amit-t
- 39 skills
- 0 followers
- 7 hours ago last updated
- ▌ Docs From Prs 2 · amit-tSurvey recent merged PRs/commits, find what is not yet documented in README.md / docs/index.html / docs/user-guide/, and update those docs with thoughtful section placement. Always re-checks the alias tables. Project-local skill for ai-ralph. Trigger when the user says "update docs from PRs", "doc the recent changes", "/docs-from-prs", or asks to bring README/landing page in sync with merged work.
- ▌ Docs From Prs 3 · amit-tSurvey recent merged PRs/commits, find what is not yet documented in README and other user-facing docs, and update those docs with thoughtful section placement. Always re-checks the project's drift hot spots (alias tables, CLI flag references, config examples). Trigger when the user says "update docs from PRs", "doc the recent changes", "/docs-from-prs", or asks to bring docs in sync with merged work.
- ▌ Faq · amit-t bundleUse when the user invokes /faq with a question, forwards a question someone asked about the current repo, or says "add this to the FAQ". Answers the question from the repo's source of truth and records it in the repo's FAQ document.
- ▌ Tdd · amit-t bundleTest-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
- ▌ Eng Spec · amit-t bundleConvert an approved PRD into TDD + Engineering Spec + ADRs, run a 5-agent engineering panel review (Architect, DB Designer, Principal SWE, SDET, Performance Engineer), fix blockers, approve, and sync to ralph.
- ▌ Grill Me · amit-t bundleInterview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me". Supports a depth selector (quick / standard / deep) — deep is the default.
- ▌ E2e Audit · amit-t bundleRun a Playwright end-to-end audit of a web app using its PRDs as the test spec. Produces a diagnostic report showing what's working and what's not from a user's perspective.
- ▌ Prd Draft · amit-t bundleCreate a modern, AI-era PRD for features and initiatives. Guides through clarifying questions, generates draft, and offers multi-agent review.
- ▌ Pmo Status · amit-t bundleFull project status across Product (PM-OS), Engineering DOE (specs/ADRs), and Engineering Implementation (fix_plan/ralph). Run this at the start of any session to orient yourself, or on demand.
- ▌ Skill Sync · amit-t bundleSync an existing at-skills skill from a source path, or scaffold a new one via claude/codex/devin. Wraps the skill-sync zsh utility in ai-utils.
- ▌ Prd Approve · amit-t bundleApprove a reviewed PRD — updates status, copies to approved inbox, and updates PRD-PIPELINE.md. Run only after /prd-review-panel is complete and you are satisfied with the output.
- ▌ Prd To Plan · amit-t bundleTurn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file in ./plans/. Use when the user wants to break a PRD into an implementation plan, or mentions "tracer bullets".
- ▌ Write A Prd · amit-t bundleCreate a PRD through user interview, codebase exploration, and module design, then submit as a GitHub issue. Use when the user wants to write a PRD or plan a new feature.
- ▌ Design Draft · amit-t bundleRun the full UXD workflow end-to-end for an approved PRD — design interview → user flow → wireframes → design system → hi-fi screens → design review → developer handoff → approve. Reads approved PRDs from pm-os automatically.
- ▌ Domain Grill · amit-t bundleEngineering-only. Stress-tests an engineering artifact (eng spec, TDD plan, refactor proposal, architecture sketch, technical design, schema migration, API contract) against the project's CONTEXT.md. Reads CONTEXT.md read-only, interviews the user against existing terminology and decisions, surfaces conflicts, may add ADRs for new hard-to-reverse decisions. For PRDs, marketing plans, or any non-code artifact, refuse and redirect to /grill-me. Supports a depth selector (quick / standard / deep) — deep is the default. Triggers include "grill this spec", "domain grill", "stress-test against CONTEXT", and "/domain-grill".
- ▌ Design Review · amit-t bundleMulti-agent design review from 5 perspectives — UX Researcher, Accessibility Auditor, Engineer, Brand Guardian, and End User Voice. Feed it any generated screen file or design description.
- ▌ Docs From Prs · amit-t bundleSurvey recent merged PRs/commits, find what is not yet documented in README and other user-facing docs, and update those docs with thoughtful section placement. Always re-checks the project's drift hot spots (alias tables, CLI flag references, config examples). Trigger when the user says "update docs from PRs", "doc the recent changes", "/docs-from-prs", or asks to bring docs in sync with merged work.
- ▌ Grill Me Auto · amit-t bundleUse when the user wants a non-interactive Grill Me run written as one collapsible markdown document, asks for "Grill Me Auto", "auto grill", "all grill questions at once", or invokes /grill-me-auto, /Grill Me Auto, or /grill me auto.
- ▌ Package Scout · amit-t bundleResearch, compare, and select the best npm/pnpm/yarn packages before installing. Use when scaffolding a project, adding a dependency or devDependency, or choosing between competing libraries — including when the user says "add dependency" or "which library should I use".
- ▌ Write A Skill · amit-t bundleCreate new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
- ▌ Gh Repo Mirror · amit-t bundleScaffold a new GitHub repo that mirrors an existing reference repo's general settings, branch-protection rules, security flags, and (optionally) its GitHub Pages site — porting the static HTML/CSS/JS docs and rebranding them. Use when the user says "create a new repo like X", "mirror settings from Y", "new repo same as Z with Pages", or asks for a skills-library / Pages-site scaffold modelled on another repo.
- ▌ Precision Mode · amit-t bundleUniversal conciseness and precision directive for all LLM output. Prepend to any system prompt to eliminate verbosity, filler, and fluff from every response.
