Paldom

Authors or improves an Agent Skill in this repo via the eval-first workflow - scope one purpose, write trigger evals, draft SKILL.md, validate, iterate. Use when the user asks to create, add, write, refine, or fix a skill ("add a skill for X", "improve triggering of Y"). Not for scaffolding a new repository or editing infrastructure (hooks, CI, the validator/scripts, docs).

Creates or completes GitHub community health files - CONTRIBUTING, CODE_OF_CONDUCT, SECURITY, SUPPORT, GOVERNANCE, FUNDING.yml, CODEOWNERS, LICENSE - tailored to the repo, not boilerplate. Use when the user asks for these files, contributing guidelines, a code of conduct, or to complete the community profile. Not for issue/PR templates or enabling security settings like scanning and rulesets.

Patterns and best practices for Lakebase Autoscaling (next-gen managed PostgreSQL). Use when creating or managing Lakebase Autoscaling projects, configuring autoscaling compute or scale-to-zero, working with database branching for dev/test workflows, implementing reverse ETL via synced tables, or connecting applications to Lakebase with OAuth credentials.

Patterns and best practices for Lakebase Provisioned (Databricks managed PostgreSQL) for OLTP workloads. Use when creating Lakebase instances, connecting applications or Databricks Apps to PostgreSQL, implementing reverse ETL via synced tables, storing agent or chat memory, or configuring OAuth authentication for Lakebase.

Builds structured GitHub contribution intake - YAML issue forms with required fields and auto-labels, config.yml routing, a pull request template with a working checklist, and starter labels like good first issue. Use when the user asks for issue templates, bug report forms, a PR template, or to stop blank issues. Not for CONTRIBUTING or other prose community files, and not for issue triage.

INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread_id, time travel, Store, and subgraph persistence modes.

Publishes this Agent Skills repository to skills.sh - pre-flight checks, public visibility flip, protections (PVR, ruleset), consumer-style install verification, telemetry seeding, and repo-page groupings. Use when the user asks to publish, deploy, release, go public, or get listed on skills.sh. Not for authoring skills or editing scaffold infrastructure.

Writes, restructures, or syncs a professional GitHub project README - front-loaded value prop, minimal badges, copy-pasteable quick start, scannable structure for a library, CLI, or web app. Use when the user asks to write, improve, restructure, or review a README, or calls it bloated, stale, or outdated. Not for repo topics/social-preview metadata, community files, or profile READMEs.

How to custom-style a Streamlit application with a modern, stable theming stack — reusable theme TOML files, self-hosted fonts, light/dark modes, sidebar theming, chart palettes, shared page bootstrap, and scoped CSS for custom component variants. Use this skill PROACTIVELY whenever the user wants to style, theme, brand, or customize the appearance of a Streamlit app — including changing colors, fonts, buttons, sidebar look, dark mode, chart colors, or adding custom CSS. Also use when the user mentions config.toml theming, Streamlit design systems, or asks how to make a Streamlit app look professional/branded. Even if the user only asks about one aspect (e.g. "change the sidebar color"), apply this skill because the answer depends on which styling layer is appropriate.

Quick reference for building full-stack Databricks Apps with apx (React + FastAPI). Use when working on apx projects, creating routes, adding components, or managing dev servers.

Create and manage Databricks Agent Bricks: Knowledge Assistants (KA) for document Q&A, Genie Spaces for SQL exploration, and Multi-Agent Supervisors (MAS) for multi-agent orchestration. Use when building conversational AI applications on Databricks.

Create and configure Databricks Asset Bundles (DABs) with best practices for multi-environment deployments. Use when working with: (1) Creating new DAB projects, (2) Adding resources (dashboards, pipelines, jobs, alerts), (3) Configuring multi-environment deployments, (4) Setting up permissions, (5) Deploying or running bundle resources

Patterns and best practices for using Lakebase Provisioned (Databricks managed PostgreSQL) for OLTP workloads.

Deploy and query Databricks Model Serving endpoints. Use when (1) deploying MLflow models or AI agents to endpoints, (2) creating ChatAgent/ResponsesAgent agents, (3) integrating UC Functions or Vector Search tools, (4) querying deployed endpoints, (5) checking endpoint status. Covers classical ML models, custom pyfunc, and GenAI agents.

