Results for “eval”

Audit agent skills, plugins, prompts, manifests, scripts, dependencies, and bundled assets for provenance, prompt-injection, permission, execution, exfiltration, persistence, and update risk. Use when evaluating a third-party skill before installing, enabling, updating, publishing, or distributing it; reviewing an untrusted SKILL.md, agent configuration, MCP integration, archive, or repository; comparing a package with a known-good version; or investigating unexpected tool, network, credential, or filesystem behavior.

Use when defining a feature's purpose and user value before building it, writing user stories, mapping user flows end-to-end, prioritizing what to build next, evaluating whether a feature solves a real problem, or reviewing scope to prevent over-engineering. Activate when user says "what should I build", "plan the feature", "is this the right approach", "define the requirements", or presents an idea without a clear user need.

Systematic methodology for auditing the Hermes Skills Hub (and external sources) to identify gaps, overlaps, redundancies, and conflicts when building a skill library for any project. Covers browsing, targeted searching, cross-referencing with web/GitHub, comparing candidates against existing inventory, verifying install safety, and planning installation order. Use when starting a new project and assembling tools, or when evaluating whether to add external skills beyond what's currently installed.

Generate and critically evaluate grounded ideas about a topic. Use when asking what to improve, requesting idea generation, exploring surprising directions, or wanting the AI to proactively suggest strong options before brainstorming one in depth. Triggers on phrases like 'what should I improve', 'give me ideas', 'ideate on X', 'surprise me', 'what would you change', or any request for AI-generated suggestions rather than refining the user's own idea.

Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.

Product strategy, market validation, commercial filtering, and MVP definition for Nick's workflow. Use when turning vague ideas into product plans, evaluating startup opportunities, identifying real market gaps, deciding if an idea should be killed before build, prioritizing features, shaping positioning, defining monetization, or judging whether a concept is strong enough to deserve design and engineering effort. Focus on painful problems, clear buyers, credible wedges, practical validation, and realistic paths to revenue.

Performs a gap analysis between two artifacts (a current state and a desired state) and produces a plain-language, stakeholder-readable report indexed by stable gap IDs. Use when the user wants to compare, evaluate, audit, or reconcile one artifact against another. Does not investigate runtime bugs — use investigate. Does not assess module-level architecture — use architectural-analysis. Does not research open-ended options with no second artifact to compare against — use research.

Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that don't fit in memory.

Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that don't fit in memory.

Use to push back-office work into Rulebase over the REST API so it can be evaluated like a conversation, with a dry-run plan, idempotent external ids and an audit log. Trigger for "send our back-office work to Rulebase", "push work items", "QA our operations team", "get case work into Rulebase", disputes or KYC queues with no customer on the line, or duplicate work items appearing after a re-run.

Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that don't fit in memory.

Out-of-core tabular analytics with Vaex for billion-row datasets that exceed RAM — lazy evaluation, fast aggregations, big-data visualization, and ML on a single machine. Use when working with large CSV/HDF5/Arrow/Parquet files, computing fast statistics on massive datasets, visualizing big data, or building ML pipelines that do not fit in memory. For distributed clusters prefer dask; for in-memory speed prefer polars. Part of the AlterLab Academic Skills suite.

Seed minimal agent harness v0 — manifest, eval checks stub, governance. AUTO-INVOKED after project-setup or retroactive-project-setup when docs/harness/manifest.json is missing. Also triggers on: generate harness, scaffold agents, agent bootstrap, first time agents in this repo, new project agent setup, set up agent harness, agent onboarding files, missing agent configuration, agent instructions setup, make agents read project rules, agent reliability setup, agents not configured. Pairs with project-setup. Evolution is harness-evolution.

Select, pair, and implement typefaces for web projects. Use when the user mentions "font pairing", "which typeface", "line height", "responsive typography", "web font loading", "type hierarchy", "variable fonts", "FOUT/FOIT", or "typographic scale". Also trigger when choosing between system fonts and web fonts, optimizing font loading performance, or designing readable long-form content layouts. Covers readability evaluation, CSS implementation, and performance optimization. For overall UI design systems, see refactoring-ui. For dramatic typographic experiences, see top-design.

