跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
法律与合规

checkpro

Audit essays, reports, literature reviews, dissertations, proposals, and source-backed assignments for high-score academic quality. Use when the user asks whether a paper can get a high grade, wants teacher/rubric feedback addressed, needs a pre-submission review, or needs checks for strict rubric compliance, academic standards, prompt/rubric alignment, argument quality, comparative analysis, evidence hierarchy, table/figure integration, citation specificity, conclusion strength, academic language, source-claim integrity, or evidence boundaries.

zxzin · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add zxzin/runpro --skill checkpro

技能说明


name: checkpro description: Audit essays, reports, literature reviews, dissertations, proposals, and source-backed assignments for high-score academic quality. Use when the user asks whether a paper can get a high grade, wants teacher/rubric feedback addressed, needs a pre-submission review, or needs checks for strict rubric compliance, academic standards, prompt/rubric alignment, argument quality, comparative analysis, evidence hierarchy, table/figure integration, citation specificity, conclusion strength, academic language, source-claim integrity, or evidence boundaries.

CheckPro

Use this skill to find grade-relevant academic weaknesses that ordinary formatting, citation, or completeness checks miss. The goal is to identify whether a written assignment is only complete or is actually strong enough to target a high score.

Do not promise a grade. Give a conservative quality judgement and a targeted repair plan.

High-score readiness is a blocking judgement, not a courtesy label. If a fixable weakness remains in prompt alignment, rubric coverage, evidence support, analysis depth, citation integrity, or final argument quality, do not call the work high-score ready or 90+ plausible.

Inputs

Prefer, in this order:

  1. assignment brief, rubric, marking criteria, or teacher feedback
  2. current .docx, .pdf, Google Doc text, or pasted draft
  3. source list or reference list
  4. any rewriting constraints, if relevant

If no rubric is available, infer the likely academic criteria from the genre and state that the audit is rubric-inferred.

If the prompt, rubric, or assignment question is unavailable and the document's required task cannot be reconstructed confidently, do not give a 90+ plausible judgement. Mark prompt/rubric alignment as unresolved and ask for the missing brief or audit only against inferred criteria.

Default Audit Order

Run the audit in this order unless the user asks for a narrower check:

  1. reconstruct the exact assignment task
  2. build a rubric ledger from the brief, rubric, marking criteria, teacher feedback, and required format rules
  3. map the draft against each rubric item
  4. check academic standards and formatting conventions
  5. check source-claim integrity for the major claims
  6. check argument quality, synthesis, visuals, and conclusion strength
  7. give the most conservative score-risk judgement
  8. produce a targeted repair plan

Do not start with a broad quality impression. The rubric and academic-standard checks control the final judgement.

Rubric Compliance Ledger

When a rubric, marking criteria, assignment brief, teacher feedback, or required question is available, create a rubric ledger before judging quality.

Each rubric item should be separated into a distinct check with:

  • criterion: the exact requirement, question, or marking criterion
  • source: where it came from, such as rubric row, brief line, teacher comment, or template requirement
  • weight_or_importance: explicit mark weight if provided, otherwise inferred importance
  • draft_location: section, paragraph start, page, table, figure, or appendix where the answer appears
  • status: pass, partial, fail, or not assessable
  • evidence: why the status was assigned
  • repair: the smallest fix needed if status is partial, fail, or not assessable

Rubric rules:

  • do not merge multiple rubric criteria into one broad judgement
  • do not treat a general discussion as satisfying a specific required question unless the answer is visible and direct
  • do not call the paper high-score ready if any high-weight rubric item is fail or not assessable
  • do not call the paper 90+ plausible when multiple low- or medium-weight rubric items remain partial
  • if no rubric is provided, create a rubric-inferred ledger and mark the limitation clearly
  • if teacher feedback exists, treat each actionable feedback point as a rubric item until it is addressed or explicitly not applicable

Academic Standards Gate

Check academic conventions as a strict gate, not as cosmetic polish.

The audit must verify when relevant:

  • citation style is identified from the assignment rather than guessed
  • in-text citations and reference-list entries match each other
  • reference-list ordering, punctuation, capitalization, italics, hanging indents, numbering, or superscripts match the required style when assessable
  • source author names, initials, years, titles, journal/proceedings/book details, DOI/URL, and access details are not simplified or invented
  • every borrowed idea, statistic, definition, method, framework, table, figure, or distinctive claim is cited
  • paragraphs follow academic reasoning: claim, evidence, analysis, and implication
  • core terms, scope boundaries, comparison criteria, methodology, and framework choices are defined before evaluative claims use them
  • headings, captions, tables, figures, appendices, page layout, word count, and file format follow the brief or template
  • figures and tables are referred to in the text, captioned correctly, and interpreted in prose
  • figures in papers do not duplicate the title inside the image when an external figure caption already supplies it
  • language is formal, precise, and field-appropriate without generic filler or unsupported exaggeration

If an academic-standard defect is visible and fixable, treat it as a repair item before high-score signoff.

Source-Claim Integrity Gate

For source-backed work, audit the relationship between important claims and sources.

At minimum, check:

  • major factual, empirical, evaluative, and comparative claims have suitable support
  • the cited source actually supports the specific claim attached to it
  • the claim preserves the source's direction, magnitude, units, sample, method, population, date range, and conditions when they matter
  • broad wording such as better, effective, significant, sustainable, high quality, or improved is tied to a measured or clearly defined outcome
阅读完整来源 ↗