Skip to content

VincenzoImp/academic-research-skills / skills/explore-sota

explore-sota

Verified

Use when building or expanding the SOTA — from an idea, keywords, seed papers, or the existing collection — through MCP search, citation chasing, triage, and digestion of accepted papers.

FileKindSize
SKILL.mdskill md3.8 KB
references/citation-chasing.mdmarkdown1.7 KB

references/citation-chasing.md

View on GitHub
# Citation Chasing & Anti-Echo-Chamber

## Review scales

| Scale | Use | Included papers | Chasing |
|---|---|---|---|
| quick-scan | orient an idea | ~8–15 | seeds + one high-yield hop |
| focused-sota | defensible related work | ~20–40 | both directions to local saturation |
| full-survey | survey-grade coverage | 50+ | iterative frontier expansion with recorded saturation |

Budgets are planning aids. Stop at saturation or at budget with blind spots
recorded — never pad with weak papers.

## Frontier discipline

1. Expand the current seed set one hop at a time (backward = references,
   forward = citers; both via semantic-scholar).
2. Deduplicate before triage: DOI, arXiv id, S2 id, then
   title + first author + year.
3. Triage chased candidates with the same inclusion/exclusion criteria as
   keyword hits.
4. Promote a candidate into the next seed set only deliberately — when it
   is digested and central to the scope. Never recursively chase everything.
5. Saturation = a new hop yields mostly duplicates or out-of-scope records.
6. If the budget ends first, record the unexpanded frontier explicitly
   instead of claiming coverage.

## Anti-echo-chamber checks (run before declaring saturation)

- Seeds span at least project-specific, seminal, and recent-frontier types.
- At least one adjacent-terminology or adjacent-community query ran with
  terms learned from full readings.
- At least one negative/contrastive query ran (failure, limitation,
  negative result, reproduction, replication).
- A sample of rejected near-misses was re-inspected to confirm the criteria
  are not too narrow.
- No single author group, venue, benchmark, or citation cluster dominates
  the SOTA without a recorded reason.
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