AI & ML

gitwalter Bundle

Spawning subagents dynamically, parent-child agent communication, task delegation and result aggregation, resource management and cleanup

gitwalter Bundle

Build stateful agents and workflows with LangGraph 1.x

gitwalter Bundle

Onboard existing repositories into the Antigravity Agent Factory ecosystem

gitwalter Bundle

Convert team workshop outputs to project management artifacts

gitwalter Skill

Statistical analysis, predictive modeling, and automated insight generation

lonsdale201 Skill

Orient a developer making a WordPress plugin or theme compatible with WPML (sitepress-multilingual-cms). Explains WPML's mental model — it translates COPIES (each translation is a separate post/term with its own ID, linked by a trid in icl_translations), unlike live-translation plugins — and the three compatibility mechanisms — (1) a declarative wpml-config.xml, (2) the runtime language hook API (wpml_current_language, wpml_object_id, wpml_switch_language, wpml_permalink), (3) string registration /translation (wpml_register_string / wpml_translate_single_string). Covers detecting WPML with defined('ICL_SITEPRESS_VERSION'), the add-on split (String Translation WPML_ST_VERSION, Translation Management WPML_TM_VERSION, Media WPML_MEDIA_VERSION) and which features need which add-on, plus a decision matrix mapping intent to mechanism. Use when starting WPML compatibility, deciding config vs API vs strings, or detecting WPML / its add-ons.

lonsdale201 Skill

Build and review WordPress 7.1 WP AI Client integrations for provider-agnostic text, image, speech, video, JSON, and ability-powered generation. Covers wp_ai_client_prompt, WP_AI_Client_Prompt_Builder, wp_supports_ai, using_model_preference, is_supported_* checks, generate_* / generate_*_result methods, WP_Error handling, using_abilities, WP_AI_Client_Ability_Function_Resolver, connector-backed provider configuration, client-safe schemas, cache-group customization, prompt prevention filters, and safe AI feature gating. Use when plugin code calls AI models or adds AI-powered WordPress features.

magnus919 Bundle

Build LLM applications with the LlamaIndex framework. Use when working with LlamaIndex or comparing RAG and agent orchestration frameworks. Do not use this skill for unrelated requests; route to the nearest named specialist.

fndlalit Bundle

QCSD Ideation phase swarm for Quality Criteria sessions using HTSM v6.3, Risk Storming, and Testability analysis before development begins. Uses 5-tier browser cascade: Vibium → agent-browser → Playwright+Stealth → WebFetch → WebSearch-fallback.

magnus919 Bundle

Build type-safe AI agents and graph-based workflows with PydanticAI and PydanticGraph. Agent creation, function tools, capabilities, dependency injection, structured output, streaming, multi-agent patterns, testing, evals, and graph state machines. Use whenever you are building agents, tool-using LLM workflows, or graph-based state machines in Python. Do not use this skill for unrelated requests; route to the nearest named specialist.

magnus919 Bundle

Build or refactor agent-facing CLI tools with non-interactive commands, stable --help and --json contracts, idempotent operations, and --dry-run previews. Use for CLI design, agent-friction refactors, output/exit-code debugging, or automation safety. Do not use for GUI/TUI design, conversational tools, MCP server design, or general API architecture; use api-design-and-evolution for the latter.

bookforge-ai Bundle

Choose the correct consistency model (linearizability, causal consistency, or eventual consistency) for each operation in a distributed system, and select the matching implementation mechanism. Use when designing a new distributed data system, deciding whether ZooKeeper or etcd is needed for coordination, evaluating whether two-phase commit is appropriate for cross-node transactions, debugging correctness violations (stale reads, split-brain, uniqueness constraint failures), or distinguishing linearizability from serializability. Also use when applying the CAP theorem correctly (beyond the "pick 2 of 3" oversimplification), selecting total order broadcast as a consensus primitive, evaluating 2PC failure modes and lock-holding cost, or assessing whether causal consistency is sufficient in place of linearizability. Produces a per-operation consistency recommendation with replication mechanism, ordering guarantee, and — when consensus is needed — protocol selection (Raft, Zab, Paxos) with documented failure mode

