College Application
Treat college application planning as a decision process of “understand yourself → understand careers/majors/industries → constrain choices with admissions data → generate an auditable report.” The main interaction takes place in the Agent conversation; HTML is used only to present the final report and is no longer the primary data-entry interface.
Mandatory disclaimer
At startup, first tell the user: This service is for reference only when making Gaokao college application decisions. All personality analyses, career recommendations, industry assessments, and admission estimates are based on public sources and model inferences; they cannot replace the provincial education examination authority, the university’s admissions prospectus, the official application system, or input from teachers or parents. Final choices must be cross-checked. The same notice must appear at both the top and bottom of the final HTML report.
Workspace files
- : Candidate profile, personality assessment summary, career-direction hypotheses, and Gaokao information. See CANDIDATE-FORMAT.md for the format.
- : Personality test scoring, interpretation, and career-direction hypotheses. See PERSONALITY-REPORT-FORMAT.md for the format.
- : Source ledger for all theories, industry, major, and admissions data. See SOURCES-FORMAT.md for the format.
- : Career/major research, application recommendations, and final plan. See PLAN-FORMAT.md for the format.
- : Final browsable report, using assets/final-report-template.html.
- , , : If long-term tracking or an independent audit is needed, follow the corresponding format files.
The legacy
assets/college-application-template.html
and
scripts/wait_for_request.py
/
/
/
are legacy compatibility assets for the web task queue workbench. The new main flow must not require the user to open a web page for data entry or make the waiter a mandatory step.
Fixed dialogue flow
1. Generate a personality assessment HTML form
Use the script to generate a static HTML form from assets/personality-assessment-form.html and give it to the user to complete in a browser:
bash
python3 <skill-dir>/scripts/create_assessment.py \
--workspace <candidate workspace absolute path> \
--open
automatically opens the form in the system’s default browser, so the user does not have to find it in a folder. The script outputs a file path such as
<workspace>/personality-assessment-YYYY-MM-DD.html
by default. Tell the user the file path and explain: Please open the HTML form in your browser, and after completing it, click “Download JSON for Agent,” then send the downloaded JSON file back, paste its contents, or authorize the Agent to read the file. Do not ask the user to complete the questions one by one in the terminal chat.
The Markdown template
assets/personality-assessment-template.md is only a fallback: if the user cannot open the HTML, run
create_assessment.py --format md
to generate a fillable Markdown form.
The questionnaire is based on the RIASEC Career Interest Inventory and the Mini-IPIP abbreviated Big Five personality inventory, with 32 items scored from 1 to 5.
2. Generate a personality and career direction report
Parse the personality assessment result JSON returned by the user (or the fallback Markdown), and score it according to the rules in the template. After scoring, first generate a readable HTML report so the user can confirm that they understand it:
bash
python3 <skill-dir>/scripts/render_personality_report.py \
--input <personality-assessment-result.json> \
--output <candidate workspace absolute path>/personality-report.html
The report should present plain-language key conclusions first, followed by the full score table and limitations in expanded form.
- RIASEC: Obtain the top three codes, such as .
- Big Five: Calculate relative levels of Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism; reverse-scored items must be reversed.
- Output 3–6 career direction hypotheses. For each direction, include “supporting evidence / counterevidence or risks / questions requiring real-world validation.”
The personality test can only serve as a directional clue; do not present its results as a diagnosis or a verdict on the person’s fate.
3. Conduct in-depth research on careers, majors, and industries
Generate 3–6 major clusters around the career direction hypotheses. Every major cluster must be researched for the following:
- Actual learning content, core courses, and differences in curriculum structure.
- Real day-to-day work, career outcomes, cross-major pathways, and pathways for further study.
- Industry demand, geographic distribution, degree requirements, qualification requirements, and the impact of AI/automation.
- Evidence supporting and contraindicating fit with this direction.
- Clickable, traceable sources.
Preferred sources include the Ministry of Education’s major catalog, Sunshine Gaokao, official university websites for curriculum plans/admissions prospectus/employment quality reports, the National Bureau of Statistics, human resources and social security departments, industry regulators, and authoritative industry associations. Job boards and commercial reports may be used only as supplementary signals, and any sample bias must be stated.
4. Generate a Gaokao information HTML form
Use the script to generate a static HTML form from assets/admission-info-form.html and give it to the user to complete in a browser:
bash
python3 <skill-dir>/scripts/create_admission_info.py \
--workspace <candidate workspace absolute path> \
--open
automatically opens the form in the system’s default browser, so the user does not have to find it in a folder. The script outputs a file path such as
<workspace>/admission-info-YYYY-MM-DD.html
by default. Tell the user the file path and explain: Please open the HTML form in your browser, and after completing it, click “Download JSON for Agent,” then send the downloaded JSON file back, paste its contents, or authorize the Agent to read the file. Do not ask the user to complete the fields one by one in the terminal chat.
