Top Agent Skills

Resume a paused experiment. Checkout the experiment branch, read results history, continue iterating.

RNA velocity analysis with scVelo. Estimate cell state transitions from unspliced/spliced mRNA dynamics, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data. Complements Scanpy/scVI-tools for trajectory inference.

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

Connect Claude to any app. Send emails, create issues, post messages, update databases - take real actions across Gmail, Slack, GitHub, Notion, and 1000+ services.

Production-ready financial analyst skill with ratio analysis, DCF valuation, budget variance analysis, and rolling forecast construction. 4 Python tools (all stdlib-only). Works with Claude Code, Codex CLI, and OpenClaw.

Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.

Turn "is this account a real fit?" into a stacked verdict. A composite 0-100 fit score built from every signal you have, a breakdown by source, override flags for when a scoring tool is wrong, a channel classification, and a written rationale. Built for reps, marketers, and RevOps, customizable to your CRM and whatever scoring you use. Trigger on "is {account} a real fit?", "score this list against our profile", "find lookalikes to our best customers", "why is the score wrong on {account}?", "validate this prospect list", "what's our coverage in {segment}?", or any account or list qualification.

Your won/lost/churn pattern analyst. Connect a CRM plus a product-analytics tool, then turn retrospective data into forward-looking action. Three modes. (1) WON, win pattern recognition that feeds your ICP and lookalike search. (2) LOST, loss pattern plus competitive intel that feeds a messaging refresh. (3) CHURN, churn theme extraction plus predictive scoring (which active accounts look like recent churners?). Trigger on "why are we winning?", "why are we losing?", "closed-lost autopsy", "churn patterns", "competitive intel rollup", "who do we lose to most?", "show me lookalike candidates to {winning customer}", "predictive churn", "which active accounts look like churners?", or any portfolio-level pattern recognition.

Deal Intelligence

Re-onboard a churned customer with the same care they got the first time. Reads why they left and whether they left the door open, picks the ones worth winning back, and builds a warm re-onboarding sequence, not a "we miss you" discount blast. Built for any post-sale or growth team, customizable to your product and win-back window. Trigger on "win back churned customers", "re-engage a lost account", "build a win-back sequence", "which churned customers should we chase", "boomerang play", "re-onboard a customer who left", or any win-back question.

Pipeline Intelligence

Audits any draft against Built GTM voice rules and returns specific, line-level violations with rewrites. Not a general style critique. A rule-based QA check. Every violation gets a specific fix. Trigger on "check this", "does this sound like me", "voice check", "is this on brand", "review this draft", "what's wrong with this", "flag the AI tells in this", "make sure this sounds like me", or any request to audit a draft against Heath's Built GTM voice before publishing. Can be used on posts, articles, newsletter editions, comments, or any Built GTM content.

Define your ICP the way a context repo needs it, so every downstream skill runs on real fit instead of a vague category. Named tiers with explicit criteria (not "Series B SaaS"), the technographic and organizational signals that indicate fit, an explicit anti-ICP, a qualification framework with must-haves separate from red flags, and an evolution log. Feeds context/icp-definition.md. Fire on "define our ICP", "who are we for", "ICP tiers", "write our ICP", "anti-ICP", "qualification criteria", or the start of building a GTM context repo.

Your customer-interview target finder. Connect Salesforce (CSM-managed customer book) and a canonical ICP doc — turns "who should I interview to validate the ICP, test the positioning, learn how they found us?" into a ranked slate of ~20 customers, each with a verdict, three-bullet why, and one named buying-committee recipient ready for a CSM-mediated intro. Use when a founder, GTM leader, or PMM is starting an ICP-validation round, testing new positioning, building a win-story program, or scouting reference customers. Trigger on "find customers to interview", "ICP validation interviews", "test our positioning with customers", "customer interview targets", "who in my book matches the ICP", "build a customer research slate", "find reference customers", "who should we talk to about how they found us", "validate the ICP with real customers", or any request to convert a CSM or AE book into a prioritized interview slate. Also fires when a new ICP doc ships and needs socializing with the customers who define it.

Use when the user wants to generate social media captions, posts, hashtags, or content for Instagram, LinkedIn, Twitter/X, Facebook, or YouTube using Gemini CLI. Trigger phrases: Gemini CLI social media, generate Instagram captions via terminal, bulk social posts with Gemini, LinkedIn content CLI. For ad copy see gemini-cli-copywriting.

Use when the user wants to build a content strategy, content calendar, editorial plan, or pillar content architecture using Gemini CLI. Trigger phrases: Gemini CLI content strategy, build content calendar via CLI, content plan with Gemini, content pillars generator CLI. For individual posts see gemini-cli-social.

Comprehensive guide to axum. Master the concepts, implementation, best practices, and real-world applications of axum in professional environments.

