calibrate
Calibration testing for agents and skills. Generates synthetic problems with known outcomes (quasi-ground-truth), runs targets against them, and measures recall, precision, and confidence calibration — revealing whether self-reported confidence scores track actual quality.
animal-disease-control
Use Agriculture and Food Board infectious animal disease sources for control measures, surveillance context, and operational response references.
rtl-p5s-cdc-verify
This skill should be used when analyzing clock domain crossings for synchronizer coverage and metastability risks.
sim-hardware-validation
Use for LawnBerry Pi simulation vs real-hardware validation. Covers SIM_MODE selection, .env and config checks, simulation-safe test-first workflow, hardware preflight expectations, and avoiding false claims that local success proves on-device behavior.
eda-hypothesis-experiment-designer
Convert research ideas into falsifiable hypotheses and experiment plans with metrics, controls, pass/fail criteria, and confounder mitigation.
ab-test-setup
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking.
eda-knowledge-gate-maintainer
Enforce experiment hygiene for this EDA repo. Utility skill for knowledge gate, tool reuse checks, and maintenance-log updates during scoped execution.
eda-retro
Perform post-experiment retrospective for EDA runs, classify failure/success mechanisms, propose high-confidence next actions, and decide whether to recursively trigger a new eda-loop iteration. Use after each experiment batch with monitor/summary/manifest artifacts.
feedback-ls
Guide for sending document pages to Label Studio for human feedback on transcriptions. Use when: feedback, label studio, annotation, review transcription, quality check, send to label studio, import to label studio, human review, correct transcription, segmentation feedback, transcription feedback, ALTO to label studio, review pages, flag pages for review, quality assurance, QA, annotation task, annotate images, label images, send images for annotation.
audit
Audit evidence collection and trail verification. Gathers artifacts, validates controls, generates audit reports, and maintains compliance documentation. Use when: "audit trail", "collect evidence", "audit report", "control testing", "compliance documentation"
tourism-information-system-dataset
Retrieve tourism services/inventory records from the official andmed.eesti.ee dataset for the national tourism information system.
bmad-domain-research
Conduct domain and industry research. Use when the user says wants to do domain research for a topic or industry
kb-fediverse-webfinger-discovery
Background knowledge about reverse WebFinger discovery — finding a WebFinger address from an ActivityPub actor — based on FEP-2c59 (DRAFT status). Covers the `webfinger` property on actors, the forward vs reverse discovery problem, why `preferredUsername` is insufficient for reverse lookups, domain mismatch use cases, validation requirements (no-redirect string comparison), security considerations, JSON-LD context registration, the community debate around alternative approaches (`alsoKnownAs`, `aliases`, property naming), Mastodon's current reverse discovery algorithm and its limitations, and the W3C SWICG acknowledgment of the problem. Load when the user asks about reverse WebFinger discovery; how to get a WebFinger address from an actor URL; the `webfinger` property on ActivityPub actors; why `preferredUsername` is not enough for constructing WebFinger handles; domain mismatch between actor URL and WebFinger address; FEP-2c59; or how Mastodon resolves actor URLs back to `user@domain` handles.
domain-mcp-setup
Guided install and configuration of domain-mcp — the Dynadot-backed MCP server — for Claude Code, Cursor, or Claude Desktop. Use when the user asks to 'install domain-mcp', 'set up Dynadot in Claude/Cursor/Claude Desktop', 'connect my Dynadot account to Claude', 'configure domain management', or is troubleshooting a broken or missing domain-mcp install. Covers preflight checks, Dynadot API key verification, MCP client config merging without clobbering existing servers, and handoff to the server's usage tools. Do NOT activate when the user just wants to use domain-mcp tools that are already installed — route them to the `help` tool or the relevant prompt workflow instead.
enrich-lead
Instant lead enrichment. Drop a name, company, LinkedIn URL, or email and get the full contact card with email, phone, title, company intel, and next actions.
triage-kubernetes-service-dns
Diagnose in-cluster DNS resolution failures and isolate root causes.
domain-operations
Standards for writing domain operations using Dry::Monads. Activate when creating or modifying files in app/domain/operations/ or components/*/app/domain/*/operations/
local-dns
Add or remove local hostname-to-IP mappings using local-dns-override. Use when you need to resolve a custom hostname (like api.local or *.dev.local) to a local IP address for development, check what a hostname currently resolves to, or test that a DNS record is working. Triggers include "add DNS record", "map hostname to IP", "resolve api.local", "local hostname", "DNS override", or any task that involves making a custom domain point to 127.0.0.1 or another local address.
domain-name-brainstormer
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