Apply meta-principles of software craftsmanship: DRY, orthogonality, tracer bullets, and design by contract. Use when the user mentions "best practices", "pragmatic approach", "broken windows", "tracer bullet", "software craftsmanship", "technical debt prevention", "prototype vs tracer bullet", or "code ownership". Also trigger when evaluating build-vs-buy decisions, designing estimation approaches, or choosing between reversible and irreversible architectural decisions. Covers estimation, domain languages, and reversibility. For code-level quality, see clean-code. For refactoring techniques, see refactoring-patterns.

Failure diagnosis, DAG mutation, and escalation engine for the WinDAGs meta-DAG. Receives failure information and quality vectors from the Evaluator. Classifies failures on four dimensions. Follows a five-level escalation ladder. Applies seven mutation types with saga compensation. Enforces BC-EXEC-002, BC-EXEC-003, BC-FAIL-002, BC-FAIL-005. Activate when operating as the Mutator role in the meta-DAG, when diagnosing node failures, when restructuring a DAG at runtime, or when deciding escalation level.

Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, and use the GraphQL API. Use whenever the user is analyzing traces or spans, investigating LLM/agent failures, deciding what to do after instrumenting an app, building failure taxonomies, choosing what evals to write, or asking "what's going wrong", "what kinds of mistakes", or "where do I focus" — even without naming a technique.

Integrate antennas into RF systems using MATLAB Antenna Toolbox and RF Toolbox. Covers impedance matching network design (L/Pi/Tee topologies, evaluation parameters, Richards transformation), measured antenna creation (E-field, directivity-only, EmbeddedE, ffsReader import), RF propagation and site planning (txsite/rxsite, coverage, SINR, ray tracing, link budget), and SAR estimation (birdcage+Phantom, conformalArray+Custom3D, direct EHfields). Use when the user wants to match an antenna, create a measuredAntenna, compute coverage or signal strength, perform ray tracing, or estimate SAR.

Design habit-forming product loops using the Hook Model (Trigger, Action, Variable Reward, Investment). Use when the user mentions "users arent coming back", "engagement loops", "habit formation", "push notifications", "variable rewards", "daily active users", "habit zone", or "user retention loops". Also trigger when designing notification strategies, building streaks or progress systems, or analyzing why users stop using a product after initial signup. Covers ethics evaluation and onboarding for habits. For friction reduction and B=MAP, see improve-retention. For viral sharing, see contagious.

Improve agent reliability over time — diagnose why agents fail and fix the setup. Triggers on: agent keeps failing, same mistake again, agent not improving, make agent smarter, agent quality plateau, agents ignore skills, agent skips tests, fix agent behavior, agent unreliable, improve agent setup, self-improving harness, agents worse over time, tune agent instructions, agent going in circles, agent ignores AGENTS.md, repeated agent errors. Requires harness v0 and eval harness. AUTO-ROUTED from harness-engineering on symptoms. Not first setup — harness-generation first.

Amazon Ads deep analysis covering Sponsored Products, Sponsored Brands (incl. Sponsored Brands Video), Sponsored Display (audiences + contextual), and basic Amazon DSP. Evaluates campaign structure, ACOS/TACOS targets, search-term harvesting, negative keyword discipline, Brand Analytics signals, day-parting, bid management, auto vs manual campaign mix, ASIN targeting, and DSP retargeting. Use when user says Amazon Ads, Amazon advertising, Amazon PPC, Amazon search ads, Sponsored Products, Sponsored Brands, Sponsored Display, Amazon DSP, ACOS, TACOS, retail media audit, Amazon Marketing Services, AMS, or Amazon seller advertising.

