KingInYellows/yellow-plugins - 第 2 页

ci-setup

Check CI prerequisites and configure the self-hosted runner SSH config. Use when first installing the plugin, after adding runners, or when CI commands fail with auth or connectivity errors.

原文语言：英语

ci-status

Show recent CI workflow run status. Use when the user asks for CI status, recent builds, what is running, or needs to find a run ID for diagnosis.

原文语言：英语

diagnose-ci

Reference guide (not an executable action) for CI debugging workflows and the F01-F12 failure-pattern catalog on self-hosted runners. Consult when you need to understand debugging workflows or failure patterns; to actually run a diagnosis, use the ci-diagnose…

原文语言：英语

codex-patterns

Canonical conventions for shelling out to the OpenAI Codex CLI. Use when authoring or modifying commands or agents that invoke codex exec — choosing flags, sandbox and approval modes, and parsing its output.

原文语言：英语

composio-patterns

Canonical conventions for running batch workflows through the Composio MCP server. Use when authoring or modifying commands or agents that call Composio tools — the Workbench sandbox, Multi-Execute batching, and the local usage counter.

原文语言：英语

agent-native-architecture

Reference for agent-native architecture principles: action parity, context parity, shared workspace, primitives over workflows, and dynamic context injection. Use when authoring agent integrations or designing tool surfaces.

原文语言：英语

agent-native-audit

Audit checklist for evaluating an existing codebase against agent-native architecture principles to identify parity gaps. Use when auditing for agent-native readiness, before adding a new agent capability, or when triaging agent-behavior regressions.

原文语言：英语

brainstorming

Reference guide for iterative brainstorm dialogues — question techniques, YAGNI, approach exploration, and research escalation. Use when running /flow:brainstorm or authoring brainstorm-style agents.

原文语言：英语

git-worktree

Git worktree management for isolated parallel development. Use when reviewing PRs in isolation, working on multiple features simultaneously, or when workflows offer worktree option.

原文语言：英语

local-config

Defines the yellow-plugins.local.md per-project config file schema. Use when authoring commands that should accept per-project overrides for review pipeline behavior, reviewer set narrowing, depth controls, or focus-area filtering.

原文语言：英语

mcp-health-probe

Canonical MCP server health classification (OFFLINE / DEGRADED / HEALTHY plus PRESENT (untested) refinement) for `/<plugin>:status` commands. Use when authoring a status command that needs to distinguish 'MCP never started' from 'MCP running but upstream API…

原文语言：英语

mcp-integration-patterns

Shared patterns for ruvector recall/remember and morph discovery integration (the ruvector protocol constants are a replica of yellow-ruvector's canonical memory-query skill). Use when authoring commands or agents that should leverage institutional memory and…

原文语言：英语

memory-recall-pattern

Recall-Before-Act pattern for ruvector — query past learnings via hooks_recall at workflow start. Use when authoring commands or agents that should seed a workflow with relevant institutional memory before executing.

原文语言：英语

memory-remember-pattern

Tiered-Remember-After-Act pattern for ruvector — record learnings via hooks_remember at workflow completion with signal-strength tiers (Auto/Prompted/Skip). Use when authoring commands that should compound institutional memory from workflow outcomes.

原文语言：英语

morph-discovery-pattern

Morph discovery + fallback pattern — discover edit_file and warpgrep at runtime via ToolSearch, prefer them for large edits and intent-based search, silently fall back to Edit/Grep when yellow-morph is missing. Use when authoring agents that edit files or run…

原文语言：英语

multi-host-fleet

Multi-host plugin credential and config reference for yellow-plugins. Use when setting up a new workstation, configuring CI/devcontainer, replicating credentials across a fleet, or wiring a secrets manager. Documents the canonical shell env var names for…

原文语言：英语

plan-status

Show a per-file checkbox progress dashboard of plans/ (open) and plans/complete/ (archived) plan documents. Use when reviewing which plans are ready to archive or checking work-in-flight at a glance.

原文语言：英语

security-fencing

Canonical prompt-injection hardening block for agents that analyze untrusted content (source code, CI logs, workflow files). Use when authoring an agent that reads untrusted input — copy the appropriate variant verbatim into the agent body; only pure…

原文语言：英语

session-handoff

Write a session-handoff artifact at plans/handoff/<YYYY-MM-DD>-<slug>.md capturing current task, workflow status, active artifact, open decisions, in-flight changes, and next action so a fresh session can resume without re-deriving context. Use when the user…

原文语言：英语

stack-provider-guard

Enforce the stacked-PR provider invariants before any provider-changing action — exactly one enabled, managed scopes fail closed, no direct settings edits, no silent fallback. Use when validating a proposed provider switch or auditing current provider state.

