Divya's parallel-first agentic engineering skills: team-based workflows, adversarial verification, security and performance gates from line 1
Use when starting any creative work (a feature, component, behavior change, schema, or refactor) before writing code, scaffolding, or invoking an implementation skill, especially when the request is vague, names multiple subsystems, or you feel an urge to skip design because it "looks simple".
Use when building, changing, or reviewing anything a user sees or touches (a page, component, app, flow, CLI output, onboarding, error message, email), when deciding whether a feature should exist, or when work looks done but feels generic, clunky, or burdensome.
Use when designing or implementing anything that touches user input, authentication, sessions, secrets, PII, network calls, file uploads, or deployment config, when adding an endpoint or a dependency, or when reviewing code for security. Symptoms: "is this safe", "validate this", handling tokens, building auth, storing passwords, accepting uploads, exposing an API.
Use when you face 2+ independent tasks (separate test failures, subsystems, files, or investigations) with no shared state or sequential dependency, and working them one at a time would waste time.
Use when something is slow or might be ("it feels slow", "is this fast enough"), or when a choice affects speed: a slow endpoint, an N+1 query, nested loops over large input, a heavy bundle, picking a stack, database, framework, data structure, or algorithm, adding a hot-path dependency, or reviewing code for performance.
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.
Parallel-first engineering skills for Claude Code. A ground-up rebuild of superpowers for the agent-team era: terse, date-agnostic, adversarially verified, secure from line 1.
Superpowers encoded the right discipline on old assumptions: one agent, one chat thread, expensive code, a human watching every step. All four flipped. dmjcustomizations keeps the gates and rebuilds the mechanics.
| Skill | One-liner |
|---|---|
| using-dmj | Meta-skill, injected each session: how skills are found, routed, and prioritized |
| brainstorming | Idea to approved spec: parallel context sweep, batched questions, evidence-based options |
| writing-plans | Spec to implementation plan with per-task dependencies, parallelizability, acceptance criteria |
| executing-plans | Team executes a plan: tasks claimed concurrently, worktree isolation, review gates |
| team-driven-development | Plan execution in the current session with implementer and reviewer teammates |
| dispatching-parallel-teams | Any 2+ independent tasks: fan out a team, coordinate, synthesize |
| test-driven-development | Iron Law TDD plus an extreme edge-case taxonomy (adversarial, concurrency, boundaries) |
| systematic-debugging | Root cause before fixes; parallel hypothesis investigation |
| verification-before-completion | Evidence before claims; independent fresh-context verification |
| requesting-code-review | Multi-lens parallel review panel: correctness, security, performance, simplicity |
| receiving-code-review | Rigor over performative agreement; verify before implementing feedback |
| using-git-worktrees | Isolation for parallel work and disposable spikes |
| finishing-a-development-branch | Verified finish: merge, PR, or cleanup, with team and worktree teardown |
| writing-skills | TDD for documentation: baseline, write, close loopholes, team-tested |
| defending-in-depth | Security from line 1: threat model, OWASP, zero trust, quantum-safe defaults |
| enforcing-performance-budgets | O(1)-first, measured budgets, cache-first, regressions block merges |
| researching-deeply | Parallel research with adversarial source verification and dated citations |
| exploring-codebases | Five-lens parallel codebase mapping with an anti-redundancy gate: reuse before rebuild |
| explore | Parallel slice-by-slice tracing of how a codebase really works, explained in chat, no artifacts |
| harnessing-claude | Capability routing: strongest native Claude feature for every job, never hand-rolled substitutes |
| crafting-experiences | Experience supremacy: Jobs test, first-second hook, cinematic with purpose, zero user burden |
| landing-sessions | Session teardown: learnings to memory, state to git, resources to zero, threads surfaced |
| selling-the-vision | Launch persuasion: one-second hook, keynote arc, one message, one CTA, honest claims |
The plugin installs as dmj, so skills fire as dmj:brainstorming, dmj:test-driven-development, etc.
From GitHub:
/plugin marketplace add divyamohan1993/dmjcustomizations
/plugin install dmj@dmj
Or from a local clone:
/plugin marketplace add D:\dmjcustomizations
/plugin install dmj@dmj
Then disable superpowers so the two rule systems do not compete:
/plugin uninstall superpowers
Forked from obra/superpowers 5.1.0 by Jesse Vincent (MIT). Rebuilt 2026-06-10 by Divya Mohan. MIT licensed.
npx claudepluginhub divyamohan1993/dmjcustomizations --plugin dmjHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,561 supported skills.