Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.

Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.

Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.

Stellar spectral analysis from first light to chemical abundance. Covers continuum emission and absorption, the OBAFGKM classification sequence, luminosity classes, line identification, Doppler shifts, curve-of-growth abundance analysis, and the astrophysical conclusions that follow from a spectrum. Use when classifying a star, measuring radial velocity, inferring composition or temperature, or teaching why the Sun is mostly hydrogen.

Use when the user reports a bug they can't reproduce, asks where to start debugging, or mentions a Heisenbug / production-only failure. Drives the observe→hypothesize→predict→test→iterate scientific method.

Recognition and mitigation of systematic reasoning errors documented in the heuristics and biases tradition. Covers confirmation bias, availability, anchoring, representativeness, framing effects, hindsight bias, overconfidence, and motivated reasoning. Each bias is presented with its mechanism, diagnostic signal, and structured mitigation. Use when you suspect your own or another reasoner's conclusions may be shaped by systematic cognitive distortion rather than evidence.

Evaluating the quality, provenance, and relevance of evidence that supports or undermines a claim. Covers source credibility, sampling quality, study design, levels of evidence (anecdote to meta-analysis), base rate integration, distinguishing primary from secondary sources, and calibrating belief to evidence strength. Use when the question is not whether an argument is valid but whether its premises are actually supported by the available data.

Bias detection and mitigation, fairness metrics, privacy frameworks, consent models, transparency requirements, and accountability structures for data science practice. Covers algorithmic bias sources, disparate impact testing, differential privacy, GDPR principles, model cards, datasheets for datasets, responsible AI frameworks, and the organizational governance needed to make ethics actionable. Use when auditing models for bias, designing privacy-preserving systems, establishing governance processes, or evaluating the social impact of data-driven decisions.

Crafts professional git commit messages following Conventional Commits. Use when committing changes or writing commit messages.

Systematic departures from rational choice theory and their implications for economic analysis and policy. Covers cognitive heuristics (anchoring, availability, representativeness), biases (loss aversion, status quo, overconfidence), prospect theory (reference dependence, probability weighting, diminishing sensitivity), nudge theory and choice architecture, and the integration of psychological findings into economic models. Use when analyzing decision-making under uncertainty, evaluating policy interventions that exploit behavioral patterns, or assessing where standard rational-agent models break down.

Every electronic system is ultimately debugged at the bench with a small set of instruments. The skill of using them well is not about knowing which button to press but about knowing what quantity you

CAD fundamentals, 3D printing (FDM/SLA/SLS), CNC machining, workshop skills, rapid prototyping methodology, and testing of physical prototypes. Covers fidelity levels, material selection for prototypes, dimensional tolerancing, assembly planning, and the iterate-test loop. Use when building prototypes, selecting fabrication methods, planning physical tests, or choosing between prototyping technologies.

Technical writing, engineering specifications, reports, presentations, and documentation standards for engineering practice. Covers document types (requirements documents, test reports, design rationale, operations manuals), writing style, data visualization, engineering drawing standards, and oral presentation techniques. Use when writing engineering documents, presenting technical results, creating specifications, or learning documentation best practices.

Ecological organization, energy flow, food webs, biodiversity, succession, and species interactions. Covers trophic structure, primary productivity, nutrient transfer efficiency, keystone and foundation species, ecosystem services, carrying capacity, disturbance regimes, primary and secondary succession, and resilience metrics. Use when analyzing how living communities are organized, how energy and matter move through ecosystems, how disturbance and recovery shape landscapes, or why biodiversity matters for ecosystem function.

Assessing anthropogenic environmental impacts — pollution pathways, habitat destruction and fragmentation, land-use change, invasive species, overharvest, and extinction debt. Covers environmental impact assessment (EIA) methodology, exposure-effect relationships, population viability analysis, IPAT and ecological footprint frameworks, and strategic environmental assessment. Use when quantifying or forecasting human impacts on ecosystems, designing monitoring programs, or evaluating a proposed intervention against a baseline.

Historical argumentation, evidence-based writing, and oral history methods. Covers thesis development for historical arguments, evidence selection and deployment, counterargument construction and rebuttal, historical writing conventions, and the methodology of oral history as both source and practice. Use when constructing historical arguments, writing analytical essays, conducting oral history interviews, or assessing the quality of historical writing.

Primary and secondary source analysis for historical reasoning. Covers source classification, sourcing (author/context/purpose), corroboration across multiple sources, contextualization within time and place, and bias detection. Use when evaluating historical evidence, assessing source reliability, or constructing evidence-based historical arguments.

Comparative framing across contemplative and mind-body traditions — Sōtō Zen and Rinzai Zen, Theravada vipassana, Tibetan Vajrayana, classical yoga and its eight limbs, Daoist internal cultivation, secular MBSR and MBCT, engaged mindfulness as Thich Nhat Hanh teaches it, Christian contemplative prayer, Sufi dhikr, the Hesychast tradition of the Eastern Orthodox church — for the routing agent who has to understand where a user is already standing before recommending a practice. Covers the pedagogical voice of each tradition, the places they overlap, the places they genuinely disagree, and the non-sectarian framing the college department uses. Use when a user arrives with a prior tradition, when a query spans more than one tradition, or when the agent needs a vocabulary for what is shared and what is lineage-specific.