Loads Therapeutics Data Commons (TDC, PyTDC) AI-ready drug-discovery datasets and benchmarks — ADME, toxicity, drug-target interaction (DTI), scaffold splits, and molecular oracles for therapeutic ML and pharmacological prediction. Use when fetching a standardized benchmark dataset, applying scaffold or cold-split evaluation, or sourcing labeled molecules for ADMET, toxicity, or DTI modeling. Sources data, splits, and oracles only — defer molecular featurization (ECFP/fingerprints), model training, and transformers to a molecular-ML skill (e.g. deepchem). Part of the AlterLab Academic Skills suite.

Read-only diagnostic that scans Claude Code session transcripts to surface which MCP servers and tools you actually use, ranked by call frequency, with zero-use servers flagged for removal. Use when planning an MCP cleanup, evaluating whether to keep a newly-added server, deciding which servers warrant token cost in the catalog, or before authoring an MCP-removal PR. Outputs a markdown report (last N days) — does not modify any settings. Pair with the manual `claude mcp remove <name>` step once findings are reviewed.

Import raw data (CSV, XLSX, TXT, or MATLAB tables) into formats used by Sensor Fusion and Tracking Toolbox. Handles both ground truth trajectories and sensor detection data. For truth: builds trackingScenarioRecording, tuning timetable, truthlog, or converted table. For sensor data: builds task-oriented dataFormat structs (preferred) or objectDetection arrays (legacy). Use when importing flight logs, GPS logs, radar detections, IR measurements, lidar/camera bounding boxes, ADS-B data, AIS ship tracks, or any recorded data for use with trackers, filter tuning, or tracker evaluation.

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", or "minimum viable experiment". 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.

This skill should be used when a SKILL.md file needs compression, deduplication, or token reduction. It provides an embedding-based compression pipeline that detects and removes redundant chunks within SKILL.md files using local embeddings (all-MiniLM-L6-v2). Two-pass approach: (1) free intra-skill deduplication via cosine similarity clustering, (2) optional LLM-judged graded eval to detect pretraining overlap. Typical result: 25-46% token reduction with zero quality loss. This skill is not intended for editing skill content, creating new skills, routing optimization, or cross-skill deduplication.

Operate and extend barretlee/agent-pulse, the evidence-backed AI industry intelligence system: inspect source catalog and lifecycle, collect and normalize signals, bind evidence, cluster Events, evaluate system health, generate Scout hypotheses, export the privacy-safe public site, and verify release gates. Use when the user asks to run, configure, debug, extend, or explain Agent Pulse, its collectors, Control Room, narratives, Scout, or GitHub Pages output. Triggers on: agent-pulse, Agent Pulse, evidence-backed intelligence, source catalog, signal collection, Event clustering, source audit, Scout opportunity, public export, weekly brief, or AI industry intelligence pipeline.

When the user wants to plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness. Also use when the user mentions "engineering as marketing," "free tool," "marketing tool," "calculator," "generator," "interactive tool," "lead gen tool," "build a tool for leads," "free resource," "ROI calculator," "grader tool," "audit tool," "should I build a free tool," or "tools for lead gen." Use this whenever someone wants to build something useful and give it away to attract leads or earn links. For downloadable content lead magnets (ebooks, checklists, templates), see lead-magnets.

Live developer experience audit. Uses the browse tool to actually TEST the developer experience: navigates docs, tries the getting started flow, times TTHW, screenshots error messages, evaluates CLI help text. Produces a DX scorecard with evidence. Compares against /plan-devex-review scores if they exist (the boomerang: plan said 3 minutes, reality says 8). Use when asked to "test the DX", "DX audit", "developer experience test", or "try the onboarding". Proactively suggest after shipping a developer-facing feature. (gstack) Voice triggers (speech-to-text aliases): "dx audit", "test the developer experience", "try the onboarding", "developer experience test".