The Markdown template
assets/admission-info-template.md is only a fallback: if the user cannot open the HTML, run
create_admission_info.py --format md
to generate a fillable Markdown form.
The Gaokao information document must cover the following:
| Item | Requirement |
|---|
| Admissions province | Required |
| Application year | Defaults to the current year and can be changed |
| Preferred application regions | Multiple selections allowed; distinguish required/preferred/no preference |
| Examination format | Automatically populated and reviewed based on the province according to references/province-exam-mode.md |
| Subject selection | Validate under 3+3 or 3+1+2; Physics and History are mutually exclusive |
| Gaokao score / provincial rank | At least one is required; rank takes priority |
| Batch/category/special eligibility | For example, regular category, special plans, Sino-foreign cooperation, etc. |
| Tuition, family circumstances, and other practical constraints | Optional but should be proactively raised; do not proactively collect private health or medical-examination information; the user should check the admissions prospectus for related major restrictions |
If information is incomplete, obtain the missing information first rather than directly generating application recommendations.
5. Estimate admission opportunities and provide application recommendations
Follow references/admission-estimation.md. Prioritize comparisons by rank. Output an interval probability only when there are at least three comparable years, the current year’s enrollment plan has been published, the definitions are consistent, and the sources are verifiable. Otherwise, output only qualitative levels—“Reach / Possible / Relatively Safe / Safety”—and clearly state which data are missing.
Never use aggregators, self-media accounts, forums, or cutoff scores without a stated year as key evidence. Critical admissions facts must be checked against the provincial education examination authority, Sunshine Gaokao, or the university’s official undergraduate admissions website.
Agent proactive data retrieval strategy
If the user provides only a score and no rank, the Agent should first attempt to retrieve the corresponding year’s official score-to-rank table from the provincial education examination authority. If data for the current year have not been published, the most recent year may be used to estimate a “reference rank,” but it must be explicitly stated that this cannot replace the actual rank. Only when no official source can be found, the page is no longer accessible, or data for the user’s province are unavailable should the user be asked to upload or provide a score-to-rank table, enrollment plan, or cutoff-score file.
6. Generate the final HTML report
The final report should preferably be rendered with the script:
bash
python3 <skill-dir>/scripts/render_report.py \
--workspace <candidate workspace absolute path> \
--output <candidate workspace absolute path>/final-report.html
The script reads
,
,
, and
from the workspace, and applies
assets/final-report-template.html. When fields are missing, display “To be supplemented / Unverifiable”; never fabricate content.
The final report should first present the key conclusions: whether the direction is a good match, whether the current data are sufficient, and what to add next. Put the full personality scores, detailed major and industry information, methodology, uncertainties, and source ledger in expanded collapsible sections later, so that the user is not overwhelmed by technical terminology as soon as they open the report.
The final report must include at least the following:
- A “For reference only / Must be cross-checked / Does not constitute an admission guarantee” notice at the top.
- Personality assessment results: RIASEC, Big Five, interpretation, and limitations.
- Suitable career directions and major clusters: matching evidence, counterevidence, and practical exploration recommendations.
- In-depth analysis of careers, majors, and industries: learning content, day-to-day work, trends, requirements, and risks.
- Gaokao information and admission analysis: province, examination format, subject selection, score/rank, data definitions, and reach/match/safety recommendations.
- Source ledger: full URL, publishing organization, year/definition, last verification date, and status.
- Conclusions that cannot be verified or lack sufficient data must be marked separately and must not be mixed with definitive conclusions.
7. Optional independent audit
If the user requests a review, the report will be used for an important decision, or the Agent is uncertain about a key source, launch a fresh subagent to conduct an independent audit according to AUDIT-FORMAT.md. If the audit does not pass, do not display “Approved for formal submission.”
Sources and honesty boundaries
- Every external fact, industry assessment, major-related fact, admissions rule, cutoff-score datum, and probability input must have and be traceable to the full URL in .
- Search-result snippets are not sources; Tavily/WebSearch can only be used to discover links and cannot directly support conclusions.
- If a page is no longer accessible, sources conflict, years do not match, or definitions are inconsistent, explicitly state “Unverifiable / Conflicting / Supplementary clue only.”
- Do not output promise-based wording such as “guaranteed admission,” “assured admission,” or “100%.”