By nitintf
General workflow helpers: catch up on what changed, compress communication (caveman), hand off a session to a fresh agent, and get grilled on any plan or design.
Summarize what changed so you can re-enter work fast. Given a branch, PR, commit range, file, or "since yesterday", it reads the diff/commits and produces a tight summary: what changed, why, risk areas, and what's left. Great for resuming after a break, reviewing what a teammate pushed, or before picking up a PR. Use when the user asks what changed or wants to get back up to speed. Triggers: "catch me up", "catchup", "what changed", "what did I miss", "summarize this branch/PR/diff", "since I last looked".
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
Standalone, relentless interview about a plan or design until you reach shared understanding, resolving each branch of the decision tree one at a time with a recommended answer for each. General-purpose — for any plan/design discussion, NOT tied to the eng pipeline's .plan docs (use eng's /grill for those). Use when the user wants to stress-test thinking or get grilled. Triggers: "grill me", "stress-test this plan", "poke holes in this", "interview me about this design".
Compact the current conversation into a handoff document for another agent to pick up. Use when the user wants to hand off work, end a session cleanly, or prep context for a fresh agent. Triggers: "handoff", "write a handoff", "hand this off", "prep for next session".
Personal Claude Code plugins — reusable skill packs for engineering workflows, packaged as a Claude Code plugin marketplace so they work in any project.
eng — plan-to-ship engineering pipelineFive composable skills plus an orchestrator. Each skill is a single pass over a
shared markdown doc that lives in the target project's .plan/ folder, so they
work solo or chained. The doc holds all state; the skills communicate through it.
| Skill | What it does |
|---|---|
/scope | Explore the codebase, decide ticket breakdown (asks you), draft a planning doc per ticket with real file:line touchpoints, house conventions, and open questions. Drafts Jira ticket text (output only). |
/grill | Read the doc's open questions, grill you (eng + business), explore for context, write answers into Decisions and sharpen acceptance criteria. |
/eng-review | EM-style review: architecture, edge cases, tests, performance, and consistency with how this codebase already builds things. Folds fixes back in. |
/tdd | Turn acceptance criteria into a test contract: unit-test spec + manual/UI QA checklist. Specifies tests; doesn't write them. |
/execute | Write the specified tests (failing first), implement against the plan & house conventions, make tests pass, verify acceptance criteria, run QA, update the doc. |
/eng-flow | Orchestrator — runs scope → grill → eng-review → tdd → execute off the doc's phase, pausing at a gate between each. Resumes wherever you left off. |
The doc schema every skill obeys is the keystone: see eng/SPEC.md.
<project>/.plan/<feature-slug>/
README.md # feature index + per-ticket status
<NN>-<ticket-slug>/doc.md # one self-contained doc per ticket
.plan/ is committed so the plan lives in history (plan-said-X vs reality-was-Y).
product — product-thinking skillsStandalone from eng, but their output (written to .plan/<feature>/) can feed
/scope.
| Skill | What it does |
|---|---|
/prd | Write a staff-level PRD (Google/Meta/Amazon bar): problem, measurable goals & non-goals, success metrics, prioritized requirements, risks, rollout. Supports the Amazon PR/FAQ format. NOT in the eng doc schema. |
/user-stories | Slice a PRD/epic into INVEST user stories with Gherkin acceptance criteria, ordered with dependencies. Feeds /scope. |
productivity — workflow helpers| Skill | What it does |
|---|---|
/catchup | Summarize what changed (branch / PR / commit range / file) so you can resume or review fast. |
/caveman | Ultra-terse communication mode — ~75% fewer tokens, full technical accuracy. Persists until "normal mode". |
/handoff | Compact the conversation into a handoff doc (saved to the OS temp dir) for a fresh agent to continue. |
/grill-me | Standalone relentless interview on any plan/design (not tied to .plan docs — use eng's /grill for those). |
Add this repo as a marketplace, then install the plugins you want:
/plugin marketplace add nitintf/ai-skills
/plugin install eng@nitin-ai-skills
/plugin install product@nitin-ai-skills
/plugin install productivity@nitin-ai-skills
(Or /plugin marketplace add <path-to-local-clone> while developing.)
Skills are plain markdown at eng/skills/<name>/SKILL.md. Edit and reload. When
adding a field or section, update eng/SPEC.md first — it's the contract all
the skills depend on.
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.
npx claudepluginhub nitintf/ai-skills --plugin productivityPlan-to-ship engineering pipeline. Five composable skills (scope, grill, eng-review, tdd, execute) plus an orchestrator (eng-flow). Each is a single pass over a shared markdown doc in the project's .plan folder, so they work solo or chained.
Product-thinking skills. Write staff-level PRDs and slice them into testable user stories. Standalone, but their output (in .plan/<feature>/) can feed the eng pipeline's /scope.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Harness-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
Frontend design skill for UI/UX implementation
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns