Map Your Lit Review Mid Conversation

Map your lit review mid-conversation to surface the underlying debate — skill template

Turn this template into a working skill by resolving every TODO. The seed prompt below is the published Anthropic example this template was derived from; your skill should generalize it for repeated, hands-off use.

Outcome

Claude reads your stack of papers and draws the argument structure inline — clusters by claim, tension lines where camps disagree, blind spots per group.

TODO: Restate the outcome for YOUR context in one sentence: who runs this, on what input, producing what artifact, how often.

Seed prompt (verbatim from source, © Anthropic PBC)

I've read 20 papers on AI in K-12 and I've lost the thread. Can you map out who's actually agreeing with who and where the real disagreements are? I can't tell anymore which papers are building on each other and which are talking past each other. If I click into a group, give me the short version of what they've got and what they're missing.

Required context and inputs

• Papers or consolidated notes file (required)
• Optional: Google Drive connector for direct paper access
• Optional: Projects feature for multi-week reviews
• TODO: exact file paths / folders / message formats this skill should expect
• TODO: domain context the model cannot infer (naming conventions, thresholds, house style)

Tools, connectors, APIs, and authentication

• Google Drive
• TODO: confirm which connectors are enabled in the runtime that will execute this skill
• Authentication: connectors authenticate via their own OAuth flows — this skill must

NEVER ask for, store, or echo credentials, tokens, or API keys. If auth is missing, stop and tell the user which connector to enable.

Permissions and sensitive actions

• Reads: TODO (folders, channels, records this skill may read)
• Writes: TODO (what it may create/modify, and where)
• Held back for the primary agent / human: sending external communications, financial

transactions, deleting or overwriting originals, submitting web forms

Workflow

1. Describe the task
2. Give Claude context (attach papers or notes)
3. Claude creates argument clusters with blind-spot analysis
4. Follow up prompts to refine, expand, or explore further

TODO: adapt the steps above (from the source page) into imperative instructions for the executing agent, including what to do between steps.

Decision points

• TODO: list each point where the skill must choose between paths, with the rule to apply
• Default rule: prefer the reversible option; when two readings of the input are

plausible, surface both rather than picking silently.

Validation criteria

• Output matches the outcome statement above (spot-check against the seed prompt's asks)
• Every factual claim is traceable to a provided input, connector record, or cited source
• TODO: add one domain-specific check a reviewer in your org would apply

Failure modes and fallbacks

• Connector unavailable or unauthenticated → pause, tell the user exactly which connector to enable and why; offer a degraded run from uploaded files
• Ambiguous or missing input → ask one targeted question; if unattended, state the assumption inline and proceed
• Any step would take a sensitive/irreversible action → stop and hand back to the user (see Delegation)

Delegation

Apply the repo's delegation policy (docs/delegation-policy.md — bundle or restate it if you install this skill outside the repo). Defaults for this template:

• Run single-agent unless a step fans out over independent items (files, records,

vendors, channels). Only independent work parallelizes.

• Each delegated task must ship with: the minimal context slice it needs, an explicit

output contract, a validation check the primary agent runs on the result, and a fallback if it returns empty or fails.

• Final review, synthesis, and every sensitive action listed above stay with the

primary agent.

• TODO: name the concrete subtasks (if any) that qualify for delegation here.

Attribution

Derived from Map your lit review mid-conversation to surface the underlying debate (retrieved 2026-07-26). Seed prompt and workflow content © Anthropic PBC. Scaffold structure original to this repository.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: iankiku
• Source: iankiku/agent-skill-factory
• License: MIT

Install and usage instructions live in the source repository linked above.