{"id":51324365,"url":"https://github.com/bjgreenberg/senior-engineering-partner","last_synced_at":"2026-07-01T17:00:38.359Z","repository":{"id":367605747,"uuid":"1280913563","full_name":"bjgreenberg/senior-engineering-partner","owner":"bjgreenberg","description":"A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/Apps Script/JS). Security-first, phase-aware engineering discipline with a spec→plan→TDD→verify workflow.","archived":false,"fork":false,"pushed_at":"2026-06-26T17:10:20.000Z","size":273,"stargazers_count":0,"open_issues_count":1,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-26T19:03:09.851Z","etag":null,"topics":["ai-agents","anthropic","bash","claude-code","claude-code-skill","claude-skill","code-review","developer-tools","pair-programming","python"],"latest_commit_sha":null,"homepage":null,"language":"Shell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bjgreenberg.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":"NOTICE","maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-06-26T03:57:19.000Z","updated_at":"2026-06-26T17:09:51.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/bjgreenberg/senior-engineering-partner","commit_stats":null,"previous_names":["bjgreenberg/senior-engineering-partner"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/bjgreenberg/senior-engineering-partner","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bjgreenberg%2Fsenior-engineering-partner","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bjgreenberg%2Fsenior-engineering-partner/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bjgreenberg%2Fsenior-engineering-partner/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bjgreenberg%2Fsenior-engineering-partner/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bjgreenberg","download_url":"https://codeload.github.com/bjgreenberg/senior-engineering-partner/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bjgreenberg%2Fsenior-engineering-partner/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35015061,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-01T02:00:05.325Z","response_time":130,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-agents","anthropic","bash","claude-code","claude-code-skill","claude-skill","code-review","developer-tools","pair-programming","python"],"created_at":"2026-07-01T17:00:22.368Z","updated_at":"2026-07-01T17:00:38.329Z","avatar_url":"https://github.com/bjgreenberg.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"# senior-engineering-partner\n\nLast updated: 2026-07-01 11:09 AM CDT\n\n[![License: Apache-2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)\n[![Latest release](https://img.shields.io/github/v/release/bjgreenberg/senior-engineering-partner?sort=semver\u0026label=release)](https://github.com/bjgreenberg/senior-engineering-partner/releases)\n[![docs-render](https://github.com/bjgreenberg/senior-engineering-partner/actions/workflows/docs-render.yml/badge.svg?branch=main)](https://github.com/bjgreenberg/senior-engineering-partner/actions/workflows/docs-render.yml)\n[![leakage-guard](https://github.com/bjgreenberg/senior-engineering-partner/actions/workflows/leakage-guard.yml/badge.svg?branch=main)](https://github.com/bjgreenberg/senior-engineering-partner/actions/workflows/leakage-guard.yml)\n[![shellcheck](https://github.com/bjgreenberg/senior-engineering-partner/actions/workflows/shellcheck.yml/badge.svg?branch=main)](https://github.com/bjgreenberg/senior-engineering-partner/actions/workflows/shellcheck.yml)\n[![OpenSSF Scorecard](https://api.securityscorecards.dev/projects/github.com/bjgreenberg/senior-engineering-partner/badge)](https://scorecard.dev/viewer/?uri=github.com/bjgreenberg/senior-engineering-partner)\n[![Conventional Commits](https://img.shields.io/badge/Conventional%20Commits-1.0.0-yellow.svg)](https://www.conventionalcommits.org/en/v1.0.0/)\n\nA custom Claude Code skill: a strict **code reviewer, pair programmer, debugger, and mentor** for\nPython, Bash, Google Apps Script, and JavaScript. It encodes a security-first,\nphase-aware engineering discipline — and an enforced **spec → plan → TDD → verify** workflow —\nas reusable instructions that activate via\n`/senior-engineering-partner` (or auto-activate when a task matches its description) in\nany Claude Code session.