原文语言：英语

stack-provider-router

Resolve which stacked-PR provider is active and route provider-specific work to it, or refuse when the state is ambiguous. Use when a workflow needs to know whether Graphite or GitHub native stacks is in effect before running a stack operation.

原文语言：英语

cursor-delegation

Host-neutral reference for the Cursor Cloud Agent delegation lifecycle, the yellow-cursor CLI's JSON contract, and its safety/idempotency rules. Use when building or reasoning about a surface that delegates work to a Cursor Cloud Agent through the CLI.

原文语言：英语

devin-workflows

Devin V3 API workflow patterns and conventions. Use when commands or agents need Devin API context, session management, or error handling.

原文语言：英语

docs-conventions

Shared documentation conventions — templates, diagram type selection, staleness detection, severity classification. Use when agents need doc generation or audit context.

原文语言：英语

linear-workflows

Linear workflow patterns and conventions reference. Use when commands or agents need Linear workflow context, issue writing guidance, or branch naming conventions.

原文语言：英语

mempalace-conventions

Canonical reference for how mempalace commands and agents integrate with the MemPalace MCP server. Use when authoring or maintaining a mempalace command or agent — exact tool naming, palace vocabulary, and error-handling rules live here.

原文语言：英语

palace-protocol

The Palace Protocol for interacting with MemPalace — wake-up sequence, query-before-assert pattern, memory stack usage, and when to use search vs KG vs navigation. Use when agents need guidance on how to interact with the palace correctly.

原文语言：英语

library-context

Use when an agent needs official library docs, API examples, or migration guides. Canonical fallback chain: context7 → EXA → WebSearch. Preloaded by within-plugin agents; inlined verbatim by cross-plugin consumers.

原文语言：英语

research-patterns

Reference conventions for how yellow-research derives slugs, formats reports, and saves output under docs/research/. Use when authoring or modifying yellow-research commands or agents that write research output.

原文语言：英语

stack-traversal

Internal reference for the bottom-up Graphite stack-traversal procedure shared by /review:all and /review:resolve-stack. Use when a yellow-review command needs to walk a Graphite stack PR by PR in dependency order.

原文语言：英语

agent-learning

Agent learning patterns and quality guidelines. Use when commands or agents need to determine when and how to record learnings, apply quality gates, or retrieve past knowledge using ranked retrieval.

原文语言：英语

memory-query

Standard pattern for querying ruvector institutional memory before acting. Use when authoring new agents or commands that should query past patterns, findings, or solutions before executing.

原文语言：英语

ruvector-conventions

ruvector workflow patterns and conventions reference. Use when commands or agents need ruvector context, MCP tool naming, current tool schemas, or error handling patterns.

原文语言：英语

semgrep-conventions

Shared conventions for Semgrep integration — triage state mappings, API patterns, fix strategy decision tree, rate limits, and security rules. Use when commands or agents need Semgrep-specific validation, error handling, or API reference.

原文语言：英语

cursor-delegation

Host-neutral reference for the Cursor Cloud Agent delegation lifecycle, the yellow-cursor CLI's JSON contract, and its safety/idempotency rules. Use when building or reasoning about a surface that delegates work to a Cursor Cloud Agent through the CLI.

原文语言：英语

gt-merge

Merge the current stack's pull requests, from trunk up to the current branch, via Graphite. Use when the user says "merge my stack" or "land these PRs" and the stack is fully reviewed and ready.

原文语言：英语

stack-decomposition-format

Structured format contract for "## Stack Decomposition" sections in plan documents, shared by gt-stack-plan (producer) and flow:work (consumer). Use when writing or parsing a Stack Decomposition section.

原文语言：英语

stack-plan-style

Display guidance for presenting a stacked-PR plan — ordered branch tree with intent, commit type, and dependency notes. Use when gt-stack-plan presents a stack plan for user confirmation.

原文语言：英语

gt-cleanup

Scan local branches for staleness and divergence, then delete or reconcile them with safeguards. Use when user says "clean up my branches" or "which branches are stale". For deleting branches whose PRs merged — and for pulling trunk or restacking — use the…

原文语言：英语

gt-amend

Fold working-tree changes into the current branch commit, audit them, and re-submit via Graphite. Use when user says "amend this", "add this to the current PR", "fold this fix in", or has follow-up edits for an already-submitted branch. Not for starting new…

原文语言：英语