Martial arts as body discipline — the shared pedagogical structure across striking, grappling, and weapon arts (stance, distance, timing, ukemi, live partner work, graded ranking, and the ethical container the best schools enforce). Covers karate, judo, jiu-jitsu (Brazilian and traditional Japanese), aikido, kendo/kenjutsu, boxing, muay Thai, and wrestling at enough depth that an agent can place a user into a reasonable first-month practice and recognize the safety failures that matter most. Leans on Moshé Feldenkrais's judo background and Yang Jwing-Ming's martial scholarship for the internal-to-external bridge. Use for any query about beginning a martial art, training injury patterns, graded progression, or the ethics of combat training.

Birding by sight and sound — gestalt, song and call vocabulary, behavioral and habitat clues, and the discipline of producing eBird-grade records. Covers the vocabulary of bird field marks, the primary categories of vocalization, the habits of habitat-filtering, and the protocol for submitting records to a citizen-science database without degrading data quality. Use when the task is bird-specific observation or record-keeping.

Following what organisms do — behavior, metamorphosis, host-plant relationships, social dynamics, and the long-form ethograms that reveal how species actually live. Covers the vocabulary of ethology, the structure of a life cycle, the classic categories of species interaction, the discipline of recording behavior without premature interpretation, and the gap between a single observation and a statistically useful record. Use when the task is to understand or record what a species does rather than what it is.

Naming and classifying organisms through binomial nomenclature, the Linnaean hierarchy, type specimens, and the rules governing taxonomic authority and revision. Covers the structure of a scientific name, the ranks from domain to subspecies, the codes (ICZN, ICN, ICNP), and the modern phylogenetic refinements that reshape the classical system. Use when the task is to place a known organism in its formal hierarchy or to reason about how names change over time.

Nutrition is a discipline in which several first-order questions remain genuinely contested after decades of research, and in which many second-order claims that were popular in earlier decades did no

Provides chaos engineering best practices for resilience testing, fault injection, and game day planning. Use when designing resilience experiments, configuring chaos tools, planning game days, or when user mentions 'chaos engineering', 'resilience', 'litmus', 'game day', 'fault injection', 'chaos monkey', 'blast radius', 'steady state', 'failure mode'.

Parallel agent fleet dispatch with progress tracking and result aggregation. Launch N agents, monitor completion, merge results. Proven at 7-agent scale.

Provides CI/CD pipeline best practices for GitHub Actions, deployment strategies, and pipeline optimization. Use when setting up pipelines, configuring GitHub Actions, managing deployments, or when user mentions 'CI', 'CD', 'pipeline', 'GitHub Actions', 'deploy', 'workflow', 'build'.

Classical RCA asks "what component failed?" Systems-theoretic RCA asks "what *control* failed?" The difference is not cosmetic. An incident where no component is individually broken — every actor beha

Analytical evaluation of texts for argument quality, author purpose, bias, credibility, and rhetorical strategy. Covers the distinction between comprehension and critique, argument analysis (claims, evidence, reasoning, warrants), rhetorical appeals (ethos, pathos, logos), bias identification (selection bias, confirmation bias, loaded language, omission), source credibility evaluation (CRAAP test, lateral reading), propaganda techniques, media literacy, and multi-text synthesis. Use when evaluating arguments, identifying bias, assessing source reliability, analyzing rhetoric, or synthesizing across multiple texts on the same topic.

Synchronous immediate signaling channel for inter-agent communication. Implements latest-wins single-file nudge pattern for health checks, stall detection, and urgent pings.

Bayesian approach to statistical inference and decision-making. Covers prior specification, likelihood functions, posterior computation, conjugate priors, Markov chain Monte Carlo (MCMC), credible intervals, Bayesian hypothesis comparison (Bayes factors), hierarchical models, and the philosophical contrast with frequentist methods. Use when updating beliefs with data, specifying priors, computing posteriors, comparing Bayesian and frequentist approaches, or building hierarchical models.

Computational tools and algorithms for statistical analysis. Covers simulation, resampling methods (bootstrap, permutation tests), Monte Carlo methods, random number generation, numerical optimization (Newton-Raphson, EM algorithm), cross-validation, and reproducible analysis workflows. Emphasizes the bootstrap revolution and the shift from formula-based to computation-based inference. Use when implementing statistical procedures, running simulations, bootstrapping confidence intervals, performing cross-validation, or building reproducible analysis pipelines.

The technology design process from needs assessment through iteration, covering empathy mapping, design briefs, concept development, prototyping, user testing, and iterative refinement. Integrates design thinking methodology (Stanford d.school) with engineering design process (ITEEA) and Don Norman's human-centered design principles. Use when designing technology solutions, evaluating existing designs, running design sprints, or teaching the design cycle. Distinct from art/aesthetics -- this skill focuses on functional design that solves real problems for real people.

