Skip to content

borghei/Claude-Skills / research-ops/product-research

product-research

Verified

Continuous product discovery research operations — picking the method that fits the question, recruiting and screening participants, building interview guides, and scoring evidence into insights. Use when planning or running discovery.

assets/sample_evidence.json

View on GitHub
{
  "study": "Ticket triage discovery",
  "insights": [
    {
      "id": "I1",
      "claim": "Agents manually re-triage tickets because the automatic assignment ignores account tier, so enterprise tickets land in the general queue.",
      "evidence": [
        {
          "participant": "P1",
          "source": "interview",
          "kind": "observed",
          "note": "Reassigned 4 of 6 tickets during the session, all enterprise accounts"
        },
        {
          "participant": "P3",
          "source": "interview",
          "kind": "observed",
          "note": "Kept a personal browser tab filtered to enterprise accounts"
        },
        {
          "participant": "P4",
          "source": "interview",
          "kind": "reported",
          "note": "Described re-triage as the first thing done each morning"
        },
        {
          "participant": "P2",
          "source": "support_tickets",
          "kind": "artefact",
          "note": "17 reassignment events in one week, 14 to enterprise accounts"
        },
        {
          "participant": "P6",
          "source": "analytics",
          "kind": "artefact",
          "note": "Median time-to-first-response 3.1x higher for misrouted enterprise tickets"
        }
      ]
    },
    {
      "id": "I2",
      "claim": "Team leads distrust the auto-triage confidence score and ignore it entirely.",
      "evidence": [
        {
          "participant": "P3",
          "source": "interview",
          "kind": "reported",
          "note": "Said the score 'has been wrong enough times that I stopped looking'"
        },
        {
          "participant": "P5",
          "source": "interview",
          "kind": "reported",
          "note": "Could not recall what the score meant"
        }
      ]
    },
    {
      "id": "I3",
      "claim": "Agents would prefer a bulk re-assignment action over a smarter routing rule.",
      "evidence": [
        {
          "participant": "P1",
          "source": "interview",
          "kind": "reported",
          "note": "Asked for a multi-select and 'move all' button"
        }
      ]
    },
    {
      "id": "I4",
      "claim": "Ticket volume spikes on Monday mornings overwhelm the triage step.",
      "evidence": [
        {
          "participant": "P2",
          "source": "analytics",
          "kind": "artefact",
          "note": "Monday inbound is 2.4x the weekday median across 12 weeks"
        },
        {
          "participant": "P4",
          "source": "interview",
          "kind": "reported",
          "note": "Described Monday as 'the day triage does not happen'"
        },
        {
          "participant": "P6",
          "source": "support_tickets",
          "kind": "artefact",
          "note": "Monday tickets show the longest untriaged dwell time"
        }
      ]
    }
  ]
}
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall