sidiangongyuan/codex-skills-library / skills/paper-writing
paper-writing
VerifiedDraft or restructure research-paper sections, refine local prose, and audit manuscript-wide consistency. Use for evidence-grounded academic writing and revision, not independent acceptance-risk review or official rebuttal management.
| File | Kind | Size |
|---|---|---|
| LICENSE | other | 1.0 KB |
| SKILL.md | skill md | 7.2 KB |
| agents/openai.yaml | config | 325 B |
| references/benchmark.md | markdown | 2.8 KB |
| references/closing-material.md | markdown | 1.9 KB |
| references/consistency.md | markdown | 4.1 KB |
| references/experiments.md | markdown | 5.8 KB |
| references/front-matter.md | markdown | 4.2 KB |
| references/method.md | markdown | 1.9 KB |
| references/prose.md | markdown | 3.1 KB |
| references/related-work.md | markdown | 1.8 KB |
references/related-work.md
View on GitHub# Related Work and Positioning
Organize prior work by the capabilities, assumptions, or research questions that
help locate this paper. Placement, length, theme count, and citation density depend
on the manuscript and venue, not a mandatory template.
A theme can explain a foundation, complement, or distinction; it need not end in
a critique. Do not invent a common limitation for a group whose members differ,
or force every paragraph to end with "Unlike these, we...". Related work should
accurately position the contribution, not demonstrate that all prior work fails.
Use verified sources to distinguish what related datasets, protocols, and methods
actually support. Closely overlapping or concurrent work may narrow a novelty
claim even when it does not change the main narrative. Do not ignore relevant
work solely because it is recent, or claim priority from an unverified chronology.
Cite baselines and reused components where readers need their provenance; not
every instrumental method requires its own Related Work discussion. Avoid turning
a list of all citations into the section structure. Describe a shared design
pattern accurately without implying architectural identity.
For uncertain titles, authors, publication versions, or substantive claims, consult
primary records. DBLP BibTeX can be a useful metadata source when available;
reconcile it with the actual paper and publication record rather than treating an
index or search snippet as infallible. Do not fabricate missing fields or silently
mix the title of one version with the authors of another.
Use an available evidence-verification workflow when needed, not as a mandatory
new literature search for every wording edit. If the user requests recent examples,
read the relevant passages and borrow their explanatory function, not unverified
claims about what a venue expects or a fixed sentence skeleton.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |