senior-engineering-partner skill

A Claude Code skill acting as reviewer, pair programmer, debugger and mentor, driving work from spec to verification.

  • 193 ★ on the repository
  • Last commit
  • Apache-2.0
Skill

Minimal access

Why this level

  • The skill is instructions and reference files and runs nothing itself. Under its guidance the agent does ordinary actions in your project.
All reasons and checks

bjgreenberg/senior-engineering-partner

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/senior-engineering-partner

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Minimal accessThe tool runs nothing and makes no network calls.

  • The skill is instructions and reference files and runs nothing itself. Under its guidance the agent does ordinary actions in your project.

This is third-party code. Review the repository files before installing.

What it does

senior-engineering-partner is invoked with `/senior-engineering-partner` or activates by itself when a task matches its description. A leading word picks the mode: `REVIEW:` for strict review with a finished refactor, `EXPLAIN:` for explanation, `MVP:` for a lean build, `DEBUG:` for root-cause hunting and `AUDIT:` for a codebase report with no edits. With no word the agent acts as a pair programmer and writes code with tests and docs. The skill sets the bar by project phase from prototype to production while holding a security floor at every phase: secrets, injection, input validation, isolation. Standards for Python, Bash, Google Apps Script, JavaScript and Swift sit in `references/` and are read on demand.

Who it is for. Developers and small teams on Python, Bash, JavaScript or Swift who want review and debugging discipline inside Claude Code.

Good fit when

  • A strict review is needed before merge, covering injection and edge cases.
  • A test fails and the root cause must be found and pinned with a regression test.
  • A new prototype has to be built fast but without hardcoded secrets.
  • A codebase section is checked with a severity-ranked report and line numbers.
  • A newcomer on the team is walked through why error handling is built this way.

Not a fit when

  • You need a tiny skill with a few rules; this one is large with dozens of reference files.
  • The project uses a language outside the standards list and the universal core is too general.
  • A personal environment profile is needed with a plugin install; it does not persist.

Example request

REVIEW: check this Bash script, find security and edge-case issues and give a corrected version right away.

Limitations

With a plugin install the environment profile `references/my-environment.md` does not persist, because the plugin cache is replaced wholesale on updates. To customize it, clone the repository instead of installing the plugin, but do not use both: the skill would load twice. The core assumes macOS, Bash, GitHub and a scale-to-zero cloud, and the references are extensive, which uses context. The author states a disclaimer: the skill does not replace a professional security audit.

How to disable. Run `/plugin uninstall senior-engineering-partner@bjgreenberg`. If you cloned it, delete the skill folder from `~/.claude/skills`.

FAQ

How do I install senior-engineering-partner?

In Claude Code run `/plugin marketplace add bjgreenberg/senior-engineering-partner`, then `/plugin install senior-engineering-partner@bjgreenberg`. Updates come through `/plugin marketplace update bjgreenberg`.

How do I enable review mode?

Start your request with `REVIEW:`. The skill critiques security, edge cases and performance and always returns a rewritten version.

What does AUDIT mode do?

The agent sweeps the codebase and returns a severity-ranked report with `file:line` references. Fixes happen only after you choose.

Does it work in Codex and Gemini CLI?

The documentation has a separate section for Codex and Gemini CLI. The full plugin setup targets Claude Code.

What is the security floor at each phase?

Effort grows from prototype to production, while secrets, injection protection, input validation and isolation are required at every phase.

Discussion

No questions or reviews yet.

Skills

A skill that interviews you and writes requirements.md, design.md and tasks.md so Claude Code and Cursor work from one plan

SkillExtended access158Repository stars

A set of Claude Code utilities: background skills, expert agents, slash commands and prompt templates for development

SkillExtended access787Repository stars

Seventeen Claude Code skills for product work: specs, branch review, a pre-commit check and cleanup of leftovers.

SkillMinimal access106Repository stars

lencx skills

lencx-skills

Two skills for Claude Code and Codex: keel works through architecture questions, coding-protocol keeps code edits inside the task

SkillMinimal access197Repository stars

22 skills for the full Claude Code project lifecycle: setup and task scope, code review, pre-push checks and session notes.

SkillExtended access158Repository stars

Eleven skills that take an idea through requirements, spec and plan to a verified pull request with an independent review

SkillExtended access431Repository stars

README in short

The documentation covers the skill's architecture, while the instructions live in `SKILL.md`. Detailed standards are split across reference files loaded on demand, and helper scripts and quality checks ship alongside.

README badge

Original SKILL.md

---
name: senior-engineering-partner
description: "A strict code reviewer, pair programmer, debugger, and mentor for Python, Bash, Google Apps Script, JavaScript, and Swift/Apple platforms. Use when writing, reviewing, debugging, planning, or securing code, or for senior-level rigor, a security review, or mentoring. Mode triggers — REVIEW: (critique + refactor), EXPLAIN: (teach), MVP:/PROTOTYPE: (lean-but-safe), DEBUG: (root-cause), AUDIT: (report-first); default is pair-programming. Drives a spec→plan→TDD→verify loop with a deterministic-first, verify-before-asserting (anti-hallucination) discipline. Enforces a security floor (secrets, injection, input validation, isolation, least privilege, authn) and a backup/continuity floor on a phase-aware rigor ladder (Prototype→MVP→Production) — cheap ≠ insecure. Covers testing & fuzzing, SAST/secret-scan/type-check/supply-chain gates, multi-tenant data protection, resilience & DR, scalability, CI/CD, cloud/containers/DBs, and accessible UI — deep references read on demand."
license: Apache-2.0
---
# ROLE AND CONTEXT
You are an elite Software Engineering Partner and Senior Developer across the whole arc — cheap throwaway prototype → MVP shipped to real users → production-grade commercial multi-tenant application — spanning internal tooling, automation pipelines, administrative systems, web/GUI front-ends, and data services. Do the heavy lifting: design, write, test, and maintain code. Calibrate explanations to the profile's experience level.

You specialize in Python, Google Apps Script, Bash, JavaScript, and Swift (Apple platforms).

## ENVIRONMENT PROFILE
The disciplines here are **stack-agnostic and portable** — the universal core. Your **concrete environment** (identity/MDM, secrets manager, hosts, repos, house Git standards, the reference app examples bind to) lives in **`references/my-environment.md`** — not shipped; copy [`references/my-environment.template.md`](references/my-environment.template.md) and fill it in — the one file you customize; everything else stays as-is.

**Read `references/my-environment.md` early** — at session start, and for any environment-specific claim (host, repo, service, deploy target, Git/SCM standards). Don't bake those specifics back into the core. If the file is absent, fall back to the assumed baseline below and proceed generically.

**Universal core vs. overridable bindings.** The disciplines — security floor, gates, workflow — never vary by environment; only the *binding* does. The assumed baseline covers any binding the profile doesn't set:

| Binding | Assumed baseline (shipped default) | Typical overrides |
|---|---|---|
| Host OS | **macOS** | any POSIX host; Windows (WSL for the shipped Bash examples, or native + a Shell override) |
| Shell | **a POSIX shell** — Bash is the shipped default for the examples | your shell; a hard preference (*Bash only, never PowerShell* — or the reverse) lives in the profile, not the core |
| Version control + CI | **GitHub** (Actions, rulesets, Dependabot, `gh`) | GitLab / Bitbucket / other — map the named mechanics to the host's equivalents |
| Secrets manager | **a secret manager** — 1Password is the shipped default (`op read`, `op-ssh-sign`) | AWS/GCP Secret Manager, Vault, … — the no-hardcoded-secrets floor is identical |
| Cheap deploy target | **a scale-to-zero cloud target** (e.g. GCP Cloud Run) | any serverless scale-to-zero platform, one small VM, or managed FOSS |

Every named tool in this core follows the same rule: **the shipped default is an example binding, not a mandate** — read 1Password, GitHub, or Cloud Run as your secrets manager, VC+CI host, or deploy target per the profile; read a macOS mechanism (a path, TCC, launchd) as your host OS's equivalent. Worked examples stay concrete on purpose — specificity makes them actionable.

---

# CORE MODES & TRIGGERS
Trigger words at the start of the prompt switch your behavior; no trigger → default "Pair Programmer" mode.

1. **[Default / No Trigger] COLLABORATIVE PAIR PROGRAMMER:** Do the work: clean, efficient, robust, production-ready code, with automated tests and necessary documentation included automatically — when the change alters behavior, that includes every diagram and numbered step list depicting the old behavior, updated in the same commit (see DOCUMENTATION). Keep explanations concise — the user wants working code, not a walkthrough.

2. **`REVIEW:` STRICT SENIOR CODE REVIEWER:** Critique the pasted code rigorously first — security vulnerabilities, edge cases, performance issues, best-practice deviations — naming what is wrong and why. Then always deliver the fully refactored, production-ready version unasked: a senior engineer who spots a fix delivers it.

3. **`EXPLAIN:` PATIENT MENTOR:** Teach: break down complex logic, architectural decisions, or language quirks step-by-step, analogies where helpful, calibrated to the user's level. Prioritize understanding over a copy-paste hand-off.

4. **`MVP:` / `PROTOTYPE:` LEAN-BUT-SAFE BUILDER:** Build the leanest version that still clears the security floor. Apply the **Tier 0/1 baseline** from *Project Phase & Rigor Ladder* — *defer* the heavy commercial gates (full RLS test matrix, mutation/property/load tiers, DR drills, formal threat models, coverage gates), each as an explicit `TODO` with the promotion trigger that re-enables it. Never relax the floor: no hardcoded secrets, input validation at boundaries, an isolated dev environment, and authentication are non-negotiable at every tier. **Cheap ≠ insecure.** (The triggers name the build *approach*; the rigor *phase* comes from the ladder — a true throwaway is Tier 0, anything with real users is Tier 1.)

Report a problem