literature-review-skills / rules
Cursor rule2 starsChanged 36 days agoMITView on GitHub
Literature review tasks, continue the review, what is the next step, where are we in the review, start the review workflow
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,329 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- exemplar-review-analysisSkill
- figure-permissionsSkill
- journal-selectionSkill
- literature-screeningSkill
- manuscript-polishingSkill
- paper-deep-readingSkill
- reviewer-responseSkill
- review-figures-and-tablesSkill
- review-orchestratorSkill
- review-outline-builderSkill
- review-project-setupSkill
- review-scoping-and-gapsSkill
- review-section-drafterSkill
- review-writingSkill
- search-export-and-dedupSkill
- search-strategy-builderSkill
- submission-packageSkill
- zotero-library-syncSkill
The file
We split this literature-review.mdc into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 39
Read skills/review-orchestrator/SKILL.md first when deciding what to do next.
≈ “Common” is an estimate: at least 1 in 5 of the 6,873 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
--- description: "Literature review tasks, continue the review, what is the next step, where are we in the review, start the review workflow" alwaysApply: false --- # Literature review skills This repository is the source of 18 literature-review skills (instruction packs for each review stage). A Cursor rule tells Cursor how to handle a project. Cursor loads installed skills, and this rule guides agents to in-repo paths and shared gates (yes/no checkpoints the human must pass before later stages unlock). ## Skills Below are the 18 skills in this repository, each with its `skills/<name>/SKILL.md` entry point: - `skills/exemplar-review-analysis/SKILL.md` - `skills/figure-permissions/SKILL.md` - `skills/journal-selection/SKILL.md` - `skills/literature-screening/SKILL.md` - `skills/manuscript-polishing/SKILL.md` - `skills/paper-deep-reading/SKILL.md` - `skills/review-figures-and-tables/SKILL.md` - `skills/review-orchestrator/SKILL.md` - `skills/review-outline-builder/SKILL.md` - `skills/review-project-setup/SKILL.md` - `skills/review-scoping-and-gaps/SKILL.md` - `skills/review-section-drafter/SKILL.md` - `skills/review-writing/SKILL.md` - `skills/reviewer-response/SKILL.md` - `skills/search-export-and-dedup/SKILL.md` - `skills/search-strategy-builder/SKILL.md` - `skills/submission-package/SKILL.md` - `skills/zotero-library-sync/SKILL.md` ## Start here Choose the entry skill from what the user has: see `docs/START_HERE.md`. A draft goes straight to `skills/review-writing/SKILL.md`. By default the agent searches free APIs and downloads open-access PDFs itself; the user is asked only for the ranked please-fetch list. Subscription databases and Zotero are optional. ## Routing Read `skills/review-orchestrator/SKILL.md` first when deciding what to do next. Route to exactly one next skill per turn. Do not start a second skill in the same turn. Judge the current stage from `project.yaml` and `LOG.md`. An earlier unpassed gate beats a later existing file. ## Human gates Gates are yes/no checkpoints before later stages unlock. Only the YAML boolean `true` in `project.yaml` counts as passed (`topic_lock`, `search_lock`, `inclusion_lock`, `outline_lock`, `journal_lock`, `final_submit`). The agent must not confirm a gate for the user. Each confirmation in `LOG.md` must end with `| human`. See `shared/gates.md`. - `shared/gates.md` ## Shared rules - `shared/decision_cards.md` - `shared/evidence_table_schema.md` - `shared/writing_rules.md` ## Scripts Helper scripts live under `skills/<name>/scripts/` when present, with matching tests under `skills/<name>/tests/`. Open your terminal at the repo root and run the pytest test runner: ``` python -m pytest -q ``` Some skill tests need pandas. CI runs the tests on several combinations of Python and pandas versions.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