Comprehensive guide to a2c. Master the concepts, implementation, best practices, and real-world applications of a2c in professional environments.

Comprehensive guide to dpo. Master the concepts, implementation, best practices, and real-world applications of dpo in professional environments.

Comprehensive guide to gat. Master the concepts, implementation, best practices, and real-world applications of gat in professional environments.

Comprehensive guide to nas. Master the concepts, implementation, best practices, and real-world applications of nas in professional environments.

Comprehensive guide to pca. Master the concepts, implementation, best practices, and real-world applications of pca in professional environments.

Comprehensive guide to sam. Master the concepts, implementation, best practices, and real-world applications of sam in professional environments.

Comprehensive guide to hdfs. Master the concepts, implementation, best practices, and real-world applications of hdfs in professional environments.

Comprehensive guide to webgl. Master the concepts, implementation, best practices, and real-world applications of webgl in professional environments.

Comprehensive guide to byol. Master the concepts, implementation, best practices, and real-world applications of byol in professional environments.

Comprehensive guide to ddpm. Master the concepts, implementation, best practices, and real-world applications of ddpm in professional environments.

Comprehensive guide to glow. Master the concepts, implementation, best practices, and real-world applications of glow in professional environments.

Comprehensive guide to mish. Master the concepts, implementation, best practices, and real-world applications of mish in professional environments.

Comprehensive guide to qmix. Master the concepts, implementation, best practices, and real-world applications of qmix in professional environments.

Comprehensive guide to sgan. Master the concepts, implementation, best practices, and real-world applications of sgan in professional environments.

Comprehensive guide to umap. Master the concepts, implementation, best practices, and real-world applications of umap in professional environments.

Comprehensive guide to loki. Master the concepts, implementation, best practices, and real-world applications of loki in professional environments.

Comprehensive guide to webgpu. Master the concepts, implementation, best practices, and real-world applications of webgpu in professional environments.

Comprehensive guide to codex. Master the concepts, implementation, best practices, and real-world applications of codex in professional environments.

Comprehensive guide to glove. Master the concepts, implementation, best practices, and real-world applications of glove in professional environments.

Track technical changes with structured records, a state machine, and session handoff. Usage: /tc <init|create|update|status|resume|close|export|dashboard> [args]

Language-specific super-code guidelines for cpp.

Language-specific super-code guidelines for php.

Database management, forms, reports, and data operations with LibreOffice Base.

Language-specific super-code guidelines for dart.

RICE feature prioritization with scoring and capacity planning. Usage: /rice prioritize <features.csv> [options]

Build content-focused websites with Astro — zero JS by default, islands architecture, multi-framework components, and Markdown/MDX support.

Documentation and capabilities reference for Daily

Help a user learn a topic through adaptive tutoring, lesson planning, practice, retrieval checks, explanations, study guides, or exercises. Use when the user asks to learn, understand, practice, drill, review, study, or be tutored on something.

Analyze sprint retrospectives for patterns and action item tracking. Usage: /retro analyze <retro_data.json>

Language-specific super-code guidelines for swift.

ALWAYS use this skill when committing code changes — never commit directly without it. Creates commits following Sentry conventions with proper conventional commit format and issue references. Trigger on any commit, git commit, save changes, or commit message task.

Decide

Freeze

Use when creating or editing a macOS LaunchAgent for a recurring or scheduled script. Covers plist structure, PATH resolution, multiple trigger times, the reload workflow, and which behaviors launchd already handles so they don't need to be rebuilt.

Use when a draft needs the writer's voice and style principles applied

Invoke after the agent has stopped, whether the user interrupted it or it paused on its own, to have it resume and stop asking for permission it doesn't need for the rest of the conversation.

Use when creating a note, document, script or project that shouldn't outlive a known date — interview prep, a migration, a course, a time-boxed experiment — so it gets deleted on time instead of rotting in the repository.

Use when the user wants to run one or more generators from `@landonschropp/generate` (initialize, prettier, only-allow, eslint, typescript, vitest, bun-test, husky).

Use when writing or modifying tests for Ink (terminal UI) components.

| Use when reviewing an incoming GitHub pull request — runs the multi-level (L1-L5) audit against the PR's real diff range, posts findings as one batched review (inline, summary, or local-only), offers the standard fix chain on NEEDS_FIX, and optionally merges. The maintainer-side counterpart to /hyperflow:issue. Trigger with /hyperflow:pr, "review PR #N", "review this pull request <url>", "audit the PR", "check this contribution".

Analyze GitHub Actions failures and identify root causes

Analyzes what is done and the users query and offers advice on what to do next. Use if user says what should I do next or what do I do now or I'm stuck or I don't know what to do

Runs repeatable AI work as checked, budgeted workflow files.