Skip to content

0xrsydn/pstack-pi / skills/poteto-mode

poteto-mode

Verified

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 md19.5 KB
playbooks/authoring-a-skill.mdmarkdown991 B
playbooks/autonomous-run.mdmarkdown2.0 KB
playbooks/autopilot-full.mdmarkdown5.0 KB
playbooks/autopilot-stack.mdmarkdown4.5 KB
playbooks/babysit.mdmarkdown8.0 KB
playbooks/bug-fix.mdmarkdown2.6 KB
playbooks/eval.mdmarkdown3.0 KB
playbooks/feature.mdmarkdown2.9 KB
playbooks/hillclimb.mdmarkdown4.4 KB
playbooks/investigation.mdmarkdown1.1 KB
playbooks/multi-phase-plan.mdmarkdown11.0 KB
playbooks/opening-a-pr.mdmarkdown3.3 KB
playbooks/orchestrate.mdmarkdown17.0 KB
playbooks/pause-safely.mdmarkdown1.5 KB
playbooks/perf-issue.mdmarkdown3.4 KB
playbooks/prototype.mdmarkdown2.5 KB
playbooks/refactoring.mdmarkdown3.9 KB
playbooks/runtime-forensics.mdmarkdown1.4 KB
playbooks/session-pickup.mdmarkdown2.1 KB
playbooks/shipping.mdmarkdown4.0 KB
playbooks/trace-forensics.mdmarkdown2.0 KB
playbooks/visual-parity.mdmarkdown1.3 KB
playbooks/worktree-cleanup.mdmarkdown2.7 KB
references/bugbot-triage.mdmarkdown9.5 KB
scripts/bootstrap.tsscript1.7 KB
scripts/bun.lockother6.5 KB
scripts/check-plan.mjsexecutablescript8.0 KB
scripts/check-plan.test.tsscript3.8 KB
scripts/orch/orch.test.tsscript18.0 KB
scripts/orch/orch.tsexecutablescript15.1 KB
scripts/orch/store.tsscript41.9 KB
scripts/package.jsonmanifest371 B
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.tsscript14.4 KB
scripts/watch-pr/policy.tsscript24.8 KB
scripts/watch-pr/render.tsscript6.9 KB
scripts/watch-pr/tsconfig.jsonconfig270 B
scripts/watch-pr/types.compile.tsscript2.2 KB
scripts/watch-pr/types.tsscript12.4 KB
scripts/watch-pr/watch-prexecutablescript211 B
scripts/worktree-audit.shexecutablescript6.2 KB

playbooks/eval.md

View on GitHub
### Eval

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

Evals test how a change affects agent behavior before promoting it: a new skill variant, a structural change, a prompt tweak. The failure mode is the observer effect. An agent that knows it's being evaluated behaves differently, so candidates must run blind.

**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. "build me a small todo cli" not "show me how you follow the principles chain".
- No chain-eliciting cues. Don't ask the candidate to list which skills, principles, or files they applied; that meta-prompt inflates citation behavior. 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, not labels like `candidate-1` or `agent-a`.
- 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. Two judge runs with different prompts don't compare, the calibration drifts.

**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.
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 local transcript under the active workspace's `agent-transcripts/` directory (the system prompt names this path). Do not glob across `~/~/.pi/agent/sessions/*/`; that crosses workspace boundaries and reads private chats from unrelated projects. Look at which files each candidate actually opened. Citing a principle is not reading its leaf skill, and reading it is not applying it. 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