Build multiple genuinely different versions of a UI piece you describe, rendered behind a visual picker so you can flip through them live and promote the one that feels right. Use this proactively, without waiting to be asked, whenever evaluating a new feature, a layout, a section, a visual, a design, or any UI decision — divergent options beat a single guess. Fast, no interview, single-component scope. For a full structured exploration (interview, 5 variants of a whole page, real feedback collection, implementation plan) when the direction itself is still open, use `design-lab` instead — that one requires explicit invocation. Source: github.com/emilkowalski/skills.

Review a built frontend against its chosen direction, catch drift back to generic AI defaults, enforce state coverage, ethical patterns, UX heuristics, and polish, and check contrast with APCA (not the legacy WCAG ratio). Produces specific, prioritized fixes — never vibes-based feedback. Works with pasted screenshots or Playwright MCP automated capture. Load when the user asks to review a UI, audit a design, check if a frontend looks generic or vibecoded, evaluate visual quality or polish, says "review this UI", "is this design good", "audit my frontend", "does this feel like [product]", "design QA", or when frontend-design routes here. Sub-skill of frontend-design.

Run a Virtual Think Tank — a structured multi-persona debate — before planning or making architectural/design/strategic decisions. Use this skill whenever the user is about to plan a system, make a technology choice, evaluate trade-offs, decide on an approach, or faces any decision where multiple perspectives would sharpen the outcome. Also trigger when the user says "think tank", "debate this", "perspectives on", "trade-offs", "should I use X or Y", "help me decide", "before we plan", or asks for pros/cons of competing approaches. This skill should run BEFORE any implementation planning begins — it produces a structured analysis that feeds into better plans.

Guardian Angel gives AI agents a moral conscience rooted in Thomistic virtue ethics. Rather than relying solely on rule lists, it cultivates stable virtuous dispositions— prudence, justice, fortitude, temperance—that guide every interaction. The foundation is caritas: willing the good of the person you serve. From this flow the cardinal virtues as practical habits of right action and sound judgment. v3.0 introduced virtue-based disposition as the primary evaluation layer, providing deeper coherence than checklists alone. The agent's character becomes the safeguard. v3.1 adds: Plugin enforcement layer with before_tool_call hooks, approval workflows for ambiguous cases, and protections for sensitive infrastructure actions.

Run a comprehensive code review on local source files. Use this skill when the user asks to review, audit, inspect, evaluate, or check code, even if they never use the word "review." Does not post comments to GitHub pull requests — use post-code-review-to-pr for that. Does not analyze architectural structure or module boundaries — use architectural-analysis for that. Does not explain code or a PR to build understanding before reviewing — use code-overview for a written overview, or code-walkthrough to be paced through it one step at a time. Does not capture feedback on Han's own skills — use han-feedback for that.

Performs deep architectural analysis of a specified module, directory, or feature area by examining structural coupling, data flow, concurrency patterns, risk, and SOLID alignment. Use when the user wants to assess, evaluate, or review the architecture, design quality, dependency structure, coupling, cohesion, or technical debt of an existing part of the codebase. Not for investigating specific bugs, runtime errors, or failures — use investigate. Not for test planning — use automated-test-planning. Not for file-level code review — use code-review. Not for researching open-ended options, prior art, or how something works — use research. Not for designing a new interface or contract — use design-an-api. Not for writing documentation or architectural decision records.

Simulates a full multi-reviewer journal review PANEL — 5 personas (Editor-in-Chief + 3 peer reviewers + a Devil's Advocate) debate a manuscript and produce a consensus Editorial Decision (accept/minor/major/reject) plus a prioritized Revision Roadmap. Modes: full, re-review (verify revisions addressed prior comments), quick, methodology-focus, Socratic guided. Use for: simulate peer review, mock review panel, editorial review before submission, multiple reviewer perspectives, re-review of a revised manuscript, or 'critique my paper hard'. For a single-reviewer referee report use alterlab-peer-review; for rubric/grade scoring use alterlab-scholar-eval; to write/revise the paper use alterlab-paper-writer. Part of the AlterLab Academic Skills suite.