Skip to content
Agentmart
Submit a tool

essay-ingest

Review or improve an essay the user already wrote.

Skill by dhruvaldarji

IndexedMIT
Write a review

Chalk Labs

Need help deploying essay-ingest?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/dhruvaldarji-essay-ingest

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Review or improve an essay the user already wrote. Use when the user pastes, attaches, or points to an existing application essay, personal statement, statement of purpose, or scholarship essay and asks for a review, feedback, or revisions, or asks to make it (or one line, claim, or paragraph of it) stronger, more specific, more personal, less generic, or less like AI. Stores the text as given, grounds every claim in a real experience by asking, and proposes changes the user approves one at a time. Never invents details.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/essay-ingest

What's inside

Skill name
essay-ingest
Description
Review or improve an essay the user already wrote. Use when the user pastes, attaches, or points to an existing application essay, personal statement, statement of purpose, or scholarship essay and asks for a review, feedback, or revisions, or asks to make it (or one line, claim, or paragraph of it) stronger, more specific, more personal, less generic, or less like AI. Stores the text as given, grounds every claim in a real experience by asking, and proposes changes the user approves one at a time. Never invents details.
License
MIT
Instructions
23 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# essay-ingest

The plugin root is `${CLAUDE_PLUGIN_ROOT}` in Claude Code. In Codex and other runtimes it is two
directories above this file. Paths below are relative to that root.

1. Read `README.md` and `system/Ingest.md`. If the user gave only one line or paragraph, treat it as
   the essay text for now and ask for the rest later. Never strengthen a line by adding a detail,
   number, name, or scene the user did not give. Ask one question for the real story instead.
2. Follow `system/Ingest.md` exactly. Resolve the essay text. Read the file the user named, or ask
   the user to paste the essay if there is no file. Then collect the essay prompt, the essay type,
   the limit, and the target program. Ask **one question at a time** with the `ask_question()`
   protocol in `CONVENTIONS.md`.
3. Ask the one required provenance question: did the applicant write this text themselves, without
   AI help? Record the answer as `self_authored` in `Drafts.md`.
4. Create `artifacts/<essay_id>/` from `templates/`, store the essay text verbatim as
   `draft-ingested` in `Drafts.md`, and write `EssayState.md` with `mode: ingest`.
5. Do not rewrite the essay in this step. The review and the suggestions come from `essay-next`, one
   unit at a time. Never invent an experience the applicant did not give.

End by telling the user the essay_id and that `essay-next` starts the review. Say that each
suggestion waits for their yes, edit, or no before it is applied.

From dhruvaldarji/essayos, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 19, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from dhruvaldarji

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get essay-ingest running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying essay-ingest?

CallGet help
Cite this page

essay-ingest skill. Agent Mart. https://agentmart.dev/skills/dhruvaldarji-essay-ingest (last updated 2026-10-24)