Claude Skills by williamwue

Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation. Use only from the configured Benny triage automation.

Investigate design rationale, historical tradeoffs, regressions, and thresholds using cited history and available evidence sources.

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.

Verify an active delegated worker can be cancelled and its generation excluded from accepted results.

Verify a generated canonical read-only role is discovered and applied to one delegated worker.

Verify one read-only delegated worker, result collection, and independent root verification.

Verify a second read-only instruction continues on the same delegated worker with preserved context.

Verify that a runtime collects one fixed choice and one user-authored value without silently inventing either response.

Verify one delegated worker resolves an explicit alternate model and reasoning setting with observable runtime metadata.

Verify parallel independent candidates, frozen review inputs, and separate review and synthesis sessions.

Verify two independent read-only workers start before waiting and return separately attributable results.

Verify that a packaged Skill can resolve its own references, assets, and executable helper without changing the workspace.

Verify a cancelled worker can later deliver its retained old-generation result without that stale result being accepted.

Verify a root session can retrieve a completed delegated worker transcript independently from its delivered result.

Verify one delegated writer changes only an isolated workspace while a separate observer remains read-only.

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.