Creates, configures, and updates Databricks Lakeflow Spark Declarative Pipelines (SDP/LDP) using serverless compute. Handles streaming tables, materialized views, CDC, SCD Type 2, and Auto Loader ingestion patterns. Use when building data pipelines, working with Delta Live Tables, ingesting streaming data, implementing change data capture, or when the user mentions SDP, LDP, DLT, Lakeflow pipelines, streaming tables, or bronze/silver/gold medallion architectures.

Generate realistic synthetic data using Faker and Spark, with non-linear distributions, integrity constraints, and save to Databricks. Use when creating test data, demo datasets, or synthetic tables.

Installs agentic guardrails into a Python repo — Claude Code hooks, a Stop gate that signs off only what pre-commit accepts, vetted public skills — and troubleshoots hooks that don't fire or block. Use for 'add Claude Code hooks', 'write an AGENTS.md', 'make this repo agent-ready', 'agent keeps bypassing checks', 'agent says done but pre-commit fails'. Not for authoring the pre-commit config.

Configures pre-commit for a Python repo — a .pre-commit-config.yaml with ruff, mypy, hygiene, commit-message and pre-push hooks, plus non-Python file formatting and validation (YAML, JSON, TOML, Markdown), kept in sync with CI. Use for 'set up pre-commit', 'add git hooks', 'format the YAML and Markdown', 'enforce conventional commits'. Not for Claude Code agent hooks or CI workflows.

Authors GitHub Actions quality-gate workflows for a Python repo — lint/type/test jobs, version matrices, uv caching, coverage upload, an all-checks-passed aggregator, required checks, rulesets, merge queues, SHA pinning. Use for 'set up CI', 'add a GitHub Actions workflow', 'make checks required', 'harden the workflows'. Not for release pipelines, pre-commit config, Dependabot, or secret scanning.

Sets up and tunes Ruff linting and formatting for a Python package — pyproject [tool.ruff] rule selection, Black/Flake8/isort migration — and fixes lint or format failures. Use when the user says 'set up linting', 'add ruff', 'fix lint errors', 'configure the formatter'. Not for type errors, non-Python file formatting, pre-commit wiring, or CI workflows.

Configures packaging for a Python library — pyproject.toml metadata, build backend choice, src layout, uv project management, building wheels and sdists, verifying py.typed lands in the wheel. Use for 'package this project', 'set up pyproject.toml', 'build a wheel', 'switch to uv', 'migrate off Poetry'. Not for publishing to PyPI, version bumps, release automation, or typing strategy.

Cuts and automates releases of a Python package — version bumps, changelogs, git tags, PyPI trusted publishing (OIDC), and the tag-triggered publish workflow with a gated environment. Use for 'cut a release', 'publish to PyPI', 'bump the version', 'automate releases', 'set up trusted publishing'. Not for packaging metadata, build backends, or non-release CI.

Hardens a Python repository's supply chain — Dependabot update automation, pip-audit vulnerability scanning, secret scanning and push protection, CodeQL, OpenSSF Scorecard, SBOMs, CODEOWNERS. Use for 'set up dependabot', 'audit dependencies', 'enable secret scanning', 'harden this repo'. Not for CI quality gates, workflow hardening, or PyPI publishing.

Builds pytest infrastructure for a Python package — layout and config, coverage gates with fail_under, Hypothesis property-based tests, mutation testing to catch weak or agent-gamed tests, multi-version runs via tox, nox, or uv. Use for 'set up pytest', 'add coverage', 'test on multiple Python versions'. Not for writing tests for one file, fixing a single failing test, or CI workflow YAML.

Designs a human AI governance council - hybrid management council plus board escalation, charter and conflict-of-interest templates, decision-rights matrix, incident escalation, KPIs, and US/EU/UK/China compliance lanes. Use for "set up an AI governance board/council", "AI review committee charter", "model launch approval process". Not for multi-model LLM ensembles or technical safety evals.

Combines multiple LLM answers or judge verdicts robustly - correlated-error limits of majority voting, reliability weighting, side-swapped pairwise comparison, judge-synthesizer separation, and surfacing dissent. Use for "combine/aggregate model outputs", "LLM judge panel/jury", "majority vote across models", "rank council responses". Not for pipeline topology, member choice, or stage prompts.

Designs LLM council orchestration - parallel fan-out, anonymized peer review, chairman synthesis, topology choice by task shape, debate round caps, stopping rules, graceful degradation. Use for "build/design an LLM council", "multi-model deliberation architecture", "structure a debate/review/synthesis pipeline". Not for member selection, prompt wording, aggregation math, or cost tuning.

