Engineering utilities: Jujutsu (jj) in place of git, evidence-based dependency scoring (dep-quality), conventions for CLIs that agents drive (cli-conventions), a seven-arm adversarial code review with a referee (review-swarm), and a release train that installs and smoke-tests every distribution channel before tagging (release-train).
Plugin dev-tools from marketplace curtisg-skills in curtisgalloway/public-skills. Commands read from the repo's manifest — 8 days ago.
cli-conventionsConventions for command-line tools that both people and agents will drive — a portable exit-code contract, a `--skill` flag that emits the tool's own usage doc, strict `--json`, non-interactive-by-default behavior, and where a tool that runs as a service keeps its secrets. Use when writing a new CLI
dep-qualityScore the health of open-source packages so you can choose between dependency alternatives on evidence instead of fame. Use this skill whenever you are about to add, recommend, or evaluate a third-party dependency; whenever the user asks "which library should I use", "is X maintained", "X vs Y", or
jjUse Jujutsu (jj) for version control instead of git. Trigger whenever a `.jj/` directory exists in the repo, or the user mentions jj or jujutsu, and then for ANY version-control operation in that repo — status, diff, log, commit, branch, bookmark, push, fetch, rebase, squash, split, conflict resolut
release-trainCut a release only after every distribution channel has been built, installed the way a user would in a throwaway prefix, and smoke-tested end to end by a parallel subagent per channel, with a regression archaeologist pinning every previously fixed bug that has no executing test. Runs that full trai
review-swarmAdversarial code review of a diff or pull request, sized to the change: a script reads the diff and picks a light (one reviewer), standard (four or five) or full (seven narrow-mandate reviewers) tier, every finding must quote the code verbatim and is checked mechanically, a referee re-reads high-sev
Working with a coding agent over time: session learning and teaching summaries, handoffs, transcript access, loop safety (intern-mode), design partnership, harness-agnostic skill authoring, and Google Docs review rounds.
17 skills · hooks
Bench and USB-analysis skills: Cynthion setup, capture, pcap decode and protocol reverse-engineering, USB device profiles, the MCCI 3411 test device, Bus Pirate, Siglent oscilloscope control, OWON electronic load queries, and FNIRSI DPS-150 supply control.
10 skills
Every skill in this repository in one plugin: hardware-lab, agent-workflow and dev-tools combined. driver-porting lives in the driver-lab repository and is installed on its own. Install either this or the themed plugins, not both.
hooks
Driver porting and review: peripheral specs whose every fact cites the line it came from, reference reviews of a driver against another implementation, a hardware investigator that answers a question as anchored facts from sources a spec repository's license accepts, board specs with the board-expert reader and a scaffold for new ones, a spec verifier, and campaign review. The clean-room skills are a separate plugin in curtisgalloway/cleanroom-skills. Lives in curtisgalloway/driver-lab; this entry points there.
Advanced git workflows with diff analysis, risk scoring, and reviewer recommendations
2 skills · 1 command · 1 agent
Automatically enforce SonarQube code quality and security in the agent coding loop — 7,000+ rules, secrets scanning, agentic analysis, and quality gates across 40+ languages. PostToolUse hooks run analysis after every file edit. Pre-tool secrets scanning prevents 450+ patterns from reaching the LLM. Slash commands give on-demand access to quality gate status, coverage, duplication, and dependency risks. Includes SonarQube CLI, MCP Server, skills, hooks, and slash commands.
SAST analysis, dependency vulnerability scanning, OWASP Top 10 compliance, container security scanning, and automated security hardening
5 skills · 3 commands · 2 agents
Zero-dependency HTML presentation generator with safe presets, bold template-library styles, PPT conversion, and anti-AI-slop design philosophy.
1 skill
45 advanced engineering skills: agent designer, agent workflow designer, RAG architect, database designer + schema designer + SQL assistant, migration architect, observability designer, dependency auditor, changelog generator, API design reviewer, API test suite builder, CI/CD pipeline builder, MCP server builder, skill security auditor, skill tester, performance profiler, focused-fix, browser-automation, full-page-screenshot, git-worktree-manager, monorepo-navigator, codebase-onboarding, interview-system-designer, runbook-generator, spec-driven-workflow, secrets-vault-manager, env-secrets-manager, pr-review-expert, self-eval, tc-tracker, feature-flags-architect, kubernetes-operator, chaos-engineering, ship-gate, slo-architect (error-budget + multi-window burn-rate alerts per Google SRE Workbook), tech-debt-tracker, agent-regression-evals, coding-agent-rollout, commit-craft, agent-run-forensics and i18n-localization. Agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw.
48 skills · hooks
Understand a codebase before looking for bugs in it. Reads it function by function, records what each one assumes and depends on, and saves the write-ups to files instead of filling up the conversation.
1 skill · 1 agent
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.