Skip to content

hashgraph-online/awesome-codex-plugins / plugins/boshu2/agentops/skills/research

research

Verified

Answer one cited question on code, history, claims or patterns. Use when: asked how it works, why it changed, if a claim or done/shipped report holds, or a pattern warrants a rule.

schemas/findings.json

View on GitHub
{
  "$schema": "https://json-schema.org/draft-07/schema#",
  "title": "Research Findings",
  "description": "Output schema for AgentOps research skill. Structured findings from codebase exploration.",
  "type": "object",
  "properties": {
    "topic": {
      "type": "string",
      "description": "Research topic or question"
    },
    "summary": {
      "type": "string",
      "description": "Executive summary of findings"
    },
    "findings": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "area": {"type": "string", "description": "Code area or component examined"},
          "observation": {"type": "string", "description": "What was found"},
          "evidence": {"type": "string", "description": "File paths, code snippets, or references"},
          "implications": {"type": ["string", "null"], "description": "Impact or significance of finding"}
        },
        "required": ["area", "observation", "evidence"],
        "additionalProperties": false
      }
    },
    "source_ledger": {
      "type": "array",
      "description": "Preserved identities for caller-supplied reports used in a multi-report synthesis",
      "items": {
        "type": "object",
        "properties": {
          "label": {"type": "string", "description": "Short local label used by comparison entries"},
          "identity": {"type": "string", "description": "Original path or caller-supplied report identifier"},
          "title": {"type": ["string", "null"]},
          "author_runtime": {"type": ["string", "null"]},
          "revision_or_date": {"type": ["string", "null"]}
        },
        "required": ["label", "identity"],
        "additionalProperties": false
      }
    },
    "comparison": {
      "type": "object",
      "description": "Claim comparison for a multi-report synthesis; omitted for ordinary single-source research",
      "properties": {
        "agreements": {"$ref": "#/definitions/comparisonEntries"},
        "contradictions": {"$ref": "#/definitions/comparisonEntries"},
        "unknowns": {"$ref": "#/definitions/comparisonEntries"}
      },
      "required": ["agreements", "contradictions", "unknowns"],
      "additionalProperties": false
    },
    "checked": {
      "type": "array",
      "items": {"type": "string"},
      "description": "Surfaces and claims examined"
    },
    "not_checked": {
      "type": "array",
      "items": {"type": "string"},
      "description": "Relevant surfaces and claims left unexamined"
    },
    "schema_version": {
      "type": "integer",
      "enum": [1],
      "description": "Schema version for forward compatibility"
    }
  },
  "definitions": {
    "comparisonEntries": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "claim": {"type": "string"},
          "source_labels": {
            "type": "array",
            "items": {"type": "string"},
            "description": "Labels from source_ledger; may be empty for a genuine unknown"
          },
          "evidence": {
            "type": "array",
            "items": {"type": "string"}
          }
        },
        "required": ["claim", "source_labels", "evidence"],
        "additionalProperties": false
      }
    }
  },
  "required": ["topic", "summary", "findings", "checked", "not_checked", "schema_version"],
  "additionalProperties": false
}
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