cursor · Agent Skills
93 Skills avec une documentation substantielle et des sources vérifiées. Ouvrez une fiche pour lire les instructions originales et vérifier le paquet et son installation.
origin-api
- Routes questions about the Cursor Origin API to the right section of the Origin docs and names the few rules to check first. Use when a task mentions Origin, the Origin API, Origin Apps, or Origin webhooks, including creating an Origin App, authenticating as one, calling Origin endpoints, or handling Origin webhook deliveries.
- Installations / 1h
- 2
- GitHub Stars
- 10,6 k
- Mis à jour
- 10 oct.
port-github-app-to-origin
- Plans the port of an existing GitHub App to a Cursor Origin App. Use when the task is to bring a GitHub App to Origin or compare what it uses against the Origin API. Reads the app's needs out of its code, maps them onto the live Origin spec, and writes a porting brief with feedback for Cursor. Planning only.
- Installations / 1h
- 2
- GitHub Stars
- 10,6 k
- Mis à jour
- 10 oct.
principle-the-algorithm
Apply to any non-trivial change before designing it. Make the requirement less dumb, delete, optimize, accelerate, automate, in that order, then run it again on the result. The reply names the requirement you questioned and what you deleted.
- Installations / 1h
- 2
- GitHub Stars
- 14,2 k
- Mis à jour
- 27 oct.
ralph-loop
Start a Ralph Loop for iterative self-referential development. Use when the user asks to run a ralph loop, start an iterative loop, or wants repeated autonomous iteration on a task until completion.
- Installations / 1h
- 2
- GitHub Stars
- 14,2 k
- Mis à jour
- 27 oct.
ralph-loop-help
Explain the Ralph Loop plugin, how it works, and available skills. Use when the user asks for help with ralph loop, wants to understand the technique, or needs usage examples.
- Installations / 1h
- 2
- GitHub Stars
- 14,2 k
- Mis à jour
- 27 oct.
reproduce-and-fix-issues
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. Use only from the configured Benny repro automation.
- Installations / 1h
- 2
- GitHub Stars
- 13,2 k
- Mis à jour
- 20 oct.
review-and-ship
Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.
- Installations / 1h
- 2
- GitHub Stars
- 14,2 k
- Mis à jour
- 27 oct.
review-plugin-submission
Audit a Cursor plugin for marketplace readiness. Use when validating manifests, component metadata, discovery paths, and submission quality before publishing.
- Installations / 1h
- 2
- GitHub Stars
- 14,2 k
- Mis à jour
- 27 oct.
run-learning-retrospective
Evaluate learning progress, identify blockers, and adjust the learning plan
- Installations / 1h
- 2
- GitHub Stars
- 14,2 k
- Mis à jour
- 27 oct.
run-smoke-tests
Run Playwright smoke tests, debug failures, and verify fixes
- Installations / 1h
- 2
- GitHub Stars
- 14,2 k
- Mis à jour
- 27 oct.
setup-benny
Configure Benny and prepare its triage and repro automations. Use when installing Benny or changing its Slack, tracker, repository, routing, control, model, or budget settings.
- Installations / 1h
- 2
- GitHub Stars
- 13,2 k
- Mis à jour
- 20 oct.
tailscale-setup
Connect Grok Bot to Tailscale on a company tailnet (a team admin enables it at cursor.com; each member authenticates their own device and an admin limits it with custom:grokbot postures) or a personal tailnet (one-click Connect when the member owns or administers the tailnet, otherwise a tag:grokbot device). Several tailnets can be connected at once. Use when the user asks to set up, troubleshoot, change the default tailnet, or disconnect Grok Bot's Tailscale connection.
- Installations / 1h
- 2
- GitHub Stars
- 14,2 k
- Mis à jour
- 27 oct.
thermo-nuclear-review
Comprehensive security and correctness audit of a branch's changes. Use for thermo nuclear, thermonuclear, or deep review requests, or branch/PR diff audits focused on bugs, breaking changes, security issues, devex regressions, and feature-gate leaks.
- Installations / 1h
- 2
- GitHub Stars
- 9,7 k
- Mis à jour
- 4 oct.
triage-issue-reports
Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation. Use only from the configured Benny triage automation.
- Installations / 1h
- 2
- GitHub Stars
- 13,2 k
- Mis à jour
- 20 oct.
verify-this
Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE.
- Installations / 1h
- 2
- GitHub Stars
- 14,2 k
- Mis à jour
- 27 oct.
weekly-review
Produce a weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new work
- Installations / 1h
- 2
- GitHub Stars
- 14,2 k
- Mis à jour
- 27 oct.
what-did-i-get-done
Summarize authored commits over a user-specified time period into a concise update
- Installations / 1h
- 2
- GitHub Stars
- 14,2 k
- Mis à jour
- 27 oct.
workflow-from-chats
Extract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine feedback, personalize workflows, or generate team/person-specific agent guidance.
- Installations / 1h
- 2
- GitHub Stars
- 14,2 k
- Mis à jour
- 27 oct.
principle-redesign-from-first-principles
Apply when integrating a new requirement into an existing design.
- Installations / 1h
- 1
- GitHub Stars
- 15,4 k
- Mis à jour
- 4 nov.
thermos
Launch both thermo-nuclear review subagents in parallel, then synthesize their findings. Use for thermos, double thermo review, or combined bug/security and code-quality branch audits.
- Installations / 1h
- 1
- GitHub Stars
- 15,4 k
- Mis à jour
- 4 nov.
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
- Installations / 1h
- 1
- GitHub Stars
- 15,6 k
- Mis à jour
- 6 nov.