lonsdale201 Skill

Consumer and reviewer reference for LW LMS Abilities API registrations in lw-lms v1.6.0. Use when calling or auditing `lw-lms/list-courses`, `lw-lms/get-course`, `lw-lms/get-progress`, `lw-lms/set-progress`, `lw-lms/get-options`, `/wp-json/wp-abilities/v1/abilities/lw-lms/.../run`, Site Manager bridge integration, standalone WP 6.9+ Abilities API fallback, ability `input_schema` / `output_schema`, or AI-agent access to LMS course/progress data.

lonsdale201 Skill

Orient skill for FluentCRM extension development. Covers the Free / Pro split (FluentCRM = funnel chassis; FluentCampaign Pro = integrations + advanced actions / benchmarks), plugin paths and constants, the bootstrap order (fluentcrm_loaded → fluentcrm_addons_loaded → init funnel listener passes → fluent_crm/after_init), the model layer (Subscriber, Company, EventTracker, Funnel, FunnelSequence, FunnelSubscriber, FunnelMetric), the global helpers (FluentCrmApi, fluentCrmDb, FunnelHelper), the contact lifecycle hooks (fluent_crm/contact_created, _updated, _email_changed, _custom_data_updated), the smart-code extension filter (fluent_crm/extended_smart_codes), and a decision matrix for picking the right extension contract. Use when scaffolding a new FluentCRM integration, choosing which contract to extend, or asking where things live. Triggers on FluentCrmApi, fluentCrmDb, FunnelHelper, fluent_crm/contact_, fluent_crm/extended_smart_codes, FLUENTCRM, FLUENTCAMPAIGN.

writer Bundle

Attribute health outcomes to specific clinical interventions, programs, or policy changes using causal inference methods. Use when determining which interventions drove observed improvements, allocating credit across concurrent programs, or defending outcome claims to payers and regulators.

magnus919 Bundle

Design, build, evaluate, govern, monitor, evolve, and retire digital twins and federated twin universes for software systems, engineering processes, agentic software factories, infrastructure, and cyber-physical operations. Use when a task involves digital-twin architecture, digital thread, simulation, predictive maintenance, twin health, agent authority, or dark-factory design. Do not use for ordinary observability dashboards, static dependency graphs, generic AI governance, or operating one named infrastructure tool without a twin-specific representation and feedback loop.

magnus919 Bundle

Analyze gaps by comparing a defined current state with a justified target state, characterizing causes and uncertainty, prioritizing actionable interventions, and producing traceable matrices, roadmaps, and decision records. Use for capability, process, compliance, readiness, maturity, operating-model, or research-evidence gaps. Do not use for a vague list of problems, a standalone root-cause analysis, a generic SWOT, or legal or audit certification advice without a governing standard and qualified owner.

magnus919 Bundle

Run a structured multi-agent debate by spawning a panel of expert agents on any question, with convergence-aware iteration and typed synthesis output via the `agent-council` CLI. Use when a decision has genuine tradeoffs, high stakes, or hidden assumptions worth adversarial collaboration, or when confidence diagnostics matter more than a single recommendation. Compatible with any AI agent harness that supports agentskills.io skills (Claude Code, Cursor, Hermes Agent, OpenHands, etc.). Do not use for simple factual lookups, tasks with a clear correct answer, routine single-perspective work, or code execution and tool orchestration beyond debate.