\n\n\u003e This README documents the skill's *architecture* — how it is organized and maintained.\n\u003e The skill's actual instructions live in [`SKILL.md`](SKILL.md); the deep, per-topic\n\u003e standards live in [`references/`](references/).\n\n- **Author:** Brian Greenberg · **Web:** https://briangreenberg.net\n- **Version:** see the metadata table at the bottom of [`SKILL.md`](SKILL.md), the\n  [`CHANGELOG.md`](CHANGELOG.md), and the\n  [Releases](https://github.com/bjgreenberg/senior-engineering-partner/releases) page\n- **Invoke:** `/senior-engineering-partner` in Claude Code, optionally prefixed with a\n  mode trigger word (see [Modes](#modes--triggers)).\n\n---\n\n## What it is\n\nA single skill that does the heavy lifting of senior engineering work — design, write,\ntest, review, debug, and document code — calibrated to an intermediate Python/Bash developer.\nThree ideas run through everything:\n\n- **Phase-aware rigor, with a security floor that never moves.** Match effort to the\n  project's phase (prototype → MVP → production), but never relax the\n  secrets/injection/validation/isolation/authentication fundamentals. *Cheap ≠ insecure.*\n- **Deterministic-first, anti-hallucination discipline.** Verify before asserting (claims\n  about the environment come from a tool run *this turn*), never invent flags/paths/APIs,\n  and mechanize anything checkable (counting, parsing, regex, transforms) in a script\n  rather than reasoning it out token-by-token.\n- **An enforced workflow, not just standards.** The skill doesn't only say what good looks\n  like — it drives the loop that produces it: **spec-first** (agree what you're building\n  before building it) → **plan** in verifiable steps → **tier-aware iron-law TDD** →\n  **verify-before-done self-review**. Depth scales with the rigor tier; the loop does not.\n\n---\n\n## What it governs\n\nThe disciplines are stack-agnostic, but they bind to concrete tooling. At a glance, what the skill\ncarries standards for:\n\n- **Languages:** Python · Bash · Google Apps Script · JavaScript / TypeScript\n- **Source control \u0026 CI/CD:** GitHub · GitHub Actions · branch protection / rulesets · supply-chain gates (SBOM · SLSA · signing)\n- **Cloud \u0026 infra:** GCP / Cloud Run · Docker · Kubernetes · Terraform (IaC)\n- **Data:** Postgres / Supabase (RLS) · BigQuery · SQLite · caching\n- **App layer:** FastAPI / Python web APIs · front-end \u0026 browser security · responsive, accessible (WCAG 2.2 AA) UI\n- **Security \u0026 standards:** the security floor (secrets · injection · input validation · isolation · least privilege) · NIST CSF 2.0 + SSDF · OWASP Top 10 / **API Top 10** / **LLM Top 10** · STRIDE · SOC 2 · Well-Architected · PCI-DSS scope\n- **Reliability \u0026 ops:** resilience engineering · disaster recovery \u0026 business continuity · scalability / system design · observability + incident response (DORA · SLOs)\n- **Platform-specific:** macOS app bundles / TCC · local \u0026 agentic AI tooling · diagrams-as-code (Mermaid)\n\nEach binds to a deep, **read-on-demand** reference (see the [catalog](#reference-catalog) below); your\nconcrete hosts, projects, and stack live only in the private, un-committed `references/my-environment.md`.