cursor__plugins/pstack/skills/poteto-mode/playbooks/feature.md at cursor/add-docusign-mcp-plugin

mirror of https://github.com/cursor/plugins.git synced 2026-09-14 20:00:00 +08:00

Files

T

lauren 3fe2823ce1 pstack: parity sweep with the private skill tree (#156 )

1. hillclimb.md: port steps 1-2 (workload grounding before choosing the
   ruler; harness sensitivity proof before freezing), fold the how-skill
   grounding into step 1 and rewrite step 4 to reference it.
2. refactoring.md: insert missing step 2 (name the structure the code is
   missing per principle-model-the-domain), renumber 3-8, and restore the
   "safety net" framing sentence in the intro.
3. feature.md + poteto-mode SKILL.md: expand the delegation scope and the
   any-code trigger to choose the organizing structure per
   principle-model-the-domain.
4. typescript-best-practices: restore the dropped "Real tests" and
   "Structured telemetry" rules in generic form.
5. poteto-mode Subagents: add the difficulty tiering criteria (judgment vs
   precisely specified vs trivial mechanical) and the setup-pstack rule
   override semantics.
6. One-liner tells ported verbatim into bug-fix, runtime-forensics,
   session-pickup, autonomous-run, and authoring-a-skill.
7. Bug fix: interrogate is "(multi-model adversarial)", not four-model;
   the default panel is three models.
8. Leak fix: drop the dangling databricks-use-dbt-models skill reference
   in why/references/sources/databricks.md.

Plus: arena cross-judge pool role line in setup-pstack, version bump to
0.11.3.

2026-07-13 17:09:30 -07:00

2.9 KiB

Raw Permalink Blame History

Feature

You own the design. Plan, review, verify. Delegate implementation; stay in the lead.

how over the affected subsystem.
architect for parallel design exploration. Skipping stays as architect skipped: <reason>; do not fold the design decision silently into implementation.
Write the throughput checkpoint as four todo items. A dimension that genuinely does not apply (single file, no fan-out) keeps its item with n/a: <reason> rather than being dropped:
- Blocking first steps. Gates run before fan-out.
- Independent workstreams. Disjoint files, services, or layers parallelize. Shared writes serialize.
- Shared mutable state. Default to splitting the target (the separate-before-serializing-shared-state principle skill). Serialize only for real invariants.
- Smallest safe decomposition. If one worker is best, name why.
Delegate code-writing to a subagent using your configured feature model (default grok-4.5-fast-xhigh) with a specific scope (file paths, named data shape and its organizing structure per principle-model-the-domain — a state machine over scattered booleans, a table/registry over branching, a typed model over repeated shape assumptions, chosen before the delegate writes logic — and success criteria); review its diff yourself. When the implementation admits multiple valid shapes (error handling, abstraction layer, test structure), delegate via the arena skill instead so the runners surface the alternatives and the cross-judge guards the pick. Mandatory: no skip-with-reason escape, and Laziness Protocol does not override it (the gain is review separation, not lines saved). You can spawn a subagent even though you are one; "the app is small" and "a subagent cannot spawn one" are both wrong. A subagent forbidden to spawn satisfies this by owning the diff directly with the same review separation; no "standing by" reply that waits on a nested agent. Comments per Comments. Surgical edits, re-ground against the source for upstream-derived files. Port shared-primitive improvements to all consumers and verify each. Commit liberally.
Verify on the matching surface. "Inconclusive" or wrong-surface is not a pass; flag it.
Rebase into small, ordered commits; stack follow-ups. Use the sequence-verifiable-units principle skill, building, verifying, and committing each small unit before the next.
If the design is contested, interrogate before shipping.
Run Opening a PR.

Code-coupled work (one feature, one migration) goes to a single owner with the checkpoint inline; that owner fans out internally after the blocking phase. Parent-level fan-out is for slices that produce independent artifacts (audits, cross-subsystem investigations, competing experiments). Rewrite the checkpoint at phase boundaries; spawn a fresh owner rather than chaining interrupts.

Reply: what you built, what you chose and why, open decisions. Tables for design alternatives.

2.9 KiB Raw Permalink Blame History

Feature

2.9 KiB

Raw Permalink Blame History