By jrjsmrtn
Orchestrate a complete software project lifecycle with AI assistance: from inception (SPARK analysis, project bootstrap) through architecture documentation (ADRs, C4 models), sprint planning, CI/CD hardening (GitHub Actions, GitLab, containers), quality automation (pre-commit hooks, config validation), and sprint closure with release provenance.
Conduct SPARK methodology analysis for new project inception. Use at the beginning of a new project, when evaluating significant features, before bootstrap-project to validate viability, or when pivoting an existing project.
Bootstrap a new project at a chosen graduation tier (t0 minimum, t1 decision-tracked, t2 full pattern language) following AI-Assisted Project Orchestration best practices. Use when starting a new software project, promoting an existing project to a higher tier, or converting an existing project for AI-assisted development.
Graduate a project's in-repo backlog (roadmap phases, sprint deliverables, ADRs) onto a forge issue tracker at a thin-hybrid default, once the backlog outgrows a single contributor. Use when a team needs to see and claim work that currently lives only in docs/roadmap and docs/sprints, when a repo has a mature in-repo roadmap but an empty tracker, when open-sourcing a project, or when deciding what work should stay in-repo versus live on a GitHub, GitLab, Codeberg/Forgejo, or self-hosted internal tracker.
Harden GitHub Actions CI/CD workflows for supply-chain security — SHA-pin actions, least-privilege token permissions, verified toolchain installs, OpenSSF Scorecard, and SLSA provenance. Use when adding or auditing GitHub Actions workflows, before making a repository public, when a supply-chain review flags CI gaps, or when standardizing CI hardening across GitHub projects. GitHub-specific by design — GitLab CI and Forgejo Actions are out of scope.
Harden GitLab CI/CD pipelines for supply-chain security — SHA-pin `include:` and CI/CD components, scope the `CI_JOB_TOKEN` allowlist, protect and mask variables, pin job image digests, and use `id_tokens`/OIDC instead of long-lived secrets. Use when adding or auditing a `.gitlab-ci.yml`, before making a GitLab project public, when a supply-chain review flags CI gaps, or when standardizing pipeline hardening across GitLab projects (gitlab.com or self-hosted). GitLab-specific by design — for GitHub Actions use `harden-github-actions`; Forgejo/Gitea Actions are out of scope.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin providing skills for AI-assisted project orchestration, following best practices for software development lifecycle, architecture documentation, and quality automation.
Install via the jrjsmrtn-skills marketplace:
/plugin install github:jrjsmrtn/jrjsmrtn-skills
Use the GitHub CLI (gh ≥ 2.90.0) — it auto-detects the agent host and installs into the right skills directory:
gh skill install jrjsmrtn/project-orchestration-skills
Pin a single skill or version: gh skill install jrjsmrtn/project-orchestration-skills <skill-name>[@v<version>]. Update later with gh skill update --all.
For Mistral Vibe (not yet in gh skill's host detection), pass --dir:
gh skill install jrjsmrtn/project-orchestration-skills --dir ~/.vibe/skills
| Skill | Description |
|---|---|
| analyze-project | SPARK methodology analysis for new project inception |
| bootstrap-project | Bootstrap a new project with foundational artifacts |
| setup-adrs | Create foundational Architecture Decision Records |
| Skill | Description |
|---|---|
| setup-architecture-as-code | Establish C4 modeling with Structurizr DSL |
| Skill | Description |
|---|---|
| setup-pre-commit | Configure two-stage pre-commit hooks |
| validate-quality-config | Validate consistency across quality configs |
| harden-github-actions | Harden GitHub Actions workflows against supply-chain risk (SHA-pinned actions, least-privilege tokens, verified toolchains). GitHub-specific by design. |
| harden-gitlab-ci | Harden GitLab CI/CD pipelines against supply-chain risk (SHA-pinned include:/components, job-token allowlist, masked+protected variables, id_tokens/OIDC). GitLab-specific by design. |
| setup-container-security | Harden container images (digest-pinned bases, verified fetches, non-root runtime, grype/SBOM) |
| Skill | Description |
|---|---|
| plan-sprint | Create sprint plans with backlog and goals |
| wrapup-sprint | Complete sprints with retrospective and release |
| graduate-backlog | Graduate the in-repo backlog onto a forge tracker (GitHub/GitLab/Forgejo, incl. self-hosted) at a thin-hybrid default, once it outgrows one contributor |
After installation, invoke skills using slash commands:
/analyze-project
/bootstrap-project
/setup-adrs
/setup-architecture-as-code
/setup-pre-commit
/validate-quality-config
/harden-github-actions
/harden-gitlab-ci
/setup-container-security
/plan-sprint
/wrapup-sprint
/graduate-backlog
Or reference them naturally in conversation - Claude will activate the appropriate skill based on context.
This plugin is extracted from the AI-Assisted Project Orchestration pattern language project, which documents patterns for effective AI-human collaboration in software project management.
MIT
npx claudepluginhub jrjsmrtn/jrjsmrtn-skills --plugin project-orchestration-skillsSkills for applying the Diátaxis documentation framework — audit, create, convert, and plan documentation organized around four user needs.
C4 architecture modeling and Structurizr DSL skills for creating, evolving, reviewing, and deploying software architecture models
Claude Code skill for interacting with Obsidian vaults via the Obsidian CLI
Complete project development toolkit: 23 agents, 23 slash commands, 29 lifecycle hooks, and 69 reusable skills for Claude Code workflows
Agent Teams orchestration, governance hooks, multi-AI review, memento skill intelligence, and project management skills for Claude Code
Development autopilot — 28 lifecycle skills + 3 methodology agents + 25 hooks (10 default-on, 15 opt-in) enforcing Three Red Lines discipline. Standalone-capable orchestration that coexists with Superpowers.
Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement
Full-cycle project development - brainstorm ideas, create specifications, plan architecture, initialize projects, and execute implementation with integrated workflows from superpowers and spec-kit
Software engineering workflows with skills for planning, implementation, quality review, and structured thinking, plus a suite of specialist agents