From goldfish
Use when the user asks for progress against current project direction, wants a status check on the active brief, or needs evidence-backed assessment across briefs, checkpoints, and docs/plans
How this skill is triggered — by the user, by Claude, or both
Slash command
/goldfish:brief-statusThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Assess status from three sources:
Assess status from three sources:
docs/plans/ = execution detailmcp__goldfish__recall({ limit: 0 })
If the user asks about a specific brief, fetch it directly:
mcp__goldfish__brief({ action: "get", id: "brief-id" })
mcp__goldfish__recall({ days: 7, limit: 20, full: true })
Use full: true when you need files, git context, or detailed checkpoint metadata.
docs/plans/ when execution detail mattersUse project plan docs to understand implementation sequencing, task lists, and status headers. Do not trust the status header blindly. Verify it against checkpoints.
docs/plans/ execution detail matches the briefUse short sections:
Direction for the active briefEvidence for completed and active workDrift for work that does not map back to the briefNext for likely immediate follow-upBe direct. If the brief is stale, say so. If the implementation work has drifted away from the brief, say so.
docs/plans/ can explain how the team is executing, but the brief explains why.docs/plans/.Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub anortham/goldfish --plugin goldfish