pluginhub

Use when running a spec's execution tail — presents the 执行方式 selector, dispatches the chosen engine (task-swarm / superpowers / specode-native TDD), then runs acceptance and the distill prompt. Trigger /specode:execute <slug> manually at any time once tasks.md exists, or invoked by name (specode:execute) via the Skill tool by the spec / continue skills.

Use when running specode's requirements phase — project analysis + code location + clarification, then writing requirements.md. Produces <specsRoot>/<slug>/requirements.md (with the project_root frontmatter contract) plus the location pointers handed to the design phase. Invoked by name (specode:intake) via the Skill tool by the specode orchestration SKILL; not a user-triggered command.

Use when creating a new spec-driven workflow — the /specode:spec entry that walks requirements → design → tasks → 执行方式 → execute → acceptance, autonomously calling superpowers skills for the heavy lifting with a first-class specode-native fallback, and filing 4 fixed artifacts (requirements.md / design.md / tasks.md / implementation-log.md) under the user document directory. Trigger /specode:spec <request>, or 进入 spec 模式 with a new requirement.

Use when resuming an existing spec by slug — the /specode:continue entry that reads the fixed docs, reports a progress brief (inferred phase + checkbox progress), then stops and waits for the user; it never auto-resumes. Trigger /specode:continue <slug>.

Use when distilling a finished specode spec into atomic, locate-oriented markdown knowledge points — writes cases/ + navigation/ + MEMORY.md into the project's own <project_root>/knowledge-base/ (md-only, no auto-injection), optionally copied to an Obsidian vault. Trigger ONLY /specode:distill <slug>, never auto-run by the main specode flow.

Use when listing all specs under the specs root — the /specode:list entry that shows every spec slug with its inferred phase, for looking up slugs or an overview; it does not resume. Trigger /specode:list.

用于对 vault 做内容策展——基于 Karpathy LLM Wiki 三层架构执行 Scan → Ingest → Curate → Lint 四阶段。触发语：/wiki-curate、scan、ingest、curate、lint、「整理我的笔记库」、「整理 vault」、「整理 LLM Wiki」。绝不改只读目录原文（07-Ideas/、10-Work/、SpecIn/），不写 wiki-struct 受管块；结构层（Home 树/分区页/地图）→ wiki-struct。

用于整理 Obsidian LLM Wiki 的统一编排入口——定位 vault → 两方只读体检 → 汇总行动计划 → 用户确认 → 按「结构→策展」编排 wiki-struct / wiki-curate 完成整理（下一步跑哪个 skill / 命令 / 参数由模型依据体检结果判断，建议性非规则）。触发语：/wiki-orchestrate（scan / set-vault）、「整理笔记库」、「跑一次编排」、「统一整理 vault」。入口自身不改内容笔记，写操作全委托子 skill 并继承其红线。

用于维护 Obsidian LLM Wiki 的「结构层」——确定性重写 Home 总览树、各一级目录 README、00-Index 分区页的「受管块」，并产出结构体检报告。触发语：/wiki-struct（check / apply / init）、「刷新 Home 树」、「更新 README 目录」、「整理结构层」。只重写 marker 包裹的受管块，绝不改内容笔记原文；内容策展 → wiki-curate。

Use when driving the task-swarm multi-agent orchestrator standalone — read a requirement or design doc, generate a pipeline.yml, then run the fork → review → validate loop to finish a multi-task implementation. Trigger /task-swarm:swarm, or when specode delegates its execution phase here; input a requirements doc or a hand-written pipeline.yml.

Use when building or refreshing the RagKit index for a project knowledge-base/ (e.g. after distill added or updated knowledge points). Trigger /ragkit:embed. Querying instead uses ragkit:query; index health uses ragkit:status.

Use when measuring or tuning RagKit retrieval accuracy — runs the golden evalset, reports recall@k and MRR per bucket. Trigger /ragkit:eval. Run before or after any retrieval-param change to keep a baseline.

Use when retrieving from a project knowledge-base/ — multi-channel RAG recall (vector plus lexical plus metadata, RRF-fused) returning locate-pointer cards; multi-round and multi-angle querying allowed. Trigger /ragkit:query, or called by name by workflows like specode. Building or refreshing the index instead uses ragkit:embed.

Use when checking RagKit index health — doc and chunk counts, backend resolution, staleness and drift between knowledge-base/ and index. Trigger /ragkit:status. Rebuilding after drift uses ragkit:embed.