\n\n---\n\n## Architecture\n\nThe skill is a **stack-agnostic universal core** (`SKILL.md`, always loaded) plus a\n**swappable environment profile** and a library of deep per-topic references read **on\ndemand** (progressive disclosure — Claude reads a reference only when its trigger\nparagraph in `SKILL.md` says the work is relevant). Forking the skill for a different\nenvironment is a matter of replacing one file (`references/my-environment.md`).\n\n```mermaid\nflowchart TD\n    U[\"/senior-engineering-partner\"] --\u003e C\n    C[\"SKILL.md — universal core\u003cbr/\u003emodes · epistemic discipline · engineering workflow · rigor ladder\u003cbr/\u003esecurity floor · coding standards · toolchain triggers\"]\n    C --\u003e|\"progressive disclosure: read a reference only when relevant\"| R[(references/)]\n    C -.-\u003e|\"shipped helpers\"| K[\"scripts/ (audit · render-diagrams · self-review)\u003cbr/\u003eevals/ (27 regression scenarios)\"]\n    R --\u003e P[\"Environment profile\u003cbr/\u003emy-environment.md (swap to re-home the skill)\"]\n    R --\u003e W[\"Engineering process (4)\u003cbr/\u003eengineering-workflow · debugging · audit-report-format · standards-authoring\"]\n    R --\u003e S[\"Security, privacy and compliance (6)\"]\n    R --\u003e T[\"Testing and QA (2)\"]\n    R --\u003e I[\"Cloud, infra and ops (9) + data (2)\"]\n    R --\u003e A[\"App toolchains, CI and collaboration (11)\"]\n    R --\u003e X[\"UI, a11y, diagrams, AI tooling, macOS (4)\"]\n```\n\n`SKILL.md` carries the rules that must always be in context (the modes, the security\nfloor, the rigor ladder, the coding/documentation/logging/SCM standards, and a short\ntrigger paragraph per toolchain). Each trigger paragraph states the non-negotiables and\npoints at the reference to **read before** doing related work — so the expensive detail\nis loaded only when it earns its place in the context window.\n\n---\n\n## Modes \u0026 triggers\n\nBehavior changes on a leading trigger word; with no trigger, it defaults to pair\nprogramming.\n\n```mermaid\nflowchart TD\n    P[User prompt] --\u003e Q{Leading trigger word?}\n    Q --\u003e|\"REVIEW:\"| R[\"Strict senior code reviewer\u003cbr/\u003ecritique rigorously, then deliver the refactor\"]\n    Q --\u003e|\"EXPLAIN:\"| E[\"Patient mentor\u003cbr/\u003eteach the why, not just a copy-paste answer\"]\n    Q --\u003e|\"MVP: / PROTOTYPE:\"| M[\"Lean-but-safe builder\u003cbr/\u003eTier 0/1, defer heavy gates, never the floor\"]\n    Q --\u003e|\"DEBUG:\"| G[\"Systematic debugger\u003cbr/\u003ereproduce, isolate, fix root cause, prove with a red-first test\"]\n    Q --\u003e|none| D[\"Collaborative pair programmer (default)\u003cbr/\u003eclean, tested, documented, production-ready code\"]\n```\n\n| Trigger | Mode | What it does |\n|---|---|---|\n| *(none)* | **Pair programmer** | Do the work — production-ready code with tests + docs, concise explanation. |\n| `REVIEW:` | **Strict reviewer** | Critique security/edge-cases/perf/best-practices first, then always deliver the refactored version. |\n| `EXPLAIN:` | **Mentor** | Educate step-by-step, calibrate to an intermediate dev, prioritize understanding. |\n| `MVP:` / `PROTOTYPE:` | **Lean-but-safe builder** | Leanest version that still clears the security floor; defer heavy gates as explicit `TODO`s with promotion triggers. |\n| `DEBUG:` | **Systematic debugger** | Reproduce → hypothesize → isolate/bisect → fix the root cause (not the symptom) → prove with a regression test seen to fail red first. |\n\n---\n\n## The rigor ladder\n\nEffort scales with project phase; the **security/CIA floor holds at every tier**. Only\nverification depth, redundancy, and operational maturity scale.