Claude Skills by tstapler

Use this agent when you need to diagnose and fix failing Go tests with

Production-ready Golang tests — table-driven tests, testify suites and mocks, parallel tests, fuzzing, fixtures, goroutine leak detection with goleak, snapshot testing, code coverage, integration tests, idiomatic test naming. Use when writing or reviewing Go tests, choosing a testing approach, setting up Go test CI, or debugging flaky/slow tests. For testify-specific APIs see `samber/cc-skills-golang@golang-stretchr-testify`; for measurement methodology see `samber/cc-skills-golang@golang-ben...

Troubleshoot Golang programs systematically - find and fix the root cause. Use when encountering bugs, crashes, deadlocks, races, or unexpected behavior in Go code. Covers debugging methodology, common Go pitfalls, test-driven debugging, pprof setup and capture, Delve, race detection, GODEBUG tracing, and production debugging. Start here for any 'something is wrong' situation. Not for interpreting profiles or benchmarking (→ See `samber/cc-skills-golang@golang-benchmark` skill), applying opti...

Survey a Google Drive's actual folder structure, apply a PARA-lite organization framework, and produce (then safely execute) a concrete reorganization plan — deduping, sweeping root-level clutter, and fixing misnested folders.

Use gritql (grit) for AST-based multi-file code transformations. Use

Engineering-focused project plans with solo work strategies, critical path analysis, professional-grade techniques, pre-work briefing checklists, and ITP-style stage-gate hold points

Structured home project planning workflow (scope → research → plan → prep → execute → close). Use for any home improvement, repair, installation, or maintenance project.

Phase 1 — Interview to scope the home project. Outputs: home_plans/<project>/scope.md

Phase 2 — Parallel research across 4 dimensions. Outputs: home_plans/<project>/research/*.md

Phase 3 — Task breakdown, materials list, and budget. Outputs: home_plans/<project>/plan.md

Phase 4 — Pre-execution readiness gate. Outputs: home_plans/<project>/prep-checklist.md

Phase 5 — Log task completion and track costs during active execution. Updates: home_plans/<project>/execution-log.md

Phase 6 — Close out the project: document results, actuals, and create a Logseq wiki page.

Determine the project name for `home_plans/<project>/` path:

Full home project workflow — scope → research → plan → prep. Research and planning run in subagents. Hand off to /home:5-execute when ready to work.

Fast path for small maintenance tasks, quick fixes, and simple installs under ~2 hours.

Show status of all home projects — phases completed, budget tracking, next steps.

Install, manage, and troubleshoot macOS packages using Homebrew. Use

Design, write, and manage Claude Code hooks. Scans conversation history to identify what hooks you need, applies layered analysis to classify controls by severity, and generates performant hookify-compatible rule files with correct deduplication strategies.

Structured pipeline for vetting hotels before recommending them to wedding guests or event guests. Aggregates reviews from multiple sources, checks neighborhood safety, scores on five guest-fitness dimensions, and produces a structured verdict card per property.

Write, review, or extend Ansible roles and playbooks in the stapler-scripts repo. Use when creating a new role, adding tasks to an existing role, reviewing a playbook for correctness, or applying Ansible best practices. Covers role structure, idempotency, OS portability, variable scoping, and the patterns established in this repo.

Docker build and test workflow with mandatory pre-push validation checklist to prevent CI/CD failures

Install, manage, and troubleshoot macOS packages using Homebrew. Use when a required tool is missing, needs updating, or when managing taps, casks, or formula versions.

Run TestKube and PGBouncer tests on Kubernetes clusters with mandatory context verification to prevent accidental deployments to wrong environments

Run TestKube and PGBouncer tests on Kubernetes clusters with mandatory

Generate STAR stories, practice questions, and talking points from resume

Use this skill when Tyler asks to iterate on a logo, run an adversarial critique-fix loop, or says 'critique and fix this until done'. Runs scored critique → targeted SVG fix cycles until no fixable issues remain.

