oh-my-stack

Ground a nontrivial design, compare distinct caller-first type and module sketches, then implement within scope and redesign when evidence contradicts the shape.

Compare independent candidates for the same artifact, cross-judge them, select a base, integrate stronger ideas, and verify the result.

Create or revise a scoped, discoverable Skill and validate that its instructions change useful decisions.

Turn a user's recurring working conventions into a concise personal mode Skill with evidence and review.

Drive one bounded engineering task through evidence-based iterations to a fixed predicate without stopping for routine intermediate prompts.

Run an explicitly authorized queue through one-owner-per-change build, independent root verdict, and owner-executed landing until its bounded completion predicate is reached.

Build, independently verify, and arrange an authorized queue as one linear reviewable change stack while reserving every landing decision for the operator.

Inspect or drive a pull request toward merge-ready while keeping status checks, repair authority, and merge authority separate.

Find downstream breakage a diff may cause and prove its load-bearing safety assumptions against real code.

Restate the assistant's immediately preceding message in clear, concise, everyday language.

Diagnose and fix a reproducible software defect with bounded scope, same-surface evidence, and independent root verification.

Create a project-local Skill that launches and drives the real user surface, captures evidence, and cleans up safely.

Run a blinded, repeatable comparison of workflow or model variants using real artifacts and a frozen rubric.

Add or intentionally change behavior through an evidence-backed design, bounded implementation, and matching-surface verification.

Design and execute an auditable plan for a complex task that lacks a narrower workflow.

Improve one measurable outcome through bounded, single-change experiments against a frozen harness.

Explain how a code path or subsystem works through evidence-backed exploration and a verified architectural walkthrough.

Run an adversarial multi-session review with identical inputs, frozen findings, independent synthesis, and root-owned judgment.

Answer a read-only engineering question from repository evidence without changing implementation files.

Audit a project verification Skill against source and live user paths, correcting proven drift in its own files.

Build a local control page that submits validated actions to an authenticated webhook, with optional private-network access.

Write a reviewable dependency plan with verifiable units, owner boundaries, live checks, and explicit execution gates.

Review comments and suppressions in a scoped diff, remove redundant ones, and encode real constraints in structure where feasible.

Prepare and, only when explicitly requested, publish a reviewed branch as a ready pull request with verified scope and evidence.

Coordinate a standing multi-session engineering program through durable briefs, bounded rolling work, independent verification, and a continuously safe integration frontier.

Stop explicitly requested in-flight engineering work at a durable boundary and leave a checkpoint another session can validate and resume.

Fix one performance defect using representative before and after traces and a correctness gate.

Route a software-engineering request to the smallest admitted Oh My Stack workflow while preserving root ownership and evidence boundaries.

Apply when two or more fixes that share one premise have failed the same gate. Take a census of which actors hold the imbalance before the next fix, then question the premise instead of writing another fix that assumes it.

Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.

Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.

Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.

Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.

Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.

Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.

Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious.

Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.

Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.

Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.

Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibility layers.

Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.

Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.

Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.

Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.

Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'

Apply when integrating a new requirement into an existing design. Redesign as if the requirement had been a foundational assumption from day one, instead of bolting it on.

Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.

Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.

Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.

Apply when you write, change, or keep a test. Call the code the way its users do and assert the result they observe against a literal expected value. If the test would still pass when every imported function returns undefined, rewrite the assertion or delete the test.