\n\n```mermaid\nflowchart LR\n    T0[\"Tier 0 — Prototype\u003cbr/\u003ethrowaway, never real tenant data\"]\n    T1[\"Tier 1 — MVP / early product\u003cbr/\u003ecritical-path tests, basic CI, secrets manager, authn, backups\"]\n    T2[\"Tier 2 — Production / commercial / multi-tenant\u003cbr/\u003efull strict posture, every merge-blocking gate\"]\n    Floor[\"Security / CIA floor — CONSTANT at every tier\u003cbr/\u003eno hardcoded secrets · validate inputs · no injection · isolated env · authn · vetted deps\"]\n    T0 --\u003e|\"real users / small scale\"| T1\n    T1 --\u003e|\"customers · money · multi-tenant · PII · 2nd contributor · public exposure\"| T2\n    Floor -.underpins.-\u003e T0\n    Floor -.underpins.-\u003e T1\n    Floor -.underpins.-\u003e T2\n```\n\nCrossing any promotion trigger (real customer/tenant data, money changing hands,\nmulti-tenant isolation, regulated/PII data, a second contributor, public internet\nexposure) re-rates the project up a tier — it is not optional polish.\n\n---\n\n## Reference catalog\n\nDeep standards, read on demand. Each carries verify-against-live-docs caveats on\nversion-specific commands.\n\n| Group | Reference | Covers |\n|---|---|---|\n| **Environment profile** | `my-environment.md` | The concrete stack/hosts/repos/house-Git-standards — the one file to swap when forking the skill |\n| **Engineering process** | `engineering-workflow.md` | The spec → plan → tier-aware iron-law TDD → verify-before-done self-review loop |\n| | `debugging.md` | Systematic root-cause method (the `DEBUG:` mode): reproduce → hypothesize → isolate → fix cause → red-first regression test |\n| | `audit-report-format.md` | The `AUDIT:` mode deliverable: a severity-ranked findings report (finding schema, severity taxonomy, mechanize-the-checkable, lead-with-verified-strengths) |\n| | `standards-authoring.md` | Distill sprawling project conventions into a checkable standards set (extract → filter → human-approve → classify floor-vs-overridable); prose-first, format-agnostic |\n| **Security, privacy \u0026 compliance** | `threat-modeling-and-api-design.md` | In-PR STRIDE threat models + attack-surface-shrinking API design |\n| | `secure-data-processing.md` | Hostile-file parsing, prompt-injection, multi-tenant data handling |\n| | `frontend-web-security.md` | Token storage, CSP, output sanitization, security headers |\n| | `secrets-and-key-rotation.md` | Rotation lifecycle, zero-downtime overlap, KMS key-version re-wrap |\n| | `data-protection.md` | GDPR/UK-GDPR/CCPA as code: DSAR, erasure cascade, retention, DPIA |\n| | `compliance.md` | NIST CSF 2.0 + **SSDF (800-218)** / OWASP / SOC 2 / **Well-Architected** as enforceable review checklists |\n| **Testing \u0026 QA** | `testing.md` | The enforced merge-gate taxonomy, tenant-isolation tests, coverage/mutation/load tiers |\n| | `testing-single-file.md` | The `conftest.py` argv-patch pattern for single-file scripts |\n| **Cloud, infra \u0026 ops** | `gcp.md` | Cloud Run, GCS, BigQuery, Secret Manager, IAM (no SA keys → Workload Identity) |\n| | `iac-terraform.md` | Terraform on GCP, locked remote state, OIDC deployer, plan-as-gate |\n| | `containers-and-orchestration.md` | Docker/Kubernetes: digest pins, non-root, scanning, securityContext |\n| | `observability-and-incident-response.md` | Structured logs + correlation id, RED/USE metrics, SLO burn-rate alerting + severity-routed channels, client-side/RUM monitoring, incident lifecycle |\n| | `disaster-recovery.md` | 3-2-1-1-0 immutable backups (Bucket Lock, not just versioning), out-of-domain copies, verified PITR, scheduled restore drills, local/sync-≠-backup |\n| | `business-continuity.md` | BIA → justified RTO/RPO, provider-outage plans, comms/decision plan, the solo-operator/bus-factor path |\n| | `resilience-engineering.md` | Degrade-don't-die in code: timeouts, circuit breaker, bulkhead, load-shed, designed degraded modes, kill-switch |\n| | `scalability-and-system-design.md` | The \"-ilities\": statelessness for horizontal scale, queue+worker, DLQ, transactional outbox, the pool/N+1/hot-partition ceilings, capacity \u0026 