Cuts cost and latency of multi-model LLM pipelines - route-first gating so the council fires only on hard queries, calibrated-confidence escalation, prompt caching, batching, tail-latency budgeting. Use for "the council/ensemble is too expensive or slow", "route to a cheaper model then escalate", "reduce multi-LLM cost". Not for deciding whether to adopt a council or aggregation choice.

Defends LLM councils against failure modes - sycophancy and groupthink (structured dissent, round caps, no early-stop-on-consensus), correlated-error monitoring, and prompt-injection amplification containment. Use for "models keep agreeing", "council groupthink", "multi-agent prompt injection", "consensus feels fake". Not for single-agent jailbreak hardening or member selection.

Implements an LLM council over headless coding harnesses in plain Python - one router over Claude Code, Codex CLI, and API models, subprocess hygiene, JSON contracts with tolerant extraction, per-member failure isolation, boss-synthesis fallback. Use for "council of Claude Code/Codex CLIs", "run coding agents headless as council members". Not for API-only orchestration frameworks.

Selects and role-designs LLM council members - provider-diverse 3-5 model panels, cognitive lenses over personas, role-to-model routing, anonymization and identity effects, persona-drift countermeasures. Use for "which models should sit on the council", "pick council members", "design advisor personas/lenses". Not for pipeline topology, aggregation math, or stage prompt wording.

Writes the prompts for each LLM council stage - forced-perspective advisor prompts, anonymized peer review with a parseable ranking contract, decisive chairman synthesis that may side with a dissenter, rebuttal rounds. Use for "write the council/advisor/chairman prompts", "peer review prompt", "synthesis prompt". Not for pipeline architecture, member selection, or aggregation rules.

Authors GitHub Actions CI for Node projects - version matrices derived from engines, setup-node caching, pnpm setup without corepack, a fail-closed all-checks aggregator, merge_group support, concurrency. Use when the user asks to set up CI, add a Node test matrix, cache installs, or fix required checks and merge queues. Not for release/publish pipelines or dependency-update policy.

Sets up and tunes linting and formatting for Node/TypeScript projects - Biome as the one-tool option or ESLint flat config plus Prettier, rule tuning, eslintrc-to-flat and ESLint-to-Biome migrations, editor and CI wiring. Use when the user asks to set up or fix linting, formatting, ESLint, Biome, or Prettier. Not for Next.js apps, type checking, or test setup.

Configures npm package artifacts - package.json exports maps, ESM-first vs dual format decisions, tsdown/tsup bundling, publint and arethetypeswrong gates, files whitelist, engines. Use when the user asks to package a library for npm, fix consumer import or type-resolution errors, or check publish-readiness. Not for version bumps, changelogs, releases, or registry auth.

Hardens the npm supply chain - lockfile discipline, Dependabot cooldown and groups, per-package-manager install-script policy, provenance verification, npm token hygiene, SHA-pinned Actions. Use when the user asks to secure dependencies, audit npm packages, respond to a compromised dependency, or pin actions. Not for repo settings like rulesets/secret scanning, or publishing.

Tunes Next.js App Router application quality - next.config hardening, eslint-config-next flat config, strict mode and typed routes, RSC and use-client boundary hygiene, bundle analysis, image and font optimization. Use when the user asks to production-harden a Next.js app, fix hydration or use-client errors, or shrink a Next bundle. Not for generic Node linting, unit test setup, or npm packaging.

Cuts and automates npm releases - Changesets, semantic-release or release-please, npm trusted publishing (OIDC) with provenance, the first-publish bootstrap, staged publishing, changelogs and tags. Use when the user asks to release, version, publish to npm, or remove tokens from publish workflows. Not for package exports/bundling artifacts or verifying dependency provenance.

Builds unit and integration test infrastructure for Node/TS/React - Vitest or node:test selection with explicit config, v8 coverage gates that fail CI, React Testing Library, mocking discipline, flaky-test triage. Use when the user asks to set up tests, add coverage thresholds, pick a test runner, or fix a flaky test setup. Not for E2E browser suites, lint rules, or CI workflow authoring.

Configures TypeScript for Node libraries and apps - explicit strict tsconfig, module and moduleResolution choices, verbatimModuleSyntax, isolatedDeclarations, declaration emit for publishing, tsc type-check gates, incremental strictification. Use when the user asks to set up TypeScript, tighten tsconfig, or fix declaration output. Not for lint rules, bundling, or package exports resolution.