magnus919 Bundle

Design and operate an organization's AI governance system: define governance principles, operating models and decision rights, risk frameworks, lifecycle gates, and fairness, transparency, privacy, security, regulatory, and board-oversight controls. Use when standing up a governance program, tiering AI use-case risk, reviewing an LLM or agent system for governance and safety gaps, mapping a regulation to a compliance plan, scoring governance maturity, or preparing board reporting. For regulated life-sciences use cases, also cover GxP, ALCOA+, data integrity, electronic records, validation/assurance, and QMS interfaces. Do not use for interpreting regulations as legal advice (route to legal-strategy), data-governance mechanics (data-architect/data-engineering), or implementing application security (secure-software-engineering).

lonsdale201 Skill

WooCommerce Memberships 1.29+ WordPress Abilities API reference for membership plan, user membership, and per-post content restriction rule abilities, category slugs, registration requirements, permissions, schemas, annotations, REST route exposure, and safe automation guardrails. Use when code or a task mentions wp_register_ability, wp_get_ability, WP Abilities API, woocommerce-memberships/plans-create, plans-delete, plans-get, plans-list, user-memberships-create, user-memberships-delete, user-memberships-get, user-memberships-list, post-restriction-rules-get, post-restriction-rules-update, /wc-memberships/v1/post-restriction-rules, or privileged agent/headless/admin automation for WooCommerce Memberships.

bookforge-ai Bundle

Determine the appropriate level of architect control over a development team using a quantitative 5-factor scoring model (-100 to +100 scale). Use this skill whenever the user asks how much they should be involved in a team's decisions, how hands-on or hands-off to be as an architect, how to calibrate their leadership style, whether they are micromanaging developers, whether they should give the team more autonomy, or any question about architect involvement level, team oversight, or technical leadership balance — even if they don't explicitly say "control." Also triggers when the user describes team dysfunction symptoms like merge conflicts increasing, nobody speaking up in meetings, or tasks falling through cracks.

bookforge-ai Bundle

Choose a replication topology (single-leader, multi-leader, or leaderless) and configure it correctly — including sync vs. async mode, quorum parameters (w + r > n), and consistency guarantees. Use when designing replication for a new system, configuring quorum values for Cassandra/Riak/DynamoDB, deciding how to handle multi-leader write conflicts, or comparing PostgreSQL/MySQL streaming replication vs. CouchDB multi-leader vs. Cassandra leaderless for your architecture. Also use for: selecting a conflict resolution strategy (last-write-wins vs. version vectors); designing multi-datacenter replication; choosing between WAL shipping, logical replication, and statement-based replication log formats. For diagnosing an existing replication failure (failover gone wrong, lag spike, quorum misconfiguration, split brain), use replication-failure-analyzer instead. For consistency model selection (eventual vs. causal vs. linearizable), use consistency-model-selector instead. For partitioning strategy, use partitioning-

writer Bundle

Explain data traceability and lineage for financial institution data assets. Use when documenting data flows for regulatory reporting, tracing data from source to consumption, assessing data quality risks, supporting model risk management, or responding to BCBS 239 and FFIEC data governance expectations.

writer Bundle

Document and explain model risk management decisions aligned with SR 11-7 and OCC 2011-12 supervisory guidance. Use when creating model validation reports, model inventory documentation, model risk assessments, ongoing monitoring plans, or responding to MRM examination findings.

bookforge-ai Skill

Systematically test web application access controls for broken authorization vulnerabilities. Use this skill whenever: performing a penetration test or security assessment of a web application's authorization model; testing for vertical privilege escalation (low-privilege user accessing high-privilege functions); testing for horizontal privilege escalation (user accessing another user's data); auditing multistage workflows for mid-flow authorization bypasses; checking whether protected static files are directly accessible without authorization; testing whether HTTP method substitution (HEAD, arbitrary verbs) bypasses platform-level access rules; probing for insecure access control models based on client-submitted parameters (admin=true), HTTP Referer headers, or IP geolocation; enumerating hidden or unlisted application functionality; reviewing source code or HTTP traffic for missing server-side authorization checks; using Burp Suite's site map comparison feature to compare high-privilege and low-privilege us

