A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, evaluating, or debugging agent systems that require effective context management and reliable operating loops.

Pre-cycle Feature sizing workflow that assesses Features from Jira using T-shirt sizes (XS–XXL), produces per-team effort breakdowns (DEV, QE, UX, UI, DOCS), and writes results back to Jira. Accepts a single Feature or all Features in a Fix Version for batch sizing. Use when sizing Features for cycle planning, prioritizing a release backlog, or evaluating whether a Feature fits in a cycle. Activated by commands: /ingest, /assess, /apply.

Requirements-to-PRD workflow that ingests requirements from Jira, clarifies ambiguities through iterative Q&A, drafts a Product Requirements Document, and manages review via GitHub PRs. Use when creating PRDs, analyzing requirements, or preparing feature specifications for review. Activated by commands: /ingest, /clarify, /draft, /revise, /publish, /respond.

KCS article workflow that gathers bug context from Jira and user input, drafts a KCS Solution article in markdown, validates it against the KCS Content Standard, and produces a handoff message for the support engineer. Use when writing KCS articles for known issues with workarounds. Activated by commands: /gather, /draft, /validate, /handoff.

Story-to-code workflow that takes a Jira Story, plans the implementation, writes contract-based tests and production code via TDD, validates against the project's CI expectations, and manages review via GitHub PRs. Use when implementing Jira stories produced by the design workflow. Activated by commands: /ingest, /plan, /revise, /code, /validate, /publish, /respond.

Story-to-e2e-test workflow that takes a Jira [QE] Story, discovers the project's e2e testing infrastructure, plans test scenarios, writes e2e tests matching project conventions, validates them, and manages review via GitHub PRs. Use when implementing [QE] stories produced by the design workflow. Activated by commands: /ingest, /plan, /revise, /code, /validate, /publish, /respond.

Design-and-decompose workflow that takes a PRD, researches the problem space, drafts a technical design document with a requirement-anchored testplan, decomposes work into Jira-ready epics and stories, and manages review via GitHub PRs. Use when creating design documents, researching external integrations or standards, breaking features into epics/stories, or syncing task breakdowns to Jira. Activated by commands: /ingest, /research, /draft, /decompose, /revise, /publish, /respond, /sync.

Automated CVE remediation that reads vulnerability details from Jira vulnerability tickets, applies multi-strategy dependency fixes, validates results, and creates pull requests with full justification. Language-agnostic: supports Go, Node.js, Python, Java, Rust, Ruby. Use when patching CVEs, updating vulnerable dependencies, or responding to Jira vulnerability tickets. Activated by commands: /start, /scan, /patch, /validate, /pr, /backport, /close, /report.

AI-driven code review workflow that reviews uncommitted changes using a discoverable reviewer profile, presents findings for human decision, and iterates until approved. Supports --unattended for automated iteration. Use when reviewing code before commit or PR. Activated by commands: /start, /continue, /clean.

Use this skill when converting Dagster code that references resources holding credentials (ConfigurableResource subclasses, EnvVar, integration resources like SnowflakeResource / S3Resource / DbtCliResource, or resources wired into Definitions) to Orchestra. Triggers: any Dagster resource that stores host/login/token/key, any EnvVar used for credentials, or environment-specific resource configuration. Must be read before finalising any Orchestra YAML that contains a connection: field.

Use this skill when a Dagster project sends notifications: @run_failure_sensor, @run_status_sensor, make_email_on_run_failure_sensor, make_slack_on_run_failure_sensor, PagerDuty/Teams/Datadog resources used in hooks or sensors, or @failure_hook/@success_hook. Covers all six Orchestra alert destination types: SLACK, EMAIL, PAGER_DUTY, MICROSOFT_TEAMS, WEBHOOK, and DATADOG. Read alongside slack-dagster-to-orchestra for complete notification coverage.

Use this skill when converting Airflow code that references credentials via Airflow's connection system: any operator/hook kwarg ending in `_conn_id` (conn_id=, aws_conn_id=, snowflake_conn_id=, ssh_conn_id=, slack_conn_id=, gcp_conn_id=, http_conn_id=), any `BaseHook.get_connection(...)` or `Connection` class usage, any `AIRFLOW_CONN_<NAME>` environment variable, or a Secrets Backend (AWS Secrets Manager / Hashicorp Vault) configured for connections. Also covers distinguishing these from `Variable.get()` / `AIRFLOW_VAR_*`, which are non-secret config, not connections. Must be read before finalising any Orchestra YAML with a connection: field converted from an Airflow source.

Use this skill when an Airflow DAG uses on_failure_callback, on_success_callback, on_retry_callback, sla_miss_callback, EmailOperator, PagerDutyEventsHook, or any notification/alerting pattern. Covers all six Orchestra alert destination types: SLACK, EMAIL, PAGER_DUTY, MICROSOFT_TEAMS, WEBHOOK, and DATADOG. Read this skill alongside slack-airflow-to-orchestra for complete notification coverage.

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.

Update the primary SDK dependencies of harness packages. Use when asked to update the harness SDKs or harness adapter dependencies.

Guide for adding first-party AI provider packages to the AI SDK. Use when creating a provider package under packages/ to integrate an external AI service.

Guide for adding new AI SDK harness packages. Use when creating a new @ai-sdk/harness-<name> package that adapts a coding-agent runtime to HarnessV1.

Translate "The Interactive Book of Prompting" chapters and UI strings to a new language

MemPalace — Local AI memory with 96.6% recall. Semantic search, temporal knowledge graph, palace architecture (wings/rooms/drawers). Free, no cloud, no API keys.