AI & ML

arvo-ai Skill

Sentry error tracking integration for searching issues, fetching stacktraces, listing projects, and running Discover event searches during RCA investigations

arvo-ai Skill

Datadog monitoring integration for querying logs, metrics, monitors, events, traces, hosts, and incidents during RCA investigations

arvo-ai Skill

New Relic observability integration for running NRQL queries, checking alert issues, and searching entities via NerdGraph during RCA investigations

theexperiencecompany Skill

Operate the running GAIA app as an agent — boot the right stack, authenticate with zero login via the dev bypass, drive the REST/SSE API and bots directly, script the LLM deterministically, and verify outcomes in Mongo instead of trusting stdout. The cookbook for end-to-end testing a change against a live stack.

arvo-ai Skill

OpsGenie / JSM Operations integration for querying alerts, incidents, services, on-call schedules, and teams during RCA investigations

arvo-ai Skill

Dynatrace APM integration for querying problems, logs, metrics, and monitored entities during RCA investigations

arvo-ai Skill

Tailscale mesh VPN integration for managing devices, SSH access, auth keys, ACLs, and DNS across your tailnet

arvo-ai Skill

Amazon CloudWatch alarm integration — receives alarm state-change notifications via SNS webhooks and creates incidents automatically

arvo-ai Skill

Confluence integration for searching runbooks, past incidents, postmortems, and operational procedures during RCA

arvo-ai Skill

incident.io integration for listing incidents, investigating details, and reviewing timelines during RCA

arvo-ai Skill

Postmortem generation and management tools for writing, reading, and versioning incident postmortems

arvo-ai Skill

SharePoint integration for searching documents, pages, and publishing incident reports via Microsoft Graph API

arvo-ai Skill

CloudBees Operations Center integration for cross-controller deployment visibility and feature flag correlation during RCA

arvo-ai Skill

ThousandEyes network intelligence integration for monitoring tests, alerts, agents, Internet Insights outages, dashboards, and BGP routes during RCA investigations

vannifr Bundle

Reviews actual translation quality across a multi-language site's locales — not whether every key exists (most i18n setups already automate that) but whether the translation itself is correct, natural, and consistent — literal phrasing, broken placeholders, untranslated leftovers, terminology drift, and length-driven layout risk. Works on any multi-language website, any i18n mechanism (client-side JSON, per-locale pages, CMS). Trigger on "review our translations", "check the French/German/Dutch copy", "is this correct in language X", or after updating locale content. NOT a substitute for a professional translator or native-speaker sign-off on launch-critical copy — flag uncertainty rather than assert fluency the model doesn't have. NOT a key-parity check — confirm the project's own parity check is green first; this assumes every key exists and asks whether the translation is any good.

thunder-id Bundle

ThunderID Documentation Skill

thunder-id Skill

Audit the pnpm overrides a repo already carries, remove the ones upstream has since fixed, and require a justification comment on every one that stays. The counterpart to fix-npm-vulnerability. Use when asked to check, clean up, or prune the overrides, or when an override's tracking issue comes up for review.

thunder-id Skill

Fix a pnpm/npm security advisory in a pnpm monorepo. First attempts to update the head dependency; falls back to a pnpm override with a tracking GitHub issue. Use when pnpm audit or Dependabot surfaces a vulnerability.

eiei114 Bundle

Template skill contributed by extensions/skill-bridge via resources_discover. Use when testing extension-provided Agent Skills or /skill:template-skill-bridge.

karthick-ramachandran Bundle

Review a change for security risks before it is accepted. Use when a change touches a trust boundary — file writes, paths, dependencies, stored secrets, network calls, telemetry, MCP, auth — and needs a decision before merging. Skip for feature planning, test writing, and convention checks.

smixs Skill

Send a rich Telegram post to ANOTHER allowlisted chat; not for the current chat reply or plain reports.