Makes a marketing landing page WCAG 2.2 AA accessible - semantic HTML over ARIA, color contrast, visible focus, touch-target size, labeled forms with linked errors, no overlay widgets, reduced motion. Use when asked to make a page accessible, fix WCAG/a11y issues, run an accessibility audit, or support screen readers and keyboard users. Not for copy, design, page speed/SEO, or A/B testing.

Writes and edits conversion copy for marketing landing pages - voice-of-customer mining, outcome-first headlines, value props, CTA labels, specific social proof. Use when the user asks to write, draft, rewrite, or fix landing-page copy, a hero headline, CTA text, or messaging. Not for section layout, visual design, or A/B testing.

Sets up conversion measurement and A/B testing for a landing page - server/edge variant assignment (no flicker), A/B vs multi-armed bandit, statistical significance, filtering bot/AI traffic, analytics. Use when asked to A/B test, run an experiment, measure conversions, check significance, or set up landing-page analytics. Not for writing copy, page structure, or Core Web Vitals.

Designs the section skeleton of a marketing landing page - the page as one sequenced argument, hero anatomy, section ordering, form-field count, and CTA/proof placement. Use when the user asks how to structure, lay out, sequence, or wireframe a landing page, which sections to include, or how many form fields. Not for the words/copy, visual styling, animation, or code.

Implements a landing page in Next.js App Router with React + shadcn/ui + Tailwind - RSC/client-component boundaries, shadcn setup, next/image & next/font, and the streaming-metadata gotcha. Use when asked to build, scaffold, or fix a Next.js landing page, resolve 'use client' errors, set up shadcn, or fix a blank-head/unindexed page. Not for copy, visual design, animation, or SEO strategy.

Adds scroll-triggered animation and motion to a landing page with the right tier by purpose - native CSS scroll-driven animation, GSAP/ScrollTrigger, or Motion - protecting INP and honoring prefers-reduced-motion. Use when asked to add scroll animations, reveals, parallax, a pinned/scrubbed sequence, smooth scrolling, or pick an animation library. Not for copy, layout, palette, or SEO.

Sets up a landing page's visual design system and keeps AI output on-brand - palette/type/spacing budgets that avoid generic 'AI slop' aesthetics, plus a DESIGN.md (tokens-as-roles, a Don'ts list) and lint/visual/a11y enforcement gates. Use when asked to choose colors, fonts, or visual style, stop AI design sameness, or set up design tokens. Not for copy, layout structure, motion, or SEO.

Engineers a landing page to rank and load fast - server-rendered HTML so crawlers and AI bots see content, Core Web Vitals (LCP/INP/CLS), field-vs-lab, structured data, off-main-thread scripts. Use when asked to improve Core Web Vitals, page speed, technical SEO, get indexed, or fix a slow page. Not for copy, design, accessibility, A/B testing, or Next.js 'use client'/build bugs.

Scaffolds a new standalone Agent Skills repository - created on GitHub via gh repo create (private, MIT), cloned locally, the bundled template overlaid and validated, .local/PROMPT.md seeded; the overlay stays uncommitted for owner review. Use when the user wants to create or scaffold a skill repo or collection ("create python-skills"). Not for adding skills to an existing repo.

Publishes this Agent Skills repository to skills.sh - pre-flight checks, public visibility flip, protections (PVR, ruleset), consumer-style install verification, telemetry seeding, and repo-page groupings. Use when the user asks to publish, deploy, release, go public, or get listed on skills.sh. Not for authoring skills or editing scaffold infrastructure.

Publishes the current Agent Skills repository to skills.sh - pre-flight checks, public visibility flip, protections (PVR, rulesets), a gh skill release, consumer-style install verification, telemetry seeding, and repo-page groupings. Use when the user asks to publish, deploy, release, go public, or get listed on skills.sh. Not for authoring skills or scaffolding repositories.

Authors or improves an Agent Skill in this repo via the eval-first workflow - scope one purpose, write trigger evals, draft SKILL.md, validate, iterate. Use when the user asks to create, add, write, refine, or fix a skill ("add a skill for X", "improve triggering of Y"). Not for scaffolding a new repository or editing infrastructure (hooks, CI, the validator/scripts, docs).

