All Agent Skills
41,263 results
- Realitygate ReviewusmanmaniiPrepare an independent cross-model code review and check the Proof Ledger — bundles a task spec plus its diff into a review pack for a reviewer from a different model family, and reports which completed tasks carry real evidence (failing tests first, green gate, approved review, real execution, existing commit).
- Realitygate ScanusmanmaniiCheck whether an agent skill, Claude Code plugin, MCP config or AI coding extension is safe before installing it — scans for remote code execution, obfuscated payloads, hidden Unicode instructions, credential or .env access, data-leak endpoints, prompt injection, permission bypass, hooks, MCP servers and install scripts.
- Reconcileeggs-gdReconcile tracked vacancy statuses against real recruiter correspondence — "applied → interview" on an interview email plus a calendar slot, "applied → rejected" on a rejection, capturing the why on the status_history entry.
- ReflectiondavidkissMUST use this skill when user provides feedback / ask to do things in certain way, or when a tool call fails - for self-improvement - to learn user preferences and store them in AGENT.md / CLAUDE.md, and to propose improvements to skills.
- Registryframes-engineeringPay-per-call API gateway for AI agents. 10 services available via x402 — no API keys, no subscriptions.
- Renewal RadarHubSpotRead-only renewal reporting for a HubSpot Solutions Partner: surface which of the partner's clients have HubSpot subscription renewals coming up, ranked by urgency, with per-Hub renewal dates and the Contract Manager to coordinate with. Also flags renewal dates in the past that need verifying. Use for viewing, prioritizing, or drilling into upcoming or per-Hub client renewals — e.g.
- Reporting AnalystActiveCampaignAnalyze campaign performance, automation results, email metrics, and engagement trends. Use when the user asks about how campaigns performed, wants reports, or asks about marketing analytics.
- Researcheroneafrikan<!-- SKILL.md — Researcher operating manual. Runtime: Claude Code + ACP (swappable coding CLI). Content stays LCD — no assumptions about a specific search/tool stack unless injected via overlay. Tool-specific commands are NOT here — mark injection points: `STACK: ...` -->
- Researching Web SourcessamjhechtStrategic web research using WebSearch and WebFetch - finds accurate, relevant information with multiple search angles, prioritizes authoritative sources, synthesizes findings with proper attribution.
- Restructured TextLiam-DeaconGuidelines for writing valid reStructuredText (.rst) in this repo (Sphinx).
- ReviewAltimateAIReview dbt project changes — dbt models (models/**/*.sql), schema.yml, dbt_project.yml, sources.yml, macros, snapshots, seeds. Use whenever the user asks to "review my dbt changes", "audit my dbt models", "check my mart / staging / marts before shipping", requests a second opinion on incremental / SCD2 / semantic-layer / cross-model semantic changes, or asks to "review this PR" AND the PR's diff…
- ReviewusmanmaniiPrepare an independent cross-model code review and check the Proof Ledger — bundles a task spec plus its diff into a review pack for a reviewer from a different model family, and reports which completed tasks carry real evidence (failing tests first, green gate, approved review, real execution, existing commit).
- Reviewing Cluster HealthCockroachDBPerforms a comprehensive health check of a CockroachDB cluster. Gathers deployment context first, then provides tier-appropriate diagnostics. Self-Hosted uses SQL against node-level system tables and CLI. Advanced/BYOC use Cloud Console and SQL with node visibility. Standard monitors provisioned compute and workload via Cloud Console. Basic monitors Request Unit consumption and connectivity.
- Rook Code ReviewjhoblittUse when reviewing, auditing, or sanity-checking rook (github.com/rook/*) code, tests, docs, or workflows — a working tree, branch, commit range, or PR; when checking a branch before opening a PR; when reviewing, critiquing, or stress-testing a rook design proposal, design doc, enhancement doc, or design/** change before it becomes code; when bulk-reviewing open rook PRs or evaluating a…
- Rook ConventionsjhoblittUse when authoring or shepherding changes to rook (github.com/rook/*) repos — committing, pushing branches, opening or updating PRs, weighing review feedback, backporting, regenerating CRDs or generated code, writing tests or GitHub Actions workflows, watching or retrying CI, or before ANY gh write (comment, label, close, edit) to a rook issue or PR.
- Rook Pr TakeoverjhoblittUse when taking over, adopting, or superseding a rook (github.com/rook/*) pull request — an author who abandoned it, stopped responding to change requests, or produced an AI-burst PR whose substance is still worth landing.
- Rook Systemic PrsjhoblittUse when applying one systemic change across a rook (github.com/rook/*) repo as a series of small, well-contained, independently reviewable PRs — dead-code elimination, lint/staticcheck cleanups, API migrations, renames, import or dependency hygiene.
- Rook TriagejhoblittUse when triaging rook (github.com/rook/*) issues or PRs — grooming or clearing the backlog, labeling or categorizing issues, finding duplicate issues, cross-linking an issue to a PR (or a PR to the issue it fixes), checking what info a bug report is missing, deciding who should review a PR or requesting reviewers, or refreshing the routing knowledge base ("kb refresh").
- Rubber DuckoneafrikanStructured rubber duck debugging that guides the user to explain their problem until the solution is obvious. Use when the user says "rubber duck", "talk me through this" or "I'm stuck".
- ruslanlap/cavemenkoruslanlapCollection🦴 Ukrainian caveman mode for Claude Code — native Ukrainian pro-drop, real measured token stats, no invented numbers. Measured savings published.
- Rustfandhe-aiRust 言語リファレンス。 別名: rustlang, rs (拡張子)、Rust-lang。 TRPL (The Rust Programming Language)、Rust by Example、Reference、 Cargo Book、rustc Book、rustdoc Book、Rustonomicon (Unsafe Rust)、 Edition Guide、Standard Library、Error Index。 所有権、ライフタイム、トレイト、async / await、エラーハンドリング、マクロ。
- ScanusmanmaniiCheck whether an agent skill, Claude Code plugin, MCP config or AI coding extension is safe before installing it — scans for remote code execution, obfuscated payloads, hidden Unicode instructions, credential or .env access, data-leak endpoints, prompt injection, permission bypass, hooks, MCP servers and install scripts.
- Scientific WritingxiechyWrite scientific manuscripts. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), abstracts, for research papers and journal submissions.
- Scouteggs-gdFetch public job-board/ATS postings, filter and dedup them deterministically, then judge each survivor the same honest way as a pasted posting — creating a vacancy record for what clears the bar, logging the rest. Use when the candidate wants job boards checked automatically instead of pasting one posting at a time ("пошукай вакансії", "run the scout", "find me matches").