bookforge-ai Skill

Review a system design for security and reliability tradeoffs before implementation begins. Use when: evaluating an architecture proposal or design document and need to identify where security and reliability requirements conflict with feature or cost requirements; auditing a proposed design to determine whether security and reliability are designed in from the start or likely to require expensive retrofitting later; deciding whether to build payment processing or sensitive data handling in-house versus delegating to a third-party provider; assessing whether a microservices framework or platform incorporates security and reliability by construction rather than by convention; or producing a design review report for a security review, production readiness review, or architecture decision record. Applies the emergent property test (security and reliability cannot be bolted on — they must arise from the whole design), the initial-versus-sustained-velocity model (early neglect accelerates to later slowdown), and t

magnus919 Bundle

Use for PhD-level expertise in data science, statistics, and machine learning: rigorous statistical analysis, experimental design, causal inference, advanced modeling, research methodology, or data science project leadership. Load when the user asks about statistical methods, experimental design, model selection, A/B testing, hypothesis testing, power analysis, regression, causality, Bayesian analysis, or research methodology. For insurance, actuarial, claims, reserving, solvency, credibility, tail-risk, or financial-risk statistical modeling, use `actuarial-risk-modeling`; for deterministic operating and SaaS financial models, use `financial-modeling`. Do not use this skill for unrelated requests; route to the nearest named specialist.

magnus919 Bundle

Plan and execute production ML engineering work — model training and fine-tuning (LoRA/QLoRA), evaluation and eval-set design, quantization decisions, inference deployment, and regression triage, grounded in practical engineering patterns for production ML systems. Do not use for statistical modeling and experimental design (that's the data scientist) or for operating a specific inference engine (that's a tool skill such as llama-cpp or vllm).

magnus919 Bundle

Teach promise vocabulary, fundamentals, and coordination diagnosis for promise-based systems. Do not use this skill for Semantic Spacetime models or SST CLI tooling; use `semantic-spacetime` for those model and tool workflows.

bookforge-ai Skill

Profile the likely adversaries targeting a system and produce a structured threat model with prioritized threat scenarios. Use when: designing a new system or service and need to identify who might attack it and how; evaluating whether existing security controls address the right threats; preparing a threat model document for a security review, compliance audit, or architecture decision record; assessing insider risk for a system that handles sensitive data or privileged operations; or mapping attack lifecycle stages to defensive controls. Applies the three adversary frameworks — attacker motivations, attacker profiles, and attack lifecycle stages — alongside a four-dimension actor-motive-action-target threat scenario matrix to produce ranked threat scenarios. Distinct from vulnerability assessment (which audits specific technical flaws) and penetration testing (which actively exploits weaknesses). Produces: adversary profile summary, insider risk matrix, threat scenario list ranked by likelihood and impact,

lonsdale201 Skill

Configures the JetFormBuilder action events system — the named events (DEFAULT.PROCESS, DEFAULT.REQUIRED, GATEWAY.SUCCESS, GATEWAY.FAILED, BAD.REQUEST, ON.DYNAMIC_STATE, never) that decide WHEN a Form Action runs. Covers declaring supported / unsupported / required events on a custom action, the validation precedence inside Base_Event::is_valid_action(), the multi-event subscription model the action editor exposes, and how to register a brand-new event type via the 'jet-form-builder/event-types' filter using Base_Event, Base_Action_Event, or Base_Gateway_Event. Use when an action must run only on payment callbacks, validation failure, a conditional state, another action's hidden flow, or when defining a custom event class (e.g. inbound webhooks). Triggers on mentions of "JFB events", "action events", "GATEWAY.SUCCESS", "DEFAULT.PROCESS", "supported_events", "unsupported_events", "get_required_events", "Base_Event", "Base_Gateway_Event", "jet-form-builder/event-types", "before-trigger-event", "add_hidden".

lonsdale201 Skill

Build a custom FluentCRM funnel action — a per-contact sequence step run when an automation reaches it — by extending BaseAction. Covers the three abstract methods (getBlock, getBlockFields, handle), the per-step handle($subscriber, $sequence, $funnelSubscriberId, $funnelMetric) signature, and the skip / failure semantics — handle ONLY overrides status on early-return, because FunnelProcessor::processSequence already marks the sequence 'complete' BEFORE dispatch. last_sequence_status uses 'complete' but successful FunnelMetric rows use the model default 'completed' — do not normalize the two. On skip/failure update both the sequence-subscriber row (via FunnelHelper::changeFunnelSubSequenceStatus) and the FunnelMetric status. Register on fluentcrm_loaded priority below 10. Use for integration actions. Triggers on BaseAction, fluentcrm_funnel_blocks, fluentcrm_funnel_block_fields, fluentcrm_funnel_sequence_handle_, changeFunnelSubSequenceStatus, funnelMetric, getBlockFields.

magnus919 Bundle

Organize durable agent research outputs as summaries, analysis, and evidence dossiers. Use when producing multi-layer research artifacts or coordinating research handoffs. Do not use this skill for unrelated requests; route to the nearest named specialist.

bookforge-ai Skill

Choose the right data access pattern — Table Data Gateway, Row Data Gateway, Active Record, or Data Mapper — for a persistence layer. Use when asked "should I use Active Record or Data Mapper?", "which ORM pattern fits my app?", "when does Hibernate-style mapping make sense vs. Rails ActiveRecord?", "how do I structure my database access layer?", "data mapper or active record for my domain model?", "Row Data Gateway vs Active Record", "Table Data Gateway vs Data Mapper", "Fowler data source patterns", "persistence layer design", "ORM pattern selection", "choose ORM pattern", "database access layer architecture", "Hibernate vs Rails persistence style". Applies when designing a new persistence layer or refactoring an existing one. Routes each domain-logic pattern (Table Module, Transaction Script, Domain Model) to its natural data-source counterpart. Identifies the Active Record / Data Mapper mismatch anti-pattern (AR when schema is not isomorphic with objects; DM when AR would suffice). Maps each pattern to mo

bookforge-ai Skill

Select the correct ORM inheritance strategy — Single Table Inheritance (STI), Class Table Inheritance (joined table / Multi-Table Inheritance), or Concrete Table Inheritance (table per class) — for any OO inheritance hierarchy that needs to be persisted in a relational database. Use when asked: "which inheritance mapping should I use?", "single table vs joined table inheritance", "STI vs CTI vs table per class", "Hibernate inheritance strategy SINGLE_TABLE vs JOINED vs TABLE_PER_CLASS", "@Inheritance JPA", "Rails STI vs multi-table inheritance", "Django model inheritance type", "how to map inheritance in database", "inheritance in database design", "discriminator column inheritance", "ORM polymorphic query performance", "polymorphic table design", "table per class inheritance trade-offs", "joined inheritance vs single table", "inheritance schema design". Applies at greenfield schema design, ORM configuration, or legacy schema refactoring. Routes to the right strategy on six trade-off dimensions: joins on poly

bookforge-ai Skill

Choose domain logic pattern for enterprise application subsystems: Transaction Script vs Domain Model vs Table Module, and decide Service Layer thickness. Use when organizing business logic, choosing between procedural service methods and rich domain models, selecting enterprise app architecture, routing domain logic to the right pattern, deciding anemic domain model vs rich domain model, applying Fowler's complexity-vs-effort curve, determining when to use Domain Model, when to use Transaction Script for simple CRUD, when Table Module fits .NET RecordSet environments, deciding Service Layer facade vs operation script vs controller-entity, avoiding transaction-script-sprawl, avoiding anemic-domain-model anti-pattern, preventing stored-procedure logic leakage, structuring enterprise app business logic, domain logic organization, choose domain pattern, enterprise app business logic design.