Skip to content

odinfree/storm-ecdsa-harness / skills/elicit-research

elicit-research

Verified

Search academic literature through the Elicit API: papers, clinical trials, reports, systematic reviews and Research Agent sessions. Use when a question needs published evidence or an outside, literature-backed view. Needs your own Elicit API key.

references/systematic-review-recipe.md

View on GitHub
# Systematic review recipe (operator's template, oct 2026)

Use for a deep question that ordinary search has not settled, or when an independent
literature-backed perspective is needed. Check quota first:

    python3 scripts/elicit.py GET /usage

Request body (save as `review-request.json`; never put a key in it):

    {
      "researchQuestion": "ONE PRECISE QUESTION",
      "searches": [{ "query": "FOCUSED SEARCH STRING", "maxResults": 200 }],
      "abstractScreening": { "generate": true, "depth": "thorough" },
      "fulltextScreening": { "reuseAbstractCriteria": true, "depth": "thorough" },
      "extraction": { "generate": true, "useFigures": false },
      "generateReport": true
    }

Create, then poll the typed detail endpoint (never re-create because it is slow):

    python3 scripts/elicit.py POST /sessions/systematic-reviews --body review-request.json --out review-session.json
    python3 scripts/elicit.py GET /sessions/systematic-reviews/RETURNED_ID --out review-status.json

Read the schema first (`POST /sessions/systematic-reviews --schema`): omitted stages are skipped,
fulltext screening needs abstract screening, and the report needs extraction. The key lives only in
`~/.config/elicit/api-key` (mode 600).
Use a systematic review only for a question that blocks the campaign or needs an outside perspective;
use /search/papers for quick lookups.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall