Claude Skills by tstapler

Wine dynamic tracing tool skill. Use when tracing Win32 API calls from a Windows binary running under Wine: WINEDEBUG relay logging, WineDbg, GDB attach to Wine process, observing file access, network connections, registry reads, DLL load order, or SEH. Called from code-reverse-engineering-binary (Phase 4) and code-re-qt5 (Phase 3).

Use when receiving code review feedback, before implementing suggestions,

Format professional references properly and prepare reference materials

Use when completing tasks, implementing major features, or before merging

Optimize resumes for Applicant Tracking Systems, check ATS compatibility, and analyze keyword match

Transform weak resume bullets into achievement-focused statements with metrics and impact

Ensure ATS-friendly formatting and create clean scannable layouts

Find opportunities to add metrics and estimate numbers when exact data unavailable

Create targeted resume sections optimized for different experience levels and roles

Customize resume for specific job postings while maintaining truthfulness

Track different resume versions, maintain master resume, manage tailored versions

Methodically decompose existing code and projects to extract architectural

How to research community reviews and longevity signals for a physical product — where to look, how to weigh sponsored vs. organic sources, and how to read warranty/repairability/failure-mode signals as durability proxies. Use as a sub-step inside a larger research or product-selection process, not as a standalone entry point.

Hub skill for Rust development. Covers the full workflow from profiling → performance diagnosis → CPU/memory optimization → parallelism. Routes to the right specialist skill based on the symptom. Links all four Rust skills: rust-profiling, rust-perf-tuning, rust-memory-optimization, rust-parallel-processing.

Idiomatic review for Rust — async/Tokio daemon design, ports-and-adapters trait boundaries, and thiserror/anyhow error handling. Use when reviewing or writing Rust code that defines async trait "ports" (dependency-inversion boundaries), runs a single-threaded Tokio daemon (current_thread runtime + LocalSet/spawn_local), or crosses a wire/domain type boundary. Covers async fn in traits vs async-trait, Rc/RefCell vs Arc/Mutex, tokio::select! cancel-safety, blocking calls in async context, thise...

Reduce Rust memory usage, eliminate allocation churn, size types precisely, apply custom allocators and arenas, build bounded telemetry buffers, and detect leaks. Covers the full cycle: measure → diagnose → fix → verify. Companion to rust-profiling (CPU flamegraphs) and rust-perf-tuning (CPU throughput).

Exploit CPU, GPU, and multi-machine parallelism in Rust. Covers rayon (data parallelism), tokio (task/async parallelism), SIMD (auto-vectorization + wide crate), wgpu/cudarc/candle (GPU compute and ML), tonic/tarpc/quinn (multi-machine RPC), MPI/ractor/DataFusion (HPC and distributed), algorithm patterns (map-reduce, pipeline, work-stealing, SPMD), profiling parallel programs, and common anti-patterns. Companion to rust-profiling (collect data first) and rust-perf-tuning (single-core fixes).

Diagnose Rust performance bottlenecks from profiling data and apply targeted optimizations. Covers the full cycle: measure → profile (see rust-profiling skill) → diagnose → fix → verify. Includes pattern-matched fixes for common flamegraph hotspots, allocation elimination, data layout, compiler settings, and parallelism tuning.

Profile Rust binaries and benchmarks using cargo-flamegraph, samply, perf, and heaptrack. Covers CPU flamegraphs, collapsed stacks for LLM analysis, memory profiling, criterion benchmark profiling, and interactive Firefox Profiler UI.

Research market rates, build negotiation strategy, and create counter-offer scripts

Phase 1 — Interview to capture requirements. Outputs: project_plans/<project>/requirements.md

Phase 2 — Parallel research across 6 dimensions. Outputs: project_plans/<project>/research/*.md

Phase 3 — Architecture + task breakdown. Outputs: project_plans/<project>/implementation/plan.md

Phase 4 — Map test coverage to requirements + run pre-mortem before writing any code. Outputs: validation.md + pre-mortem.md in project_plans/<project>/implementation/

Phase 5 — Execute plan via parallel worker subagents. Requires a fresh session (see below).

Phase 6 — Dynamic idiom review, architecture review, refactor pass, then correctness + test gate before shipping.

