Search
Development · By cursor
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs. | cursor/ | 10k | 9 repos | ~2.6k | Automated safety check: Pass | No licence | yesterday |
| 2 | Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read. | cursor/ | 10k | 10 repos | ~2.4k | Automated safety check: Pass | No licence | yesterday |
| 3 | Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. | cursor/ | 10k | 3 repos | ~569 | Automated safety check: Pass | No licence | yesterday |
| 4 | Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. | cursor/ | 10k | 14 repos | ~3.1k | Automated safety check: Pass | No licence | yesterday |
| 5 | Sketches types, signatures and module boundaries with stub bodies before real code, compares at least two designs, then implements against the chosen sketch. | cursor/ | 10k | 8 repos | ~1.4k | Automated safety check: Pass | No licence | yesterday |
| 6 | Runs one read-only reviewer subagent per configured model against a diff to challenge a change, then synthesizes a single verdict without applying any fixes. | cursor/ | 10k | 8 repos | ~1.3k | Automated safety check: Pass | No licence | yesterday |
| 7 | Finds what a code change could break outside its diff and proves the single fact that makes it safe by running real code instead of writing an explanation. | cursor/ | 10k | 9 repos | ~964 | Automated safety check: Pass | No licence | yesterday |
| 8 | Designs a step-by-step playbook for large or unfamiliar work, runs it as a loop of hypotheses and measurements, and logs decisions so a human can review them later. | cursor/ | 10k | 8 repos | ~1k | Automated safety check: Pass | No licence | yesterday |
| 9 | Fixes a bug with a failing regression test first when a cheap, focused test path exists, and falls back to the closest practical check when it does not. | cursor/ | 10k | 8 repos | ~786 | Automated safety check: Pass | No licence | yesterday |
| 10 | Answers how-does-this-work and where-should-this-live questions by exploring the codebase with read-only subagents and writing an onboarding-depth explanation. | cursor/ | 10k | 6 repos | ~771 | Automated safety check: Pass | No licence | yesterday |
| 11 | Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services. | cursor/ | 10k | 1 repo | ~1.1k | Automated safety check: Pass | No licence | yesterday |
| 12 | Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. | cursor/ | 10k | 8 repos | ~615 | Automated safety check: Pass | No licence | yesterday |
| 13 | Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. | cursor/ | 10k | 8 repos | ~553 | Automated safety check: Pass | No licence | yesterday |
| 14 | Generate an interactive PR review walkthrough as an HTML page. | cursor/ | 10k | 1 repo | ~2.3k | Automated safety check: Pass | No licence | yesterday |
| 15 | Apply when debugging. An agent skill from cursor/plugins. | cursor/ | 10k | 9 repos | ~312 | Automated safety check: Pass | No licence | yesterday |
| 16 | Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. | cursor/ | 10k | 9 repos | ~343 | Automated safety check: Pass | No licence | yesterday |
| 17 | Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. | cursor/ | 10k | 8 repos | ~383 | Automated safety check: Pass | No licence | yesterday |
| 18 | Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after proof. | cursor/ | 10k | 1 repo | ~3.6k | Automated safety check: Pass | No licence | yesterday |
| 19 | Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation. | cursor/ | 10k | 1 repo | ~2.6k | Automated safety check: Pass | No licence | yesterday |
| 20 | Resolve merge conflicts non-interactively, validate build and tests, and finalize conflict resolution | cursor/ | 10k | 3 repos | ~247 | Automated safety check: Pass | No licence | yesterday |
| 21 | Apply when sequencing an addition, refactor, or rewrite. An agent skill from cursor/plugins. | cursor/ | 10k | 4 repos | ~274 | Automated safety check: Pass | No licence | yesterday |
| 22 | Fetch and summarize review comments from the active pull request | cursor/ | 10k | 4 repos | ~133 | Automated safety check: Pass | No licence | yesterday |
| 23 | Design rules for command-line tools that coding agents can run reliably: flags over prompts, layered help with examples, fast errors, idempotency and dry-run. | cursor/ | 10k | — | ~828 | Automated safety check: Pass | No licence | yesterday |
| 24 | Create a new Cursor plugin scaffold with a valid manifest, component directories, and marketplace wiring. | cursor/ | 10k | — | ~726 | Automated safety check: Pass | No licence | yesterday |
| 25 | A skill your agent uses when the user runs /debug-voice, says voice mode has flaws, asks to see or capture what happened in a Grok realtime voice session, or a voice integration has no debug logging… | cursor/ | 10k | — | ~3.1k | Automated safety check: Pass | No licence | yesterday |
| 26 | Review one or more PRs in Dylan's style: up to 7 copy-pasteable asks and one 🟢/🟡/🔴 call. | cursor/ | 10k | — | ~2k | Automated safety check: Pass | No licence | yesterday |
| 27 | Render a PR diff review as a Cursor Canvas that groups changes by reviewer importance, separates boilerplate from core logic, and highlights tricky or unexpected code. | cursor/ | 10k | — | ~1.2k | Automated safety check: Pass | No licence | yesterday |
| 28 | Dylan's agent style on top of pstack: concise verified delivery, root causes over symptom patches, The Algorithm before design, plain /bro replies, live UI proof, reuse/simplify, and hard merge gates. | cursor/ | 10k | — | ~1.7k | Automated safety check: Pass | No licence | yesterday |
| 29 | Launch both thermo-nuclear review subagents in parallel, then synthesize their findings. | cursor/ | 10k | 1 repo | ~383 | Automated safety check: Pass | No licence | yesterday |
| 30 | Produce a weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new work | cursor/ | 10k | 1 repo | ~226 | Automated safety check: Pass | No licence | yesterday |
| 31 | Create a fresh branch, complete work, and open a pull request | cursor/ | 10k | 1 repo | ~167 | Automated safety check: Pass | No licence | yesterday |