Authors or improves an Agent Skill in the current repo via the eval-first workflow - scope one purpose, write trigger evals, draft SKILL.md, validate, benchmark. Use when the user asks to create, add, write, refine, fix, or benchmark a skill ("add a skill for X", "improve triggering of Y"). Not for scaffolding a new repo (create-skill-repo) or distilling research packs (skill-from-research).

Turns a research pack (reports, notes, transcripts) into installable Agent Skills - inventories the pack, verifies claims against primary sources, splits into single-purpose skills, authors each eval-first. Use when the user has research and wants it turned into a skill ("turn this research pack into a skill", "skillify this"). Not for authoring without research or repo scaffolding.

Authors or improves an Agent Skill in this repo via the eval-first workflow - scope one purpose, write trigger evals, draft SKILL.md, validate, iterate. Use when the user asks to create, add, write, refine, or fix a skill ("add a skill for X", "improve triggering of Y"). Not for scaffolding a new repository or editing infrastructure (hooks, CI, the validator/scripts, docs).

Publishes this Agent Skills repository to skills.sh - pre-flight checks, public visibility flip, protections (PVR, ruleset), consumer-style install verification, telemetry seeding, and repo-page groupings. Use when the user asks to publish, deploy, release, go public, or get listed on skills.sh. Not for authoring skills or editing scaffold infrastructure.

Plans, writes, or restructures project documentation - Diátaxis structure (tutorials, how-to guides, reference, explanation), minimal doc set, runnable examples, README-to-docs graduation, drift prevention. Use when the user asks to write, improve, or reorganize docs, guides, or tutorials. Not for the README itself, deploying a docs site, or community files.

Stands up, deploys, or fixes a documentation site on GitHub Pages - generator choice (MkDocs, Sphinx, Docusaurus, Starlight), the official Actions workflow, base-path/.nojekyll/custom-domain pitfalls, docs CI, versioning. Use for publishing docs to github.io or debugging a broken/unstyled Pages deploy. Not for writing the docs content, the README, or branch protections.

Writes, restructures, or syncs a professional GitHub project README - front-loaded value prop, minimal badges, copy-pasteable quick start, scannable structure for a library, CLI, or web app. Use when the user asks to write, improve, restructure, or review a README, or calls it bloated, stale, or outdated. Not for repo topics/social-preview, community files, profile READMEs, or docs sites.

Audits a GitHub repository against a professional open-source checklist - README quality, metadata, community files, intake templates, protections, activity - and returns a scored gap report with prioritized fixes. Use when the user asks to audit, health-check, or score their repo, or asks what's missing before going public. Not for fixing a single named file or code-level security audits.

Implements MCP server authorization - OAuth 2.1 resource server role, RFC 9728/8414 discovery, PKCE, RFC 8707 audience validation, scopes, client registration. Use when adding auth, OAuth, tokens, or credentials to an MCP server, or debugging 401/403/discovery failures. Not for general threat hardening, transport wiring, or non-MCP app login.

Deploys, operates, and distributes MCP servers - stateless scaling, session externalization, observability, health probes, canary rollouts, MCPB bundles, npm/PyPI packaging, MCP Registry publishing, versioning. Use when the user asks to deploy, host, scale, operate, package, publish, or version an MCP server. Not for writing server code, auth flows, hardening, or evals.

Designs an MCP server's tool/resource/prompt surface - outcome-oriented consolidation, tool budget, naming, descriptions-as-prompts, flat typed schemas, pagination, agent-readable errors. Use when planning what an MCP server should expose, fixing wrong-tool choices by improving names and descriptions, or turning an API into MCP tools. Not for writing server code, OAuth, or deployment.

Implements MCP servers with the official TypeScript or Python SDK - registering tools/resources/prompts, stdio and Streamable HTTP transports, lifecycle, isError vs protocol errors, structured output, progress and cancellation. Use when the user asks to build, create, code, scaffold, or debug an MCP server or its transport. Not for choosing the tool surface, OAuth, hardening, evals, or hosting.

Hardens MCP servers against MCP-specific attacks - tool poisoning, rug pulls, prompt injection via tool results, session hijacking, SSRF, command injection - with guardrails-in-code, sandboxing, audit logging, kill switches. Use for securing, hardening, threat-modeling, or security-reviewing an MCP server or vetting a third-party one. Not for OAuth/token wiring or generic appsec scans.