perf targets |\n| | `logging-and-monitoring.md` | Structured logging in Python (JSON + `contextvars` correlation id, per-stack loggers), log location/rotation, the launchd open-fd gotcha, unattended-job monitor design |\n| **Data** | `databases.md` | Postgres/Supabase RLS (+ pgTAP), BigQuery, SQLite, migrations |\n| | `caching.md` | Cache-key-must-encode-the-tenant, invalidation, what-not-to-cache |\n| **App toolchains, CI \u0026 collaboration** | `python-web-apis.md` | FastAPI/Uvicorn/psycopg: lifespan, Pydantic, auth-as-`Depends`, RLS pipeline |\n| | `github-actions.md` | Least-priv `permissions`, SHA-pinned actions, multi-gate pipelines (audit/typecheck/lint), SBOM + build-provenance attestation, gated deploy + canary + release automation |\n| | `github-teams.md` | Team-grade repo hygiene (required gates, CODEOWNERS, review every agent PR) |\n| | `package-managers.md` | Brewfile/npm/mas — reproducible pinned manifests, supply-chain vetting |\n| | `dev-environments.md` | VS Code/Xcode/Antigravity hygiene, extension vetting, signing |\n| | `dev-environment-isolation.md` | Never dev against prod, per-project venv/container, sandbox untrusted code |\n| | `foss-adoption.md` | Vet FOSS before adopting (license/Scorecard/CVEs) + pin/lock/contract-test |\n| | `multi-agent-coordination.md` | The concurrency override when \u003e1 writer shares a repo |\n| | `python-typing-and-packaging.md` | The TypedDict worked example + the single-file→package target layout |\n| | `google-apps-script.md` | `clasp` + git over the editor, minimal `oauthScopes`, `PropertiesService` secrets/limits, `LockService`, trigger quotas + the 6-min wall, Advanced Services vs `UrlFetchApp`, `console`→Cloud Logging, pure-logic isolation for testing |\n| | `javascript-and-typescript.md` | TS strict mode (the `mypy --strict` analog) + the flags `strict` misses, runtime-validated typed boundaries (the Pydantic analog), Node `SIGTERM`/no-floating-promises patterns |\n| **UI, docs \u0026 AI tooling** | `ui-design-and-accessibility.md` | Responsive + light/dark + WCAG 2.2 AA + Claude Design handoff |\n| | `diagrams-and-visual-docs.md` | Diagrams-as-code, Mermaid-first; render-check before commit |\n| | `local-and-agentic-ai-tools.md` | Agentic assistants + self-hosted LLMs (Ollama/Open WebUI) |\n| | `macos-app-bundles.md` | LaunchAgent `.app` bundles, TCC/FDA, the compiled-launcher requirement |\n\n---\n\n## Shipped helpers \u0026 evals\n\nBeyond the always-loaded core and the read-on-demand references, the skill ships two\nsupport directories:\n\n- **`scripts/`** — the utility scripts the disciplines reference, shipped so they're\n  *executed*, not regenerated: `audit.sh` (manifest-level dependency-audit gate),\n  `render-diagrams.sh` (the `docs-render` Mermaid render-check), and `self-review.md` (the\n  verify-before-done checklist). Pin `render-diagrams.sh`'s `MMDC_IMAGE` to a digest before\n  relying on it.\n- **`evals/`** — a regression suite. Each `scenarios/*.json` encodes a real miss from the\n  changelog as a checkable expectation, in Anthropic's evaluation shape. `evals/README.md`\n  documents the baseline-then-iterate (Claude-A authors / Claude-B tests) loop. **Add or\n  extend a scenario whenever a new changelog entry is written from a real miss** — a lesson\n  without a guarding eval can silently regress.\n\n---\n\n## Install\n\nClaude Code loads skills from `~/.claude/skills/`. Install by cloning this repo into that\ndirectory under the skill's own name:\n\n```bash\ngit clone https://github.com/bjgreenberg/senior-engineering-partner \\\n  ~/.claude/skills/senior-engineering-partner\n```\n\nThen **customize it for your environment** (next section) and invoke it with\n`/senior-engineering-partner` (optionally prefixed with a mode trigger word). The universal\ncore works out of the box against the assumed baseline (macOS, Bash, GitHub, a secret\nmanager, a scale-to-zero cloud target); the profile is what makes its guidance specific to\n*you*.