Computes finite-temperature CALPHAD equilibria, phase fractions, and phase compositions from thermodynamic TDB databases using pycalphad. Use for alloy phase stability, equilibrium temperature sweeps, tie lines, lever-rule checks, or reproducible phase-fraction calculations with explicit components and mole-fraction conditions.

Official GSAP skill for timelines — gsap.timeline(), position parameter, nesting, playback. Use when sequencing animations, choreographing keyframes, or when the user asks about animation sequencing, timelines, or animation order (in GSAP or when recommending a library that supports timelines).

Apply the "learning mechanics" framework — the emerging physics-style theory of deep learning training dynamics — when writing, debugging, scaling, or tuning neural-network code. Use for decisions about learning rate / batch size / width / depth scaling, μP (Maximal Update Parameterization) and hyperparameter transfer, edge-of-stability and progressive sharpening, lazy vs. rich (feature-learning) regimes and initialization scale, neural scaling laws, gradient-flow conservation laws / symmetries, neural collapse, the neural feature ansatz, and for designing scientific experiments on training. Trigger phrases: "learning mechanics", "why is training unstable", "how should I scale the learning rate with width/batch", "muP / mup / hyperparameter transfer", "edge of stability", "lazy vs rich", "feature learning regime", "scaling laws", "tune hyperparameters on a small model". Source: Simon et al., "There Will Be a Scientific Theory of Deep Learning" (2026).

Opens a GitHub Pull Request with the standard PR template: Description, Staging Links, and JIRA ticket. Infers the ticket from the branch name and generates staging preview URLs from changed files after the PR is created. TRIGGER when: user asks to open, create, submit, make, update, or edit a PR or pull request, or wants to refresh staging links on an existing PR.

Constructing and interpreting Honeycomb queries on trace, log and event datasets: operation selection (percentiles not AVG, HEATMAP for distributions), relational fields (root., parent., any., none.), calculated fields, query math, and reading results (P99/P50 ratios, heatmap bands, TOTAL/OTHER rows, raw JSON via query_result_json). Trigger phrases: "show me latency", "error rate", "find slow requests", "find outliers", "interpret results", "relational fields", "calculated fields", "download raw results". For metrics datasets (dataset_type=metrics) use metrics-queries.

Configures canonical/gh-jira-sync-bot in a repository by creating or updating .github/.jira_sync_config.yaml following the platform-engineering-charm-template conventions, then validates it. Use when a repository needs GitHub-to-Jira issue synchronization or its Jira sync config must be created, fixed or audited.

SwiftUI ↔ Figma translation. Use whenever the user mentions Swift, SwiftUI, iOS, iPhone, or iPad — in EITHER direction — translating a Figma design into SwiftUI (design → code), or pushing SwiftUI views / screens / tokens back into a Figma file (code → design). Triggers on phrases like 'implement this Figma design in SwiftUI', 'build this screen in Swift', 'push this SwiftUI view to Figma', 'mirror my Swift code in a Figma file', or whenever a Figma URL appears alongside `.swift` files / an `.xcodeproj`. Routes to a direction-specific reference doc; loads alongside `figma-use` for the code → design path.

Record a demo video of a web app feature or flow on a real desktop (Docker, Xvfb, XFCE, real X cursor), producing an mp4 plus a click/hover/scroll/type telemetry file. Takes a flow description, an existing demo name or path, or init. Use when the user says "record a demo of the checkout", "gravar um demo dessa feature", "make a screencast of this flow", "video for the changelog", "re-record the checkout demo", "refresh the demo video", or "demo init". Do NOT use for general browser testing or automation that needs no video (use playwright-skill), page debugging or network inspection (use chrome-devtools), or static screenshots.

Use when challenging ideas, plans, decisions, or proposals. Invoke to play devil's advocate, run a pre-mortem, red team, stress test assumptions, audit evidence quality, or find blind spots before committing. Do NOT use for building plans, making decisions, or generating solutions — this skill only challenges and critiques. For a multi-agent panel that challenges and then commits to a verdict, use the-jury.

Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.

Use when a pull request changes a voice agent and the repository's committed Cekura test suite has to keep up: "update the tests for this PR", "extend test coverage for these changes", "does this PR need new voice tests", "keep cekura.tests.json in sync", "add a regression test for this bug fix", "review the suite against my diff", "run a test writer on every PR". Reads the PR diff against its merge base, decides per change whether existing cases already cover it, and makes the smallest edit that closes a real gap — most often no edit at all. This skill updates an existing suite; it never creates one from scratch (use cekura-infra-test-suite), never authors dashboard evaluators (use cekura-eval-design), and never places a live call.

