agentsclimarketplace

Admissions ops

Skill TianCZeng/admissions-ops/.agents/skills/admissions-ops

Graduate admissions workspace for AI agents — the LLM does the judgement, deterministic validators keep it honest. Sourced program evaluations, evidence-grounded CVs and statement drafts, nothing final without human review.

Install
npx -y skills add TianCZeng/admissions-ops --skill admissions-ops

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 18 days oldThe repository was created 18 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Graduate admissions command center -- evaluate programs, adapt academic CVs, compare options, and track applications

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

4.0 KB, 881 tokens by cl100k_base, as published. Nobody here has run it

admissions-ops Router

Mode Routing

Determine the mode from $mode:

InputMode
emptydiscovery
official program URLprogram
programprogram
input beginning with program, including --write-draftsprogram
inboxinbox
comparecompare
cvcv
statementstatement
trackertracker

If $mode is not recognized but contains an official university or department program URL, route to program.

Discovery Mode

Show this menu:

admissions-ops

Available commands:
  /admissions-ops {official URL}  Run the one-program draft pipeline
  /admissions-ops program         Run one URL or selected inbox entry through the draft pipeline
  /admissions-ops inbox           Review curated entries in programs/inbox.yml
  /admissions-ops compare         Compare evaluated programs only
  /admissions-ops cv              Create an academic CV or resume adaptation plan
  /admissions-ops statement       Create a statement plan and draft for a reviewed program
  /admissions-ops tracker         Review tracker and checklist state

Runtime commands that read or write applicant-specific live state require --student <student-id> and use students/{student-id}/. For the program workflow, --write-drafts is explicit user approval to write Review Required CV/resume and statement draft artifacts after successful dry-runs; it is not approval to mark anything final or externally ready.

Full Pipeline Default

The default program workflow is one agent-led draft pipeline:

  1. read the selected students/{student-id}/ workspace;
  2. retrieve and cite official sources for the selected program only;
  3. write or update shared catalog facts and the student-scoped evaluation, report, checklist, and tracker row;
  4. create or revise the LLM-authored CV/resume adaptation plan and, when official instructions require a statement and statement-brief.md exists, the LLM-authored statement_plan, statement draft, and claim map;
  5. run npm run cv -- --student <student-id> --program <program-id> as the deterministic dry-run renderer and validator (append --document-type academic_cv|admissions_resume when the user explicitly overrides the plan's document type; the override is logged and, on write, persisted into the plan);
  6. when a statement plan, LLM-authored draft, and claim map are in scope and statement-brief.md exists, run npm run statement -- --student <student-id> --program <program-id> as the deterministic dry-run packager and validator;
  7. inspect the dry-run artifacts, links, evidence maps, and validation concerns;
  8. if the user specified --write-drafts and the dry-runs succeeded without blockers, rerun the applicable deterministic renderer or packager with --write to refresh only Review Required draft artifacts and report/tracker links;
  9. return one final review bundle.

Stop mid-pipeline only for a real blocker: missing selected-student files, inaccessible official sources, ambiguous program identity or intake, conflicting official requirements that prevent a truthful draft, or explicit approval before any --write operation. A user-specified --write-drafts flag is that approval only for post-dry-run draft artifact writes.

Context Loading

For program, compare, cv, statement, and tracker, read:

  • AGENTS.md
  • DATA_CONTRACT.md
  • modes/_shared.md
  • modes/{mode}.md

For inbox, read:

  • AGENTS.md
  • modes/inbox.md
  • programs/inbox.yml if it exists, otherwise programs/inbox.example.yml

Execute the selected mode instructions. Do not run broad discovery unless a future mode explicitly implements it.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 327,132. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.