Use when working with the WordPress Abilities API (wp_register_ability, wp_register_ability_category, /wp-json/wp-abilities/v1/*, @wordpress/abilities) including defining abilities, categories, meta, REST exposure, and permissions checks for clients.

Use when the user asks about WordPress codebases (plugins, themes, block themes, Gutenberg blocks, WP core checkouts) and you need to quickly classify the repo and route to the correct workflow/skill (blocks, theme.json, REST API, WP-CLI, performance, security, testing, release packaging).

Use when the deliverable is WordPress Playground Blueprint JSON or a Blueprint bundle, including creating, editing, reviewing, validating schema keys, choosing steps/resources, and debugging Blueprint files. For only running or sharing a Playground environment, use wp-playground.

A step-by-step problem-solving loop (classify the ask, define done, gather evidence, decide, act surgically, verify by observation, report outcome-first). Use when the user says "/fable-method", "use the fable method", or "approach this like Fable", or proactively when starting any multi-step task that no task-specific skill covers. Subcommands - plan (stop after the plan), audit (grade finished work against the loop), report (rewrite an answer outcome-first).

End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification agents, honest outcome-first report. Use for non-trivial multi-step tasks when the user says "/fable-loop", "run the fable loop", or "do this the way Fable would". For the rules alone without orchestration, use fable-method; for large multi-phase projects, prefer the GSD workflow and use this inside phases.

Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened tests and false completion claims, and delivers an evidence-based verdict (VERIFIED / VERIFIED WITH CAVEATS / REFUTED). Use after any agent or model claims work is complete - "/fable-judge", "judge this work", "verify what it did", "did that actually work?". Also runs the fable-method trap suite against a skill or model via "/fable-judge suite <target>".

Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke eval. Use when the user says "/fable-domain <sector>", "make a skill for <domain>", "add a domain to the fable method", or "give a lesser model Fable's workflow for <domain>". The bundle is the deliverable; a workflow without its flowchart, sources, and trap is not done.

Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.

Run local ClawSweeper exact-item or committed-range reviews without GitHub mutation.

Use the Crabbox wrapper for validation across Linux, macOS, Windows, and WSL2, including delegated Blacksmith Testbox proof. Report the actual provider and id.

Translate and synchronize rtp2httpd Chinese documentation into English. ALWAYS use this skill whenever Chinese docs under docs/ need English translations under docs/en/, when Chinese doc diffs need to be reflected in existing English files, when VitePress English sidebar entries need to mirror Chinese docs, or when translation terminology needs to stay consistent across docs.

Synchronize rtp2httpd FCC IP documentation from GitHub issue feedback. ALWAYS use this skill when the user asks to update FCC address docs, check new FCC IP reports, validate existing FCC entries, or process comments from https://github.com/stackia/rtp2httpd/issues/5.

Execute the rtp2httpd release workflow — tag, GitHub release, CI handling, and stable branch updates.

Write, run, review, and debug end-to-end tests for rtp2httpd. ALWAYS use this skill when the user: (1) wants to write or optimize e2e/integration tests, (2) asks to run tests or mentions run-e2e.sh, uv, pytest, collect-only, xdist, markers, fixtures, or parallelism, (3) needs to debug failing, flaky, slow, or hanging e2e tests, (4) mentions any file under e2e/ or scripts/run-e2e.sh, (5) mentions MockRTSP*, MockHTTP*, MockFCC*, MockSTUN*, R2HProcess, MulticastSender, helper APIs, or test fixtures, (6) asks about multicast, RTSP, HTTP proxy, FCC, STUN, M3U, EPG, URL template, or zerocopy test coverage in rtp2httpd, or (7) uses Chinese phrases such as "端到端测试", "跑测试", or "e2e 测试" in this repo.

Build, run, and configure rtp2httpd locally. Use this skill whenever the user wants to compile the project, start the daemon, pass command-line arguments, edit configuration, or troubleshoot build/runtime issues. Also activate when the user mentions cmake, build directory, rtp2httpd.conf, web-ui build, pnpm run, vite build, embedded_web_data.h, or asks how to test the service locally.

运行项目测试（涵盖 Python 后端、Vue 前端及多语言校验）

进行深入访谈以收集需求并编写详细的规格说明书 (spec)

规划、实现或重构角色扮演模式（默认上帝视角下的单角色接管）时使用。适用于一期文本决策、二期统一有限选择框架、三期依附 Conversation 动作的自由对话，以及对应的 runtime/API/frontend/test 收口。

Use when working on tools/img_gen avatar image generation, OpenAI-compatible image API config, human or yaoguai portrait prompts, qi-refining base generation, image-to-image realm edits, white-background postprocessing, manifests, or prompt rules that preserve pixel-art identity while changing cultivation realms.

国际化 (i18n) 开发指南。在添加新文本、创建物品/事件、修改翻译或管理 PO/MO 文件时使用。