Religious ethics and practice across traditions — moral theology and its sources, the role of virtue, law, and narrative in ethical formation, ritual as ethical shaping, the relation of contemplative practice to ethical life, and comparative work on shared ethical ground (the golden rule, non-harm, care for the stranger) and genuine disagreement. Use when a query asks what a tradition requires of its adherents, how ritual and ethics interact, or how traditions agree and differ on specific moral questions.

"Mysticism" is a contested term. William James in the *Varieties of Religious Experience* (1902) identified four marks — ineffability, noetic quality, transiency, passivity — and treated mysticism as

Scripture interpretation across traditions — hermeneutics, exegesis, textual criticism, canonical formation, and the history of reading practices. Covers Jewish (Tanakh, Talmud, Midrash), Christian (Old and New Testament, patristic and medieval senses), Islamic (Qur'an, tafsir, asbab al-nuzul), and Daoist-Confucian classical commentary traditions. Use when a query involves reading a sacred or classical text, comparing how different traditions interpret the same passage, or understanding why a specific text is canonical to a specific community.

Systematic theology as a method — the organization of doctrine into a coherent structure with defined loci (God, creation, humanity, sin, Christ or analogous figure, salvation, church, last things, where applicable to tradition). Covers creedal formation, the history of doctrine, the distinction between dogmatic and systematic work, and the comparative shape of systematics across Western Christian, Eastern Christian, Jewish, and Islamic traditions. Use when a query asks about a specific doctrine, its historical development, or its place in a tradition's overall conceptual architecture.

Craft methodology for the trades — how skilled work is organized, decomposed, sequenced, and evaluated from first principles through finished artifact. Covers the craft arc (intent, layout, roughing, fitting, finishing, inspection), the distinction between process knowledge and product knowledge, and how craft traditions encode error-correction in their sequencing. Use when designing a new trade process, diagnosing a faltering one, or teaching craft structure to a learner.

Upstream version checking, agentskills.io spec compliance audit, Claude Code feature gap analysis. Activates on updates, version checks, or alignment work.

Generates knowledge pack content suites: vision documents, modules YAML, activities JSON, assessment frameworks, resource catalogs, and .skillmeta files. Shared by all 3 tier-specific author agents. Use when creating or updating pack content files.

Conversational guide for using tools/session-retro/observe.mjs to capture friction, wins, corrections, decisions, gaps, tool-use, and checkpoints as they happen during a session. Use at session start (to kick off the log), at inflection points (to record events), and at session end (to archive and feed the retrospective generator).

OpenStack backup operations skill for protecting cloud infrastructure through systematic backup strategies and disaster recovery procedures. Covers database backups (MariaDB full and incremental with mariabackup), configuration backups (globals.yml, inventory, Fernet keys), volume snapshots (Cinder LVM snapshots), image exports (Glance), instance snapshots (Nova), backup encryption (GPG/OpenSSL), retention policies (daily/weekly/monthly rotation), restore procedures (database point-in-time recovery, service rebuild), RPO/RTO planning, and disaster recovery drills. Use when planning backup strategy, scheduling automated backups, testing restore procedures, or executing disaster recovery.

Kolla-Ansible day-2 operations skill for post-deployment infrastructure lifecycle management. Covers service reconfiguration (globals.yml changes, config overrides, prechecks, targeted reconfigure with --tags), minor and major OpenStack upgrades (image pull, upgrade procedure, rollback), container management (restart, logs, health inspection), maintenance mode (compute disable, instance drain, host maintenance), password rotation, certificate renewal, and rolling updates. This skill is for operations after initial deployment -- the kolla-ansible deployment skill covers initial bootstrap and deploy.

OpenStack networking debug operations skill for SDN troubleshooting, packet tracing, and flow analysis. Covers OVS/OVN debugging (ovs-vsctl, ovs-ofctl, ovs-appctl, ovn-nbctl, ovn-sbctl, ovn-trace), security group analysis via OVS flow rules and conntrack, DHCP troubleshooting through namespace inspection and dnsmasq diagnostics, floating IP diagnosis with NAT rule and ARP verification, network namespace inspection (ip netns), MTU chain analysis for overlay networks, DNS resolution debugging, and east-west traffic diagnosis. Use when diagnosing network connectivity failures, tracing packets through the SDN stack, or analyzing flow tables in a running OpenStack cloud.

Generates complete construction documentation packages — BOM, installation sequences, commissioning checklists, and O&M manuals — from verified engineering designs.

When this skill is first used or when the user seems unsure how to use it or ask you to make something amazing with it, guide them to ask Claude this specific question:

Prepare and validate OpenSkills release readiness across runtime, bindings, examples, and regression gates with a deterministic checklist and go/no-go outcome.

Done

Done

This skill guides users through creating custom skills for claude-code-setup. Use when users want to create a new command or context skill.

Java coding standards for enterprise applications. Includes naming conventions, modern Java features, design patterns, and recommended tooling.