Turns a hard product or career decision into a one-page decision memo with the eigenquestion, options, pre-mortem with kill criteria, reversibility rating, a named decider and a review date. Use when you ask 'how should we decide', 'should we build or kill this', 'one-way door or two-way door', 'run a pre-mortem', 'we keep going in circles', 'quit or pivot', or want to grade a decision doc. Draws on 396 insights from 177 Lenny's Podcast guests, led by Annie Duke, Shreyas Doshi and Shishir Mehrotra.

Update Codex's pinned `v8` / `rusty_v8` versions, validate the release-candidate path, and investigate failed V8 canary or artifact builds. Use when asked to bump V8, update `rusty_v8` artifacts, prepare or validate a V8 release candidate, check `v8-canary`, or diagnose why a V8 version update no longer builds.

Create professional, studio-grade PDF documents with bold editorial design quality. Use this skill whenever the user asks for a high-quality PDF, professional book, manual, playbook, report, ebook, whitepaper, or any multi-page document that needs magazine-quality layout. Also trigger when: "make it look professional", "studio grade", "publication quality", "book layout", "editorial design", or any request to transform markdown/text content into a beautifully designed PDF. This skill handles everything from single-page reports to full 300+ page books with cover pages, table of contents, styled code blocks, chapter openers, headers/footers, and custom typography. Do NOT use for simple PDF merging, splitting, or form-filling — those are basic PDF tasks.

Manage ClaudeBar's GitHub Actions CI/CD pipelines: build, test, and release workflows. Use this skill when: (1) Setting up secrets for CI/CD (certificate, API key, Sparkle key, Codecov) (2) Creating a new release — tag-based or manual workflow_dispatch (3) Triggering or explaining the build.yml, tests.yml, or release.yml workflows (4) Debugging release failures (signing, notarization, appcast) (5) Managing beta vs stable channels for Sparkle auto-updates (6) User says "release a new version", "push a tag", "set up CI secrets", "why did the release fail"

Design MVPs, validated learning experiments, and pivot-or-persevere decisions using Build-Measure-Learn. Use when the user mentions "MVP scope", "validated learning", "pivot or persevere", "vanity metrics", "test assumptions", "innovation accounting", "build-measure-learn", "minimum viable experiment", "should we pivot", "test a business idea cheaply", or "build the smallest version first". Also trigger when deciding what to include in a first version, measuring startup progress, or evaluating whether to change direction on a product bet. Covers innovation accounting and actionable metrics. For 5-day prototype testing, see design-sprint. For customer motivation analysis, see jobs-to-be-done.

Run a structured 5-day process to prototype, test, and validate product ideas with real users. Use when the user mentions "design sprint", "validate before we build", "rapid prototype", "test with users", or "should we build this". Also trigger when a team is stuck in endless debate over a high-stakes product decision, or wants to de-risk a costly idea before investing in development. Covers mapping, sketching, deciding, prototyping, and testing across Monday-Friday. For ongoing experimentation and MVPs, see lean-startup. For customer job analysis, see jobs-to-be-done. For non-leading user interviews, see mom-test.

Run a structured 5-day process to prototype, test, and validate product ideas with real users. Use when the user mentions "design sprint", "validate before we build", "rapid prototype", "test with users", or "should we build this". Also trigger when a team is stuck in endless debate over a high-stakes product decision, or wants to de-risk a costly idea before investing in development. Covers mapping, sketching, deciding, prototyping, and testing across Monday-Friday. For ongoing experimentation and MVPs, see lean-startup. For customer job analysis, see jobs-to-be-done. For non-leading user interviews, see mom-test.

Create a pull request for the current branch. Handles uncommitted changes, generates a PR title matching the `[{modules}] {type}: {description}` format enforced by CI, and fills in the PR description template. Trigger: 'create pr', 'open pr', 'submit pr', 'make pr'.

Selects, deploys, and customizes AI models on Amazon SageMaker. Training or Processing jobs, fine-tuning (SFT/DPO/RLVR/RLAIF), model selection, dataset preparation, evaluation, SageMaker or Bedrock deployment, inference optimization and endpoint diagnostics. Covers the full lifecycle from planning through production. Use when fine-tuning models on SageMaker, choosing which base model to customize, fine-tune, or deploy from SageMaker JumpStart or Hub, SageMakerPublicHub, or the SageMaker public model catalog, transforming or validating training data, evaluating model quality, deploying or optimizing endpoints, configuring IAM/S3 for training, or managing SageMaker Managed MLflow. Use for endpoint health, failures, latency, logs, metrics, errors. Covers Serverless Model Customization, Nova and OSS deployment paths, and PySDK v3. NOT for Ground Truth labeling, Feature Store, or general-purpose AWS infrastructure.