Phase 7 — Create the PR and drive it to merge-ready via github:pr-ship.

Capture an architecture decision record

Maintenance shortcut — pick highest priority bug, find root cause, fix, verify

Maintenance shortcut — rank refactor candidates by complexity × churn, refactor the top one, verify

Full SDD workflow — ideate → research → plan → validate → implement → verify → ship. Planning runs in subagents; no fresh session required.

One-shot workflow for simple tasks and bug fixes that fit in a single context window. Skips artifacts and fresh-session requirements.

Show current SDD phase and the next command to run

Compare two Claude Code sessions by path or name. Extracts duration, model, all token buckets, estimated cost, human turns, tool calls, files touched, and generates a markdown conversation summary. CLI wrapper around ~/dotfiles/stapler-scripts/session-compare.

Analyze text, commands, or other content to determine if it should be converted to a Claude Agent Skill

Create a new Claude Agent Skill following Anthropic's best practices with prompt engineering guidance

Use this agent to plan software features, gather requirements, design

Apply Spring Boot and Java coding standards when writing, reviewing,

Use this agent when you need expert guidance on Spring Boot testing,

Use this agent when you need expert SQLite database optimization, schema design review, or performance analysis for SQLite-backed applications. This agent should be invoked when reviewing DDL, designing indexing strategies, evaluating WAL/journal configuration, diagnosing write contention, analyzing query plans with EXPLAIN QUERY PLAN, or optimizing ent/GORM ORM usage against SQLite. Covers SQLite-specific constraints that differ materially from PostgreSQL (single-writer, type affinity, limit...

Use when you need to add a new persistent guard, convention, or anti-pattern check to the stapler-squad project. This skill scaffolds a new project skill at .claude/skills/<slug>/SKILL.md with the correct frontmatter and optionally updates CLAUDE.md's reference index.

Desktop UI automation for SteleKit Compose app. Launch app, take screenshots, click buttons, type text, verify UI state. Like playwright but for the SteleKit desktop app. Use when user wants to test SteleKit UI, debug visual issues, verify flows work, or automate desktop interaction.

Best practices for the AWS Strands Agents SDK — structuring prompts,

Execute an implementation plan by dispatching fresh subagents per task with dual-review (spec compliance + code quality). Use when running sdd:5-implement or executing any multi-task implementation plan.

Execute a full bidirectional sync between the personal fork (origin) and the work upstream (upstream-fanatics). Creates a dated integration branch, resolves known conflict patterns, runs CI checks, opens two PRs (fork→upstream and upstream→fork), and monitors until checks pass. Use after /fork-merge-plan or whenever both repos have diverged and need to be brought back in sync.

Optimize resumes for software engineering, PM, and technical roles

Use this agent to improve technical writing clarity, impact, and actionability.

Set up Temporal Cloud and run a sample Workflow on it for the user, doing the work end to end. Use when the user wants to set up Temporal Cloud, get started on Temporal Cloud, install the unified Temporal CLI (prerelease cloud-cli), create a Cloud namespace or API key, clone a money-transfer sample app, write the client config TOML, or connect a local Worker to Temporal Cloud and run a sample Workflow. This is the Cloud setup path, not the local learning path (see temporal-getting-started). C...

Develop, debug, and manage Temporal applications across Python, TypeScript, Go, Java, .NET, Ruby, and Rust. Use when the user is building workflows, activities, or workers with a Temporal SDK, debugging issues like non-determinism errors, stuck workflows, or activity retries, using Temporal CLI, Temporal Server, or Temporal Cloud, or working with durable execution concepts like signals, queries, heartbeats, versioning, continue-as-new, child workflows, or saga patterns. Also use when the user...

Administer and diagnose running Temporal Cloud or self-hosted Temporal Server environments via CLI (temporal, tcld) — not SDK code. Operations: namespace CRUD, Cloud capacity/APS, API-key rotation, mTLS cert rotation, workflow health, batch cancel/terminate/reset, export, search attributes, Ops API, billing, audit logs, Terraform, SAML/SCIM, migration. Diagnosis: bottom-up triage of stuck workflows, non-determinism, worker-health, task-queue problems, HA failover, payload size limits, perform...