From halyard
Gather background context before starting work or answering questions about a topic. Use when the user asks 'what do we know about', 'background on', 'catch me up on', 'context on', 'research X before starting', 'what's the history of', 'look into', 'investigate', 'find out about', or needs orientation on an unfamiliar area. Also use proactively at the start of a task when the work touches a named system or feature area (auth, payments, ingestion, a specific service), requires architectural judgment, or the codebase has prior decisions that could constrain the approach. Skip for mechanical edits, single-file changes, or clear-cut bug fixes where prior context is unlikely to change behavior. Combines knowledge base search, codebase exploration, and web search.
How this skill is triggered — by the user, by Claude, or both
Slash command
/halyard:gather-contextThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Use this skill when any of these apply:**
Use this skill when any of these apply:
Skip it when:
Start with knowledge base search — it's the fastest way to surface prior decisions and past work. Work outward from there:
Knowledge base first — Search for the topic area:
mcp__plugin_halyard_ask-expert__search_knowledge(query: "the feature area or system")
If results look relevant, follow up with explore_knowledge(entry_id: "...") to pull in connected decisions and prior work.
Codebase — Read relevant files, check git log/git blame for recent changes and who owns the area.
Web — Search externally only when the topic genuinely extends beyond the repo (third-party APIs, standards, recent releases).
If knowledge base tools are unavailable, rely on codebase exploration and web search. Either way, synthesize findings into a brief summary (2–4 bullets) before proceeding with the task — this doubles as a sanity check that you gathered enough.
npx claudepluginhub halyard-labs/claude-plugin-marketplace --plugin halyardCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.