Skip to content

MVPavan/via / .claude/skills/research

research

Verified

Use when a decision needs multiple sources gathered and weighed. Answer a single factual lookup directly from an appropriate source.

FileKindSize
SKILL.mdskill md2.1 KB
agents/openai.yamlconfig42 B
references/examples.mdmarkdown2.7 KB
references/frameworks.mdmarkdown3.1 KB
references/playbooks.mdmarkdown3.8 KB
references/source-selection.mdmarkdown2.2 KB
references/synthesis-engine.mdmarkdown1.9 KB

references/playbooks.md

View on GitHub
# Research Playbooks

Pick one primary playbook. Pull from a second only if the question truly spans domains.

## 1. Technology Or Tooling Decision

Use for: frameworks, SDKs, databases, queues, workflow engines, observability, hosting, LLM infrastructure.

Sequence:
1. Define the decision and non-negotiables.
2. List viable options and explicit exclusions.
3. Compare current capabilities from official docs.
4. Check integration fit, operational burden, failure modes, pricing, ecosystem maturity, and migration cost.
5. Find practitioner evidence for real-world pain.
6. Recommend one option, a fallback, and upgrade triggers.

Best frameworks: decision matrix, build-vs-buy, ecosystem maturity, risk register.

## 2. Investing And Fundamental Research

Use for: public-company research, industry trends, ripple effects, catalysts, competitive positioning, thesis validation.

Sequence:
1. Define the investable question and time horizon.
2. Separate trend, company exposure, fundamentals, valuation, catalysts, and risks.
3. Use primary filings and transcripts before commentary.
4. Map first-order and second-order beneficiaries or losers.
5. Compare unit economics, margins, balance sheet, management incentives, and competitive durability.
6. Red-team the thesis with disconfirming evidence and base rates.

Best frameworks: thesis map, catalyst/risk timeline, segment exposure map, valuation sensitivity.

## 3. Product, Market, Or Competitive Landscape

Use for: product opportunities, feature research, competitors, market entry, pricing, customer needs.

Sequence:
1. Identify the customer, job, and buying trigger.
2. Map segments and competing alternatives, including "do nothing".
3. Compare pricing, packaging, positioning, distribution, and switching costs.
4. Read negative reviews and support docs for implementation reality.
5. Identify gaps, over-served segments, under-served segments, and hidden adoption blockers.
6. Produce decision points and the conditions under which each option wins.

Best frameworks: JTBD, positioning map, segmentation, value proposition, win/sacrifice table.

## 4. Developer Tooling Or Architecture Research

Use for: orchestration architecture, agent harnesses, code tools, infra design, platform tradeoffs.

Sequence:
1. Define the workflow and correctness requirements.
2. Separate control plane, execution plane, data plane, tool plane, and human approval plane.
3. Compare build vs adopt vs compose.
4. Evaluate reliability, debuggability, security, extensibility, and operator burden.
5. Check official docs and live source before trusting examples.
6. Recommend the smallest architecture that satisfies the real workflows.

Best frameworks: architecture responsibility map, failure-mode analysis, dependency budget, upgrade triggers.

## 5. Policy Or Regulatory Research

Use for: laws, regulation, compliance, procurement rules, standards, platform policies.

Sequence:
1. Identify jurisdiction, regulator, regulated actor, and date sensitivity.
2. Read primary law/rule/guidance before summaries.
3. Check enforcement actions and implementation guidance.
4. Separate written rule, enforcement reality, and practical compliance pattern.
5. Build a risk matrix: likelihood, severity, evidence, mitigation.
6. State what needs counsel or expert confirmation.

Best frameworks: regulatory map, enforcement reality, risk matrix, compliance gap list.

## 6. Problem-Solving Or Operations

Use for: diagnosing failures, reducing cost, improving conversion, fixing workflow bottlenecks.

Sequence:
1. Define the measurable problem.
2. Identify symptoms vs causes.
3. Find analogous problems and case studies.
4. Compare solution classes by evidence, cost, time, risk, and prerequisites.
5. Identify quick wins, strategic bets, and false fixes.
6. Recommend a staged path and validation metrics.

Best frameworks: root cause analysis, analogous industry scan, solution matrix.
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