Tests and evaluates MCP servers - Inspector, the official conformance suite, agent evals with verifiable answers, transcript-driven description iteration, tool-selection accuracy, CI regression gates, load tests. Use when the user asks to test, evaluate, verify, or measure an MCP server or its tool selection. Not for fixing server code, security hardening, or generic unit testing.

Renders an app/package icon SVG at 512/64/32/16 px and reviews the pixels against a fixed rubric (16px silhouette, Gestalt device, stroke, centering, distinctiveness), with targeted SVG fixes on request. Use when the user asks to review, critique, compare, rate, or fix an icon or whether it reads at small/favicon sizes. Not for designing icons, ideation, exporting assets, or UI icon-set reviews.

Draws a minimalist app or OSS package icon as a master 1024x1024 SVG - symmetric glyph on a dark grey rounded-rectangle (Apple-style radius). Use when the user asks to design, create, draw, generate, or make an app icon, package icon, or simple logo mark. Not for icon concept brainstorming, critiquing renders, exporting favicon/assets, UI icon sets, or vectorizing images.

Exports an approved master icon SVG into platform assets - favicon.ico + SVG favicon, apple-touch-icon, PWA 192/512 + maskable, App/Play Store PNGs, macOS icns, GitHub social preview, plus HTML/manifest snippets. Use when the user asks to export, generate, or ship favicons, app icon files, or store icons, or to wire the exported set into a repo. Not for designing, ideating, or critiquing icons.

Derives a minimalist icon design brief from a text prompt or the current repo - 3-5 symbol concepts (one Gestalt device each), symmetry axis, dark-grey house palette, distinctiveness notes. Use when the user wants icon ideas, icon concepts, symbol metaphors, or a pre-drawing brief for an app/package icon. Not for drawing the SVG, critiquing renders, or exporting icon assets.

Designs and diagnoses the control flow of agentic loops - pattern selection, supervisor-enforced caps and terminal states, no-progress detection, external verifier gates, context and compaction budgets, crash recovery. Use when an agent loop stalls, drifts, repeats itself, or never stops, or when building agent orchestration. Not for goal or prompt wording, ordinary code loops, or scheduled jobs.

Builds standalone prompt evaluations - test sets from real failures, paired A/B comparisons with sample-size math, deterministic checks before LLM judges, judge calibration and bias controls. Use when asked which prompt is better, to A/B test or benchmark prompts, or to set up LLM-as-judge scoring. Not for rewriting prompt text, agent goals, or loop runtime design.

Rewrites and tunes existing prompt text - removes contradictions, applies reasoning-vs-standard regime rules, sizes few-shot examples, fixes structured output, follows current Fable 5 / GPT-5.6 guidance, then checks the rewrite. Use when asked to optimize, improve, rewrite, shorten, tune, fix, or migrate a prompt or system prompt. Not for agent-run goal text, prompt benchmarks, or loop design.

Drafts or fixes the goal text for an autonomous agent run (/goal, unattended sessions) - checkable success conditions, evidence requirements, scope and permission limits, retry and budget exits. Use when writing an agent goal, run definition of done, or run success criteria, or when a goal gets gamed or marked done early. Not for generic project goals, prompt rewrites, or loop runtime design.

Records real terminal sessions to asciicast .cast files with asciinema 3.x - interactive or headless/scripted capture with clean-environment hygiene so machine details and secrets stay out. Use when the user asks to record, capture, or rec a terminal session, command run, or shell activity. Not for authoring scripted demo tapes/gifs, redacting, or rendering casts.

Scrubs secrets, tokens, usernames, and machine paths from asciicast .cast recordings before publishing - scan and rewrite via a bundled script that catches secrets split across events and in headers. Use when the user wants to redact, sanitize, scrub, mask, or scan a terminal recording for leaked credentials. Not for editing .env files, trimming casts, or rendering.

Renders asciicast .cast recordings into themed GIFs and MP4s with agg, gifsicle, and ffmpeg - trimming, speed and idle control, brand or neutral themes, size budgets, README embedding. Use when the user asks to convert, render, trim, speed up, optimize, or embed an existing terminal recording. Not for creating demos from scratch, capturing sessions, or general video files like screen recordings.

Creates polished terminal demo GIFs/MP4s as code with VHS .tape scripts - simulated typing, themed terminal, hidden setup, reproducible re-renders for READMEs and docs. Use when the user wants to make, script, or fix a terminal demo, demo gif, or CLI showcase from scratch. Not for recording live sessions or converting existing .cast files.