Agent Skills
› brycewang-stanford/Awesome-Journal-Skills
› proghg-revision
proghg-revision
GitHub用于处理人文地理进展（PiHG）审稿意见的修订与回复。针对覆盖缺口、公平性、概念论证等反馈，生成逐点回复信及修订计划，协助作者整合文献、调整立场并优化文章结构。
Trigger Scenarios
收到编辑或审稿人对综述/进度报告的修改意见
审稿人指出文献遗漏、偏见或概念不清
需要撰写针对综述文章的逐点回复信
Install
npx skills add brycewang-stanford/Awesome-Journal-Skills --skill proghg-revision -g -y
SKILL.md
Frontmatter
{
"name": "proghg-revision",
"description": "Use when responding to Progress in Human Geography (PiHG) editor and referee feedback on a review or progress report — coverage gaps, fairness\/reflexivity complaints, conceptual-argument asks, accessibility, and scope\/strand fit. Drafts the response and revision plan; it does not run the submission preflight (proghg-submission) or redesign the spine from scratch (proghg-organizing-framework)."
}
Revision & Response for a Review (proghg-revision)
When to trigger
- An editor/referee letter on the review or progress report arrived
- Referees flagged missing literatures/traditions, imbalance, mischaracterization, partisanship, or "reads like a list"
- The editor asked to expand, cut, or rebalance coverage, or to sharpen the conceptual argument
- You need a point-by-point response for a review article, not an empirical paper
Categories of review feedback (and how to answer each)
PiHG revision asks cluster differently from empirical-paper asks. Triage every point into one bucket:
| Feedback type | Typical phrasing | Response move |
|---|---|---|
| Coverage gap | "you omit the X literature / author Y / the Z tradition" | almost always concede and integrate — place the missing work in the right framework cell; re-run saturation (proghg-literature-synthesis) and update the coverage account |
| Fairness / reflexivity | "this slights tradition Z / is partisan / over-cites the author" | steelman the slighted side; surface positionality; re-audit self-citation and tradition balance (proghg-comprehensiveness-and-balance) |
| Appraisal accuracy | "you mischaracterize work W" | correct precisely; reviewed authors often referee — fix exactly |
| Conceptual argument / structure | "this is an annotated bibliography / a neutral roundup" | strengthen or make explicit the spine and the position (proghg-organizing-framework); do not just reorder paragraphs |
| Accessibility | "a geographer outside the subfield can't follow Section 4" | add intuition, define jargon (proghg-writing-style) |
| Scope / strand / length | "too broad / wrong strand / overruns length" | negotiate with the editor (proghg-editor-strategy); rescope deliberately, within the strand envelope |
| Conceptual-not-empirical | "this reads like an empirical paper / has original cases" | remove original data/cases; reframe as critical synthesis (PiHG publishes no empirical results) |
| Transparency | "how did you decide what to include? from what standpoint?" | document/expand the coverage account + positionality (proghg-transparency-and-reproducibility) |
Writing the response letter
- Point-by-point, quote-then-respond. Reproduce each comment, then state the change and where it lives (section/page/table).
- Coverage asks: concede and integrate. A missing literature or tradition is a real defect in a state-of-the-art review; adding it strengthens the article. Resist defensiveness — the omitting author may be the referee who named it.
- Fairness asks: show the steelman and the reflexivity. Demonstrate the revised text states the other side at its strongest and, where partisanship was alleged, surfaces the author's standpoint openly. If a tradition was slighted, show it is now weighed on its own terms.
- Accuracy asks: fix exactly. Mischaracterizing a reviewed author who is your referee is the fastest route to a hostile second round; correct the wording precisely and, where helpful, quote their own framing.
- Argument asks: sharpen the spine, don't reshuffle. An "annotated bibliography" or "neutral roundup" critique demands a stronger conceptual argument and a clearer position, not reordered paragraphs.
- Disagree rarely and respectfully. If an ask would break the spine or overrun the strand envelope, explain the trade-off and propose an alternative, ideally pre-cleared with the editor.
- Keep the editor central. On scope, strand, and conflicting referee asks, ask the editor to adjudicate rather than satisfying mutually-incompatible referees.
- Track every addition's ripple. Adding a literature can shift the review's center of gravity; after each integration, re-check that the framework cells, the exhibits, the balance audit, and the coverage account still hold, and that the draft still fits the strand's length.
Checklist
- Every comment triaged into a bucket (coverage / fairness / appraisal / argument / accessibility / scope / conceptual / transparency)
- Coverage gaps conceded and integrated into the right framework cell; saturation + coverage account re-run
- Fairness complaints answered by demonstrable steelmanning, surfaced positionality, and self-citation/tradition re-audit
- Mischaracterizations corrected precisely (reviewed authors may be the referees)
- "Annotated bibliography / roundup" asks answered by a stronger/explicit spine and position, not reordering
- Accessibility fixes add intuition / define jargon for the cross-subfield reader
- Any original empirical content removed if flagged as out of scope
- Scope/strand conflicts routed to the editor; rework fits the strand envelope
- Point-by-point letter: quote-then-respond, with section/page/table locations
- Comprehensiveness + balance + coverage account re-audited after all additions
Anti-patterns
- Defending an omission rather than adding the missing literature/tradition (a review gap is a real defect)
- Answering a fairness complaint with assertions of balance instead of revised, steelmanned text and surfaced positionality
- Dismissing or re-mischaracterizing a reviewed author who is likely your referee
- "Fixing" an annotated-bibliography critique by shuffling paragraphs without strengthening the argument
- Bloating scope to satisfy every "also cover…" until the review overruns its strand limit
- Trying to satisfy two contradictory referees instead of asking the editor to decide
Output format
【Triage】each comment bucketed (coverage/fairness/appraisal/argument/accessibility/scope/conceptual/transparency)? Y/N
【Coverage gaps】conceded + integrated into framework cells; saturation + account re-run? Y/N
【Fairness】steelman + positionality shown in revised text; self-citation + tradition balance re-audited? Y/N
【Appraisal fixes】mischaracterizations corrected precisely? Y/N
【Argument asks】spine + position strengthened/made explicit (not reordered)? Y/N
【Scope/strand】fits the strand envelope; any empirical content removed if flagged? Y/N
【Letter】point-by-point, quote-then-respond, with locations? Y/N
【Next step】→ proghg-submission (re-submit the revised review)
Version History
- 1839142 Current 2026-07-05 14:14
