qxbyte

qxbyte/pluginhub

Plugin Claude Code

qxbyte's multi-host plugin marketplace (Claude Code / CodeBuddy / Codex / Kimi).

qxbyte/pluginhub

Instructions file

Instructions for qxbyte/pluginhub, covering claude.md, what this repo is, multi-host adaptation, commands and non-negotiable conventions.

qxbyte/pluginhub

Plugin Claude Code

Maintain an Obsidian LLM-Wiki (structure layer + content curation + orchestrator).

qxbyte/pluginhub

Skill Claude CodeCodex

A skill for organising an Obsidian vault, a local collection of linked Markdown notes, into a structured knowledge wiki. It uses four stages: scan, ingest, curate, and lint.

qxbyte/pluginhub

Skill Claude CodeCodex

A coordinator for organizing an Obsidian vault, which is a folder of linked Markdown notes, by first checking its structure and then arranging the notes.

qxbyte/pluginhub

Skill Claude CodeCodex

A skill for keeping the structure of an Obsidian knowledge base up to date. It regenerates marked sections such as the home page tree, directory lists, and index pages.

qxbyte/pluginhub

Plugin Claude Code

Standalone knowledge-base RAG (vector + lexical + metadata recall, RRF-fused).

qxbyte/pluginhub

Hook

Runs when a session starts, executing run-hook.sh via sh. From qxbyte/pluginhub.

qxbyte/pluginhub

Skill Claude CodeCodex

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.

qxbyte/pluginhub

Skill Claude CodeCodex

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.

qxbyte/pluginhub

Skill Claude CodeCodex

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…

qxbyte/pluginhub

Skill Claude CodeCodex

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.

qxbyte/pluginhub

Skill Claude CodeCodex

Overview of the ragkit plugin and how to use it — knowledge-base multi-channel retrieval and its four skills. On Kimi Code this is loaded at session start via the manifest's sessionStart.skill; on hosts with a SessionStart hook the same advisory is injected by the hook instead.

qxbyte/pluginhub

Plugin Claude Code

Lightweight spec-driven workflow (requirements → design → tasks → execute → acceptance).

qxbyte/pluginhub

Skill Claude CodeCodex

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 .

qxbyte/pluginhub

Skill Claude CodeCodex

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

qxbyte/pluginhub

Skill Claude CodeCodex

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 manually at any time once tasks.md exists, or invoked by name (specode:execute) via the Skill tool…

qxbyte/pluginhub

Skill Claude CodeCodex

Use when running specode's requirements phase — project analysis + code location + clarification, then writing requirements.md. Produces / /requirements.md (with the projectroot frontmatter contract) plus the location pointers handed to the design phase. Invoked by name (specode:intake) via the Skill tool by the…

qxbyte/pluginhub

Skill Claude CodeCodex

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.

qxbyte/pluginhub

Skill Claude CodeCodex

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 /…

qxbyte/pluginhub

Skill Claude CodeCodex

Overview of the specode plugin and how to activate it — the spec-driven workflow, its five commands, and when to enter spec mode. On Kimi Code this is loaded at session start via the manifest's sessionStart.skill; on hosts with a SessionStart hook the same advisory is injected by the hook instead.

qxbyte/pluginhub

Plugin Claude Code

Standalone multi-agent orchestration via pipeline.yml (fork coders + reviewer/validator loops).

qxbyte/pluginhub

Agent

CODER subagent dispatched by the task-swarm orchestrator. Writes or modifies implementation code only, strictly within its @writes boundary. Never reviews, never scores, never accepts. Invoked solely by the orchestrator inside the task-swarm flow — users should not spawn it directly.

qxbyte/pluginhub

Agent

REVIEWER subagent dispatched by the task-swarm orchestrator (advisory mode). Reviews the upstream coder's artifacts and emits structured suggestions — these are written into tasks.md as > ⚠️ comments for the user to review. Does not participate in the fix loop — the reviewer never fails a stage and never re-dispatches…