smixs Skill

Shape a reply for Telegram: headings, tables, folds, footnotes, formulas, pictures, slideshows, maps, and buttons (choice, link, copy, mini app) inside the text. Load before a structured answer, a comparison, a report in chat, or whenever you offer the user a choice or a link.

smixs Skill

Браузер для веб-задач: зайти на сайт, форма, клик, скриншот, логин, спарсить JS-страницу.

smixs Skill

Something broke or the user complains: gather evidence and offer to file an issue or ask the support chat

smixs Skill

Restore or merge owner customizations after an Iva update; resolve data/update-conflicts/.

smixs Bundle

Untrusted content, prompt injection, secret leak: emails, pages, forwards, webhooks, group content.

smixs Bundle

Личный Telegram владельца (userbot): читать чаты, искать, писать от его имени; подключение аккаунта.

smixs Bundle

Iva's daily-memory processor. Reads the day's two-sided transcript (daily/YYYY-MM-DD.md), distills noteworthy entities / decisions / ideas into typed autograph cards, links them into the graph, and produces a daily-summary card (topics + MOC) that navigates down to the raw transcript and up to the week. Model-agnostic — runs on any LLM driving the vault (Iva uses DeepSeek). Triggered by the daily rollup (scripts/memory/rollup.ts daily).

jakeselby Bundle

Write or revise a plan file, proposal, design doc or handoff that the user reviews before approving work. Carries the Review Card contract — the one-screen summary, the system diagram, the numbered steps, the decision block — and the addendum rules for everything below it. Use before writing anything into .agent-harness/plans/, and for any markdown deliverable whose job is to get a go/no-go.

jakeselby Bundle

Show progress of background Workflow runs — which agents have returned, which are still working, and how much output has accumulated. Use when the user asks about workflow progress, says "/workflows doesn't work", asks "is the workflow done", "how's the workflow going", "check the workflow", or wants to inspect a multi-agent orchestration run. Reads local Claude workflow journals; Codex background-agent status is not implemented by this reader.

jakeselby Skill

Verify a third-party library, asset, model, font, dataset or copied snippet is safe to ship under the project's licensing stance, and record it correctly. Use before adding or upgrading any dependency, before downloading any asset, and before a release.

jakeselby Skill

Decide where an instruction belongs and write it there. Use when asked to add, change or remove a rule, skill, instruction, hook, setting or CLAUDE.md line, when asked to "remember" something that should persist beyond this session, or when a correction should apply to future sessions. Routes the change into the agent-harness checkout, a personal file, a repo's own instructions, or auto memory, and runs the sync and lint.

jakeselby Skill

Decide whether to spawn a subagent and which model tier and reasoning effort it should run on. Use when planning a fan-out, choosing a subagent model, writing a workflow script's opts.model, authoring an agent definition, setting a repo's cost posture, or when a delegation decision is non-obvious. Carries the evidence, the bands, the safety conditions and the untrusted-content protocol behind the standing rule.

jakeselby Skill

Isolate an agent's work in its own git worktree branched off the default branch, so two agents never land conflicting changes on the shared checkout. Use at the start of any implementation task in a repo where other agents or the user may also be working, and whenever a repo's instructions say "work in a worktree".

cree1116 Bundle

Design, compile, or audit production-grade Crack interactive story chats from story.md and characters.md into platform-limited prompts and keyword books. Use for worldbuilding, psychologically generative characters, player agency, pacing, combat loops, adult boundaries, prompt compression, cinematic openings, and Crack showcase sites, image hosting, banners, and onboarding descriptions.

jeinn-co Bundle

Check AI subscription usage limits across Claude, ChatGPT and Grok in one unified report — percent used, how much is left, when each window resets, the model / effort of each CLI's newest session, and a cost-effectiveness recommendation. Use when the user runs /ai-usage or /uu, or asks 額度, 用量, usage, limit, 還剩多少, 什麼時候 reset, 被限流了嗎, rate limit, quota, "am I out of Claude", "how much ChatGPT left".