Skip to content

Jrecos/omp-pstack / skills/poteto-mode

poteto-mode

Unverified

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.

FileKindSize
SKILL.mdskill md25.2 KB
playbooks/authoring-a-skill.mdmarkdown829 B
playbooks/autonomous-run.mdmarkdown2.1 KB
playbooks/autopilot-full.mdmarkdown6.9 KB
playbooks/autopilot-stack.mdmarkdown877 B
playbooks/babysit.mdmarkdown8.3 KB
playbooks/bug-fix.mdmarkdown2.3 KB
playbooks/eval.mdmarkdown2.6 KB
playbooks/feature.mdmarkdown7.0 KB
playbooks/hillclimb.mdmarkdown4.3 KB
playbooks/investigation.mdmarkdown928 B
playbooks/multi-phase-plan.mdmarkdown14.0 KB
playbooks/opening-a-pr.mdmarkdown6.6 KB
playbooks/orchestrate.mdmarkdown4.8 KB
playbooks/pause-safely.mdmarkdown1.8 KB
playbooks/perf-issue.mdmarkdown1.4 KB
playbooks/prototype.mdmarkdown2.1 KB
playbooks/refactoring.mdmarkdown3.4 KB
playbooks/runtime-forensics.mdmarkdown1.3 KB
playbooks/session-pickup.mdmarkdown2.2 KB
playbooks/shipping.mdmarkdown5.9 KB
playbooks/trace-forensics.mdmarkdown1.8 KB
playbooks/visual-parity.mdmarkdown1.2 KB
playbooks/worktree-cleanup.mdmarkdown3.6 KB
references/bugbot-triage.mdmarkdown9.4 KB
references/omp-control-cli.mdmarkdown6.2 KB
references/omp-control-ui.mdmarkdown7.0 KB
references/omp-create-skill.mdmarkdown3.6 KB
references/omp-deslop.mdmarkdown1.1 KB
scripts/check-plan.mjsexecutablescript8.1 KB
scripts/check-plan.test.tsscript4.0 KB
scripts/watch-pr/cli.test.tsscript6.0 KB
scripts/watch-pr/cli.tsscript6.8 KB
scripts/watch-pr/fakes.test-helper.tsscript3.3 KB
scripts/watch-pr/github.test.tsscript15.8 KB
scripts/watch-pr/github.tsscript25.0 KB
scripts/watch-pr/policy.test.tsscript17.6 KB
scripts/watch-pr/policy.tsscript25.5 KB
scripts/watch-pr/render.tsscript7.2 KB
scripts/watch-pr/tsconfig.jsonconfig270 B
scripts/watch-pr/types.compile.tsscript2.2 KB
scripts/watch-pr/types.tsscript12.7 KB
scripts/watch-pr/watch-prexecutablescript906 B
scripts/worktree-audit.tsexecutablescript21.9 KB

playbooks/eval.md

View on GitHub
### Eval

**You own the experiment design. Plan, blind, run, synthesize.**

**Non-negotiables for blinding:**

- No `eval`, `test`, `judge`, `experiment`, `rubric`, `score`, `compare`, `benchmark`, `candidate`, or `arena` in any directory, file, or prompt the candidate sees.
- The candidate prompt looks like an organic user request. State the goal, not the meta.
- No chain-eliciting cues. Don't ask the candidate to list which skills, principles, or files they applied. Ask for design notes generally and grade chain-following from code shape, not self-report.
- Sanitize directory and slug names. Use project-shaped names a user might pick.
- Don't tell the candidate other candidates exist.
- The judge can know it's judging but sees outputs by sanitized label only, never by model name.
- Comparing two variants: one judge scores both sets in a single pass on one scale, blind to which set each came from.

**Steps:**

1. **Frame.** State what variant is under test and what behavior counts as success. Write the rubric (3-6 concrete criteria) for the judge only. Hold it back from candidates.
2. **Set up sanitized environments.** Per-candidate working dir with the variant in place. Plant any context an organic task would have: a project skeleton, the skills the candidate would naturally read.
3. **Author one organic prompt.** What a user would type. No leakage of what's being measured.
4. **Spawn N parallel candidates** on different models per the **arena** skill's Phase B. Each works in its own sanitized dir. Same prompt to each. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section.
5. **Spawn one blinded judge** on a different model family per the **arena** skill's Phase C. Judge sees outputs by sanitized label and the rubric, never a model name.
6. **Verify the chain from transcripts, not self-report.** Read each candidate's session with the native `pstack_history` tool (`read` with that candidate's `sessionId`). It reads only the selected workspace; do not glob across agent-profile session dirs; that crosses workspace boundaries and reads private chats from unrelated projects. Look at which files each candidate actually opened. Grade chain-following from the files it really read plus the shape of the code, never from the candidate's own claims.
7. **Read every candidate output yourself** end to end. Compare to the judge's verdict. Disagreement means a model is biased or the rubric is ambiguous. Synthesize.

**Reply:** variant under test, rubric, per-candidate notes, judge's verdict, your synthesis, and a recommendation for whether to promote the variant.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall