Skip to content

JPeetz/agent-skills / skills/development/finding-unknowns/skills/interview-me

interview-me

Verified

Use when planning is done but ambiguity still remains.

FileKindSize
CHANGELOG.mdmarkdown397 B
SKILL.mdskill md1.9 KB
evals/evals.jsonconfig2.4 KB

evals/evals.json

View on GitHub
{
  "skill": "interview-me",
  "version": "1.0.0",
  "cases": [
    {
      "id": "e1",
      "description": "Should trigger: planning done but ambiguity remains",
      "input": "The plan is mostly done but I have open questions about permissions. Ask me.",
      "shouldTrigger": true,
      "expect": "Asks one question per turn, ordered by blast radius, with context and options",
      "assertions": [
        "Reads everything already established first",
        "Orders questions: architecture-changers first, behavior definers, then polish",
        "Asks exactly one question per turn",
        "Offers 2-3 concrete options with recommendation, accepts 'you decide'",
        "Checkpoints every few questions; ends with final decision list"
      ]
    },
    {
      "id": "e2",
      "description": "Should trigger: post-brainstorm gap closing",
      "input": "We brainstormed, but I'm still fuzzy on the failure-mode handling. Interview me.",
      "shouldTrigger": true,
      "expect": "Asks behavior-definer questions one at a time",
      "assertions": [
        "Does not re-ask already-answered items",
        "Flags contradictions with earlier decisions immediately"
      ]
    },
    {
      "id": "n1",
      "description": "Not trigger: ambiguity resolvable from the codebase",
      "input": "Does our API use JWT or sessions?",
      "shouldTrigger": false,
      "expect": "Looks it up instead of asking",
      "assertions": [
        "No interview question produced; answer discovered from code"
      ]
    },
    {
      "id": "n2",
      "description": "Not trigger: fully specified task",
      "input": "Build the login page exactly as the spec describes.",
      "shouldTrigger": false,
      "expect": "Proceeds to implementation",
      "assertions": [
        "No questions asked"
      ]
    },
    {
      "id": "e3",
      "description": "Should trigger: architecture-changing question first",
      "input": "One of my open questions would change the whole data model. Ask me that one first.",
      "shouldTrigger": true,
      "expect": "Orders architecture-changers first and asks exactly one question per turn",
      "assertions": [
        "Puts the architecture-changing question first",
        "Asks exactly one question per turn",
        "Gives context, 2-3 options, and a recommendation",
        "Checkpoints decisions after a few rounds"
      ]
    }
  ]
}
planning-and-task-breakdownaddyosmani/agent-skillsBreaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
screenpipethedotmack/claude-memSearch screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
contact-widgetnexu-io/open-designSelf-contained floating chat widget with welcome screen, social links, meeting button, and message input. Single HTML file, zero dependencies.Stars: 108kUpdated Claude CodeCodexVerifiedInstall
meeting-notesnexu-io/open-designMeeting notes page — title bar with attendees, agenda checklist, decisions block, action items table with owners + dates, and a "next meeting" footer. Use when the brief mentions "meeting notes", "minutes", "1:1 notes", "all-hands recap", or "会议纪要".Stars: 108kUpdated Claude CodeCodexVerifiedInstall