Discover Java API signatures from compiled JARs using javap instead of

Diagnose and fix failing Java tests (JUnit 5/4, Spring Test, TestNG, Mockito, AssertJ)

Profile Java/Kotlin processes using JFR (Java Flight Recorder). Covers Gradle task setup, CI integration, collapsed-stacks output for LLM analysis, flamegraph visualization, and bottleneck identification patterns.

Use this agent for FBG JIRA ticket creation, project management, and

Create well-structured Jira tickets following INVEST principles and FBG hierarchy rules

Create or update Confluence documentation using the Diataxis framework

Create emergency bug tickets with proper severity and impact assessment

Break down features and organize project work following INVEST principles

Analyze job postings, calculate match scores, identify gaps, and create application strategy

Improves existing docs/journeys/*.md spec files — fills in gaps flagged by journeys-extract, refines vague steps, and links plausible test_ids by searching the repo's test suite — without a full rediscovery pass and without clobbering fields owned by journeys-verify. Always proposes a before/after diff and waits for explicit approval before writing (plan-validate-execute), then applies via journeys-extract's upsert script so the verified→stale invariant stays enforced in one place. Use when a...

Extracts user journeys from an app's existing code into persistent, declarative markdown+YAML spec files under docs/journeys/ — one file per journey, each with a stable journey_id and frontmatter fields for test linkage (test_ids, status, last_verified) that journeys-verify and journeys-enrich own and update later. Uses three parallel lean agents (PM story-map backbone, UX flow analysis, Mermaid diagram generation) to discover journeys, then upserts by journey_id so re-running never duplicate...

Verifies that docs/journeys/*.md spec files (written by journeys-extract) still hold true — every source_ref path still exists and every test_id is still findable in the repo's test suite. Runs a cheap deterministic script (Tier 1, safe for CI/pre-commit on every PR) that flips each journey's status between draft/verified/stale, plus an optional LLM semantic-drift pass (Tier 2, per journey, checks whether the narrative still matches the actual UI/code) for a fuller review. Use to check journe...

Idiomatic review for Node.js glue code that bridges Rust wasm-bindgen modules to playwright-core (e.g. crates/wasm/src/glue/*.js in stapler-mcp). Use when reviewing or writing JS/TS files that call playwright-core APIs from a wasm-bindgen import object, wrap Playwright errors for the wasm boundary, manage browser/page lifecycle, or write node:test tests around that glue.

Fix JVM/Kotlin performance bottlenecks identified via profiling. Covers concrete code changes for allocation pressure, GC tuning, lock contention, JIT blockers, and Kotlin-specific patterns. Use after jfr-profiling has identified the hotspot. Invoke when an engineer has a profile and needs to know what to change.

Publish markdown files to Confluence, crawl Confluence pages to local markdown, sync bidirectionally, validate links, and manage page hierarchy. Use when publishing documentation, downloading Confluence content, checking sync status, resolving conflicts, managing comments, or troubleshooting Confluence page issues.

Conduct structured literature reviews by searching arXiv, building citation graphs via Semantic Scholar, and storing papers locally in the knowledge base. Use when asked to: review literature on a topic, map a research area, find key papers or state-of-the-art methods, explore citation networks, build a reading list, identify research gaps, expand from a seed paper to find related work, or understand what has been published in a field.

Synthesize knowledge from multiple sources — including a conversation, PR, or investigation — into Zettelkasten notes for a personal Logseq wiki. Use when creating wiki pages, integrating academic research, building interconnected knowledge with [[links]] and #[[tags]], or whenever the user says "synthesize this to my wiki" / "add this to my wiki" / "synthesize this to my personal wiki" / "write this up in my notes."

Knowledge Processing Architecture

Migration Guide: Unified [[Needs Processing]] Tag

Knowledge Processing Architecture Migration Notes

Comprehensive analysis of your Logseq wiki to identify what needs attention, prioritized by importance

Transforms any topic into a well-structured, interconnected Zettelkasten note optimized for Logseq with proper file paths

Knowledge Enrichment Orchestrator