Use when positioning an American Journal of Political Science (AJPS) manuscript against the literature. AJPS is double-blind, so positioning must engage the relevant debates while keeping the manuscript fully anonymized (third-person self-citation, no first-person "we showed"). Stakes the contribution; it does not write the lit review.
SkillScore77Maintained
Automatic
◆Research pack
Last verified 8/15/2026
What it changes
Passed 17 of 22 test cases with the skill, and 3 of 22 without it.
Without skill14%
With skill77%
Checks it passed that the model alone missed
Uses the bracket tag 【Gap】.
Uses the bracket tag 【Move】.
Uses the bracket tag 【Debate】.
and 10 more in the full report
17 fixed0 passed either way2 still failing3 broke
Pass-rate lift
+64 pp
Tokens
+44%
Agent turns
0%
Response time
-8%
Model gemini-3.6-flashMeasured 8/15/2026v117 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 17
Prompt
In my draft intro for a study on campaign finance, I included a footnote saying: 'This research was supported by NSF Grant #1928374 and presented at the 2023 MPSA panel on money in politics.' Does this pass the anonymity check for double-blind review at AJPS?
What was checked, without and with the skill
Checked
Without skill
With skill
Flags grant numbers as double-blind anonymity violations.
Passed
Passed
Uses the bracket tag 【Anonymity】.
Missed
Passed
case-10 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md90 linessingle file
Literature Positioning (ajps-literature-positioning)
At AJPS the introduction must do two things at once: place the paper inside a live empirical or
theoretical debate that a broad political-science readership recognizes, and stay consistent with
double-blind review. The second constraint is easy to break — a single "as we demonstrated in our
2021 paper" can identify the authors. Positioning is where the contribution is staked and where
anonymity is most often lost.
When to trigger
Drafting or revising the introduction and the "contribution" paragraph
A reviewer said you "missed obvious work" or "don't engage the debate"
Distinguishing your contribution from the closest prior papers
Checking that self-citations are anonymized for double-blind review
How AJPS wants the literature engaged
Engage a debate, not a citation pile. Name the live disagreement, the contested estimate, or
the open mechanism your paper speaks to, and cite the works that define it.
Locate the marginal contribution precisely. "Prior work estimates effect E assuming A; we relax
A / identify E cleanly / show E is conditional on C." A generalist reader should see the increment.
Pre-empt the obvious rival. AJPS reviewers are expert and quantitatively literate; name the
strongest alternative explanation and signal how the design adjudicates it (hand off to
ajps-research-design).
Speak to a broad readership. AJPS spans subfields; show why a reader outside your niche should
care, without diluting the specialist contribution.
Third-person self-citation. Cite your own prior work as you would anyone else's — never "in our
earlier work" or "we previously showed."
No identifying tells. Remove acknowledgments, grant numbers, named datasets you uniquely hold,
conference-presentation mentions, and "available on my website" links.
Watch the bibliography. A wall of single-author self-cites can de-anonymize even in third person;
cite only what the argument needs (see ajps-submission).
Anti-patterns
A "literature dump" with no organizing debate
First-person self-reference that breaks anonymity ("as we showed in...")
Use when positioning a British Journal of Political Science (BJPS) manuscript against the literature so it reads as a contribution of wide, cross-subfield, international interest. BJPS readers span subfields and countries, so the paper must engage the literatures they expect and avoid the desk-screen trap of looking parochial. Stakes the contribution; it does not write the lit review.
Use when defending the research design of an American Journal of Political Science (AJPS) manuscript — causal identification for observational work, experimental and survey-experimental design, formal-empirical linkage, or case-based inference. AJPS reviewers are quantitatively demanding, so identification must license the claim being made. Strengthens the design; it does not write code.