\n\n## Customize for your environment (`my-environment.md`)\n\nThe core is deliberately **stack-agnostic** — it carries no hosts, repos, employer, or\nmachine specifics. Those live in one file you create from the shipped template:\n\n```bash\ncd ~/.claude/skills/senior-engineering-partner\ncp references/my-environment.template.md references/my-environment.md\n$EDITOR references/my-environment.md   # fill in your stack/hosts/Git standards/reference app\n```\n\n`references/my-environment.md` is `.gitignore`d, so your real details are never committed —\nyou can keep your fork's core in sync with this repo (`git pull`) without ever exposing your\nprofile. The core instructs the assistant to **read `my-environment.md` early and for any\nenvironment-specific claim**, so the more complete it is, the more grounded the guidance.\n\n## Maintaining / contributing\n\n- **Versioning + releases are automated** with\n  [release-please](https://github.com/googleapis/release-please): it reads the Conventional\n  Commits on `main`, opens a release PR that bumps the `Version` in `SKILL.md`'s metadata table\n  and prepends the entry to [`CHANGELOG.md`](CHANGELOG.md). A maintainer enriches that entry's\n  narrative, then cuts the **signed** tag + GitHub Release — the repo's `tag-protection` ruleset\n  requires signed tags, so that final step is a deliberate manual one (see\n  [`MAINTAINERS.md`](MAINTAINERS.md) → *Cutting a release*). The skill's own documentation\n  discipline, applied to itself.\n- **Diagrams are render-checked before commit:** a Mermaid block that fails to render is a\n  broken deliverable. Validate with GitHub/VS Code preview, mermaid.live, or\n  `@mermaid-js/mermaid-cli` (`mmdc`) — see\n  [`references/diagrams-and-visual-docs.md`](references/diagrams-and-visual-docs.md). CI\n  runs `scripts/render-diagrams.sh` (the `docs-render` gate) on every PR.\n- **Helper scripts are ShellCheck-clean:** a `shellcheck` gate lints `scripts/*.sh` on every PR\n  (the skill's own \"zero warnings is the standard\" applied to itself). A script that trips\n  ShellCheck is a broken deliverable and can't merge.\n- **No environment-specific leakage in the core:** a `leakage-guard` check greps the tree against\n  a denylist of personal/host/repo identifiers. It's **two-tier**: generic class-patterns (a\n  CGNAT/Tailscale IP range, Obsidian-style wiki-links) ship in `scripts/leakage-guard.sh` and run in CI,\n  while your *literal* identifiers live in an un-committed `references/leakage-denylist.local`\n  (created from its `.template`) so the public repo never has to publish them to block them. Keep\n  the universal core universal; anything specific belongs in your (un-committed) `my-environment.md`.\n- **Add or extend an `evals/` scenario** whenever you add a load-bearing rule — a lesson\n  without a guarding eval can silently regress.\n\n## License\n\nApache-2.0 © Brian Greenberg. See [`LICENSE`](LICENSE) and [`NOTICE`](NOTICE).\n\n## Disclaimer\n\nThis skill is provided **as is**, without warranty of any kind, under the Apache-2.0 license —\nsee the *Disclaimer of Warranty* (§7) and *Limitation of Liability* (§8) sections of\n[`LICENSE`](LICENSE). It offers **engineering guidance, not professional security, legal, or\ncompliance advice**. Review and validate any code, configuration, or security decision it\ninfluences before relying on it — you are responsible for what you ship.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbjgreenberg%2Fsenior-engineering-partner","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbjgreenberg%2Fsenior-engineering-partner","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbjgreenberg%2Fsenior-engineering-partner/lists"}