, project updates, and…

    28k GitHub stars~1.1k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed

More from sreichholf/dreamDroid

All 12 skills in this repo

  • Verify Dreamdroid

    sreichholf/dreamDroid

    Prove dreamDroid phone UI. An agent skill from sreichholf/dreamDroid.

    116 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Principle Never Block On The Human

    sreichholf/dreamDroid

    Run the experiment or make the reversible best-effort change, then show the result.

    116 GitHub stars~235 tokensUpdated today
    Auto-check passed

  • Architect

    sreichholf/dreamDroid

    Settle data shapes, ownership, boundaries, and interfaces before code crosses a function/module boundary.

    116 GitHub stars~224 tokensUpdated today
    Auto-check passed

  • Arena

    sreichholf/dreamDroid

    Spawn parallel candidate implementations for the same task, cross-judge, and graft the best parts into the winning base.

    116 GitHub stars~273 tokensUpdated today
    Auto-check passed

  • Automate Me

    sreichholf/dreamDroid

    Create a personal mode skill from recurring workflow patterns in available history.

    116 GitHub stars~208 tokensUpdated today
    Auto-check passed

  • Create Verification Skill

    sreichholf/dreamDroid

    Generate a project-local verification skill that drives the real app and captures evidence.

    116 GitHub stars~205 tokensUpdated today
    Auto-check passed

Questions about Poteto Mode

What does Poteto Mode do?

Lauren Tan-inspired rigorous engineering mode for concise communication, deliberate decomposition, simple code, independent review when available, and runtime verification. Poteto Mode is an agent skill from sreichholf/dreamDroid. Lauren Tan-inspired rigorous engineering mode for concise communication, deliberate decomposition, simple code, independent review when available, and runtime verification.

When should I use Poteto Mode?

Poteto Mode fits situations like: non-trivial engineering tasks; the user asks for Poteto Mode/pstack-style rigor.

How do I install Poteto Mode in Claude Code?

Run `npx skills add sreichholf/dreamDroid --skill poteto-mode -a claude-code`. Or copy the skill folder (.agents/skills/poteto-mode in sreichholf/dreamDroid) into .claude/skills/poteto-mode in your project. Claude Code loads it when a task matches its description.

How do I install Poteto Mode in Codex?

Run `npx skills add sreichholf/dreamDroid --skill poteto-mode -a codex`. Or copy the skill folder (.agents/skills/poteto-mode in sreichholf/dreamDroid) into .agents/skills/poteto-mode in your project. Codex loads it when a task matches its description.

Can I use Poteto Mode in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sreichholf/dreamDroid --skill poteto-mode -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/poteto-mode, .gemini/skills/poteto-mode, .github/skills/poteto-mode and .opencode/skills/poteto-mode in your project.

What does Poteto Mode need to run?

SKILL.md names no scripts, command-line tools or credentials: Poteto Mode is instructions for the agent only.

Does Poteto Mode access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Poteto Mode safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Poteto Mode use?

Poteto Mode is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Poteto Mode use?

About 2k tokens (SKILL.md is roughly 8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Poteto Mode?

Skills that share tags, products or a category with Poteto Mode: Communicating Concisely (GanyuanRan/Aegis, 1.3k stars), How To Communicate (databasus/databasus, 8.8k stars), Twilio Communications (sickn33/agentic-awesome-skills, 47k stars) and Internal Communication (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Poteto Mode?

sreichholf (a GitHub user) maintains it in sreichholf/dreamDroid, which has 116 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 9, 2026.

Source: sreichholf/dreamDroid on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.