Skip to content

aiskillstore/marketplace / skills/89jobrien/technical-research

technical-research

Verified

Technical spike and research investigation specialist. Use when exploring options for a technical decision, conducting timeboxed investigations, or evaluating technology choices.

FileKindSize
SKILL.mdskill md1.4 KB
references/technical-spike.template.mdmarkdown3.1 KB
skill-report.jsonconfig9.8 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-05T13:57:55.028Z",
    "slug": "89jobrien-technical-research",
    "source_url": "https://github.com/89jobrien/steve/tree/main/steve/skills/technical-research",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "0d8b9d733efe13ccf0fee7df7b763196d98890be98ab92f2e7b0c4788d10ed53",
    "tree_hash": "917621e284e8eb2c9a36d6378fd156ad74adb4bb89258a73fe4248e3512816a2",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "technical-research",
    "description": "Technical spike and research investigation specialist. Use when exploring options for a technical decision, conducting timeboxed investigations, or evaluating technology choices.",
    "summary": "Guides structured technical spikes for evidence-based engineering decisions.",
    "icon": "📦",
    "version": "1.0.2",
    "author": "Joseph OBrien",
    "license": "MIT",
    "category": "research",
    "tags": [
      "technical-spike",
      "architecture",
      "research",
      "proof-of-concept",
      "decision-making"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands"
    ]
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "The only static finding is a false positive caused by Markdown inline code for a reference file path in SKILL.md. No evidence found for prompt injection, data exfiltration, unsafe external command execution, or malicious intent in the reviewed files.",
    "remediation": [],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 37,
            "line_end": 37
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 37,
        "line_end": 37,
        "snippet": "- `references/TECHNICAL_SPIKE.template.md` - Structured spike investigation format"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "SKILL.md line 37 uses Markdown backticks around a reference file path, not Ruby or shell execution. There is no executable code or command invocation at this location."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 2,
    "total_lines": 274,
    "audit_model": "codex",
    "audited_at": "2026-07-05T13:57:55.028Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Evaluate Technical Options with Structured Spikes",
    "value_statement": "Technical decisions often need evidence, not opinion. This skill guides timeboxed spikes with options, proof of concept results, comparison matrices, risks, and recommendations.",
    "seo_keywords": [
      "technical research",
      "technical spike",
      "architecture evaluation",
      "technology selection",
      "proof of concept",
      "risk assessment",
      "implementation planning",
      "Claude",
      "Codex",
      "Claude Code"
    ],
    "actual_capabilities": [
      "Guides timeboxed investigations with objectives, questions, and success criteria.",
      "Structures option comparisons with proof of concept findings, pros, cons, and effort estimates.",
      "Builds weighted decision matrices for multiple technical approaches.",
      "Documents risks, dependencies, implementation phases, and open questions.",
      "Produces recommendation records that answer the original research questions."
    ],
    "limitations": [
      "Does not replace expert security, legal, or compliance review for high-risk decisions.",
      "Requires user-provided context, constraints, and access to relevant code or documentation.",
      "Proof of concept quality depends on available time and test coverage.",
      "Does not verify external benchmarks or vendor claims without source review."
    ],
    "use_cases": [
      {
        "title": "Select a Framework",
        "description": "Compare candidate frameworks against delivery risk, maintainability, performance, and team familiarity.",
        "target_user": "Engineering lead"
      },
      {
        "title": "Validate Feasibility",
        "description": "Plan a short proof of concept that answers clear technical questions before implementation starts.",
        "target_user": "Backend engineer"
      },
      {
        "title": "Prepare an Architecture Decision",
        "description": "Turn research notes into a recommendation with risks, dependencies, and phased implementation steps.",
        "target_user": "Product engineering manager"
      }
    ],
    "prompt_templates": [
      {
        "title": "Start a Spike",
        "prompt": "Create a technical spike for choosing between [Option A] and [Option B]. Include objective, questions, success criteria, risks, and a recommendation.",
        "scenario": "Beginner investigation planning"
      },
      {
        "title": "Compare Options",
        "prompt": "Compare three approaches for [problem]. Use weighted criteria for performance, maintainability, cost, delivery risk, and team familiarity.",
        "scenario": "Structured technology selection"
      },
      {
        "title": "Plan Evidence Collection",
        "prompt": "Run a timeboxed research plan for [decision]. Define experiments, proof of concept scope, expected evidence, and reporting format.",
        "scenario": "Intermediate spike execution"
      },
      {
        "title": "Challenge a Recommendation",
        "prompt": "Audit our existing findings for [technology decision]. Challenge assumptions, identify missing evidence, update the comparison matrix, and propose an implementation path.",
        "scenario": "Advanced decision review"
      }
    ],
    "output_examples": [
      {
        "input": "Need to choose a queue technology for a billing workflow.",
        "output": [
          "Objective: determine which queue supports retry behavior, monitoring, and expected throughput.",
          "Recommendation: use the managed queue because operations risk is lower and required features are available.",
          "Risks: vendor limits, message ordering assumptions, and migration effort need validation."
        ]
      },
      {
        "input": "Evaluate whether a search index should replace database filtering.",
        "output": [
          "The spike compares current filtering, a managed search service, and a self-hosted index.",
          "The matrix scores latency, relevance quality, operational load, cost, and rollout complexity.",
          "The recommended path is a limited managed search pilot with measured relevance checks."
        ]
      },
      {
        "input": "Decide if a service should move from REST to GraphQL.",
        "output": [
          "The research questions focus on client flexibility, caching, authorization, schema ownership, and migration cost.",
          "The recommendation includes a phased rollout, unresolved risks, and acceptance criteria for the next milestone."
        ]
      }
    ],
    "best_practices": [
      "Define success criteria before comparing options.",
      "Keep proof of concept work limited to the agreed timebox.",
      "Record unresolved questions and owners before implementation starts."
    ],
    "anti_patterns": [
      "Choosing the preferred tool before evidence is collected.",
      "Running a spike without constraints, scoring criteria, or decision owners.",
      "Treating prototype code as production-ready without review."
    ],
    "faq": [
      {
        "question": "What does this skill produce?",
        "answer": "It produces structured research notes, option comparisons, risk lists, and an implementation recommendation."
      },
      {
        "question": "Can it help with architecture decisions?",
        "answer": "Yes. It helps compare approaches and prepare evidence for an architecture decision record."
      },
      {
        "question": "Does it write production code?",
        "answer": "It can outline proof of concept work, but production code still needs normal engineering review."
      },
      {
        "question": "How many options should I compare?",
        "answer": "The skill recommends at least two or three options when the decision has meaningful alternatives."
      },
      {
        "question": "Can it evaluate vendor tools?",
        "answer": "Yes. Provide requirements, constraints, pricing context, and trusted sources for the strongest result."
      },
      {
        "question": "Is it suitable for quick investigations?",
        "answer": "Yes. The template includes a timebox so research stays focused and produces a clear decision."
      }
    ]
  },
  "file_structure": [
    {
      "name": "references",
      "type": "dir",
      "path": "references",
      "children": [
        {
          "name": "technical-spike.template.md",
          "type": "file",
          "path": "references/technical-spike.template.md",
          "lines": 218
        }
      ]
    },
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 56
    }
  ]
}
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