- ▌ Wisdom Capture · amit-t bundleRecord a wisdom snippet — quote, idea, or observation worth keeping — into the user's personal corpus. Categorizes into a closed bucket from wisdoms/_categories.yml, writes a frontmatter Markdown file, and commits. Captures from terminal CLI (`wisdom`) or in-session slash command (`/wisdom` / `$wisdom`).
- ▌ Session Handoff · amit-t bundleCompact the current conversation into a discoverable handoff document so a fresh agent can pick it up with /resume-session-handoff. Use when the user wants to hand off work to a fresh session or teammate, or stop here and resume later. Triggers include "/session-handoff", "write a session handoff", "hand this off to another agent".
- ▌ Two Axis Review · amit-t bundleReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X" or for a "two-axis review".
- ▌ Design Interview · amit-t bundleInteractive design brief interview. Always run before generating any screens. Extracts product context, user goals, visual style, constraints, and success criteria through a structured conversation.
- ▌ Prd Review Panel · amit-t bundleRun a 7-perspective multi-agent PRD review (Engineering, Design, Executive, Legal, UXR, Skeptic, Customer Voice) that catches gaps and surfaces conflicts before stakeholder review. Use when the user wants a PRD reviewed, asks for panel or multi-agent feedback, or runs /prd-review-panel.
- ▌ Resume Tailoring · amit-t bundleTailor a resume to a specific job by researching the company/role, surfacing undocumented experience through branching interview, matching content with confidence scores, and emitting MD + DOCX + PDF + interview-prep report. Use when the user says "I want to apply for [Role] at [Company]. Here's the JD:", pastes a job description, provides multiple JDs/URLs, or asks to tailor/optimize a resume for a role. Never fabricates experience; reframes and emphasizes truthfully.
- ▌ Session Feedback · amit-t bundleMine the current conversation for every correction the user made, every preference they stated, and every "do-differently" lesson, then write a dated feedback file into the project's auto-memory directory so future sessions can reload the patterns. In future sessions, before applying any item from a past feedback file the agent must ask the user "Do I care about this at the moment, or do I not?" using the compact recall-listing format. Use when user says `/session-feedback` (write mode), `/session-feedback --recall` (bulk recall at session start), or whenever the agent is about to apply a remembered pattern (just-in-time recall).
- ▌ Setup Pre Commit · amit-t bundleSet up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current JS/TS repo. Use when the user wants to add pre-commit hooks or set up Husky/lint-staged for commit-time formatting, typechecking, and tests.
- ▌ Concise Reporting · amit-t bundleUse when reporting status, progress, results, errors, or any information back to the user. Does not apply when writing content, documents, or artifacts for the user.
- ▌ Leadership Update · amit-t bundleReformat a status update so leadership remembers you positively. Turn raw notes into outcome-first, three-sentence updates with a clear ask. Use when the user wants to give an update to a manager, exec, or stakeholder, mentions a "status update", "leadership update", "exec update", or pastes raw notes about what they've been working on.
- ▌ Repo Context Scan · amit-t bundleScans a codebase to build CONTEXT.md (or CONTEXT-MAP.md for multi-context repos) and seed ADRs for clearly-deliberate decisions. Autonomous by default; asks only when ambiguity blocks resolution. Use after cloning a repo, joining a project mid-flight, or when docs have drifted from code. Triggers include "scan repo context", "build CONTEXT.md", "bootstrap domain context", and "/repo-context-scan".
- ▌ Setup Amit Skills · amit-t bundleConfigure a repository for amit-t/skills conventions — bootstrap AGENTS.md/CLAUDE.md, docs/agents context docs, ADR layout, or skill catalog category vocabulary. Triggers include "setup amit skills", "/setup-amit-skills", and "make this repo work with amit-t/skills".
- ▌ Ubiquitous Language · amit-t bundleDEPRECATED. Superseded by /repo-context-scan (build domain context from a codebase scan) and /domain-grill (stress-test engineering artifacts against the resulting CONTEXT.md). Do not invoke. The replacement skills produce richer outputs (CONTEXT.md + ADRs + relationships + multi-context support) and split the build vs grill responsibilities cleanly. Use /repo-context-scan to build, /domain-grill for engineering artifacts, and /grill-me for PRDs or non-technical plans.
- ▌ Compact Conversation · amit-t bundleCompact a long conversation into a saved progress summary — completed work, key decisions, current state, pending tasks — so a fresh session can pick up without losing context. Fires only as a fallback when the agent has no native /compact command; check for one first. Use when the user says "compact this conversation", "compact the context", "reduce context window", "summarize our progress", or "create a conversation summary".
- ▌
- ▌ Gh Pages Neo Brutalist · amit-t bundleUse when scaffolding a GitHub Pages site for a new (or existing) repo and you want a cohesive neo-brutalist design system. Drops in Jekyll layouts, design tokens, four-theme switcher (light/dark/cyberpunk/solarized), copy buttons, and a hero/nav/markdown-body system in one shot.
- ▌ Resume Session Handoff · amit-t bundlePick up where a previous session left off by loading the newest open handoff document written by /session-handoff. Reads `.claude/handoffs/<timestamp>-<slug>.md` inside the project root, runs an environment preflight (branch, cwd, uncommitted state) against the handoff's frontmatter, then on user confirmation moves the file to `.claude/handoffs/resumed/`, internalises the content, and **asks the user what to do next** — never auto-executes. Triggers include "/resume-session-handoff", "resume the session handoff", or "pick up where we left off".