Jylhis

@jylhis source repo

71 skills
0 followers
3 hours ago last updated

▌
Taste · jylhis
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

0
installs
▌
Defuddle · jylhis
Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for URLs ending in .md — those are already markdown, use WebFetch directly.

0
installs
▌
Azure AI · jylhis bundle
Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.

0
installs
▌
Azure Cost · jylhis bundle
Unified Azure cost management: query historical costs, forecast future spending, and optimize to reduce waste. WHEN: "Azure costs", "Azure spending", "Azure bill", "cost breakdown", "cost by service", "cost by resource", "how much am I spending", "show my bill", "monthly cost summary", "cost trends", "top cost drivers", "actual cost", "amortized cost", "forecast spending", "projected costs", "estimate bill", "future costs", "budget forecast", "end of month costs", "how much will I spend", "optimize costs", "reduce spending", "find cost savings", "orphaned resources", "rightsize VMs", "cost analysis", "reduce waste", "unused resources", "optimize Redis costs", "cost by tag", "cost by resource group", "AKS cost analysis add-on", "namespace cost", "cost spike", "anomaly", "budget alert", "AKS cost visibility". DO NOT USE FOR: deploying resources, provisioning infrastructure, diagnostics, security audits, or estimating costs for new resources not yet deployed.

0
installs
▌
JSON Canvas · jylhis bundle
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.

0
installs
▌
Obsidian CLI · jylhis
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.

0
installs
▌
Azure Deploy · jylhis bundle
Execute Azure deployments for ALREADY-PREPARED applications that have existing .azure/deployment-plan.md and infrastructure files. DO NOT use this skill when the user asks to CREATE a new application — use azure-prepare instead. This skill runs azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery. Requires .azure/deployment-plan.md from azure-prepare and validated status from azure-validate. WHEN: "run azd up", "run azd deploy", "execute deployment", "push to production", "push to cloud", "go live", "ship it", "bicep deploy", "terraform apply", "publish to Azure", "launch on Azure". DO NOT USE WHEN: "create and deploy", "build and deploy", "create a new app", "set up infrastructure", "create and deploy to Azure using Terraform" — use azure-prepare for these.

0
installs
▌
Azure Storage · jylhis bundle
Azure Storage Services including Blob Storage, File Shares, Queue Storage, Table Storage, and Data Lake. Answers questions about storage access tiers (hot, cool, cold, archive), when to use each tier, and tier comparison. Provides object storage, SMB file shares, async messaging, NoSQL key-value, and big data analytics. Includes lifecycle management. USE FOR: blob storage, file shares, queue storage, table storage, data lake, upload files, download blobs, storage accounts, access tiers, storage tiers, hot cool cold archive, storage tier comparison, when to use storage tiers, lifecycle management, Azure Storage concepts. DO NOT USE FOR: SQL databases, Cosmos DB (use azure-prepare), messaging with Event Hubs or Service Bus (use azure-messaging).

0
installs
▌
Documentation · jylhis
Write and maintain technical documentation. Trigger with "write docs for", "document this", "create a README", "write a runbook", "onboarding guide", or when the user needs help with any form of technical writing — API docs, architecture docs, or operational runbooks.

0
installs
▌
Azure Compliance · jylhis bundle
Run Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks. WHEN: compliance scan, security audit, BEFORE running azqr (compliance cli tool), Azure best practices, Key Vault expiration check, expired certificates, expiring secrets, orphaned resources, compliance assessment.

0
installs
▌
Azure Kubernetes · jylhis bundle
Plan, create, and configure production-ready Azure Kubernetes Service (AKS) clusters. Covers Day-0 checklist, SKU selection (Automatic vs Standard), networking options (private API server, Azure CNI Overlay, egress configuration), security, and operations (autoscaling, upgrade strategy, cost analysis). WHEN: create AKS environment, provision AKS environment, enable AKS observability, design AKS networking, choose AKS SKU, secure AKS, optimize AKS, rightsize AKS pod, AKS spot nodes, AKS cluster-autoscaler.

0
installs
▌
Product Brainstorming · jylhis
Brainstorm product ideas, explore problem spaces, and challenge assumptions as a thinking partner. Use when exploring a new opportunity, generating solutions to a product problem, stress-testing an idea, or when a PM needs to think out loud with a sharp sparring partner before converging on a direction.

0
installs
▌
Grafana Dashboarding · jylhis bundle
Build, modify, and ship Grafana dashboards as JSON via the HTTP API — panel types (timeseries / stat / gauge / table / heatmap / logs / traces / node-graph), `gridPos` 24-column layout, units, thresholds, template + datasource + chained variables, transformations (`organize` / `calculateField` / `filterByValue`), panel + dashboard links with `${__field.labels.x}` / `${__from}`, and Loki/Prometheus annotations. Use when scripting dashboard creation, writing the dashboard JSON for a new service, adding a `$job` dropdown variable, computing an "Error %" column with a transformation, overlaying deploys as annotations, or pushing a dashboard via `POST /api/dashboards/db` — even when the user says "create a dashboard for this metric", "add a service dropdown", "show errors as percentage", "overlay our deploys", or "export the dashboard JSON" without naming the API or schema. After every API push, verify with the returned `version` plus a GET on the dashboard UID.

0
installs
▌
Karpathy Guidelines · jylhis
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

0
installs
▌
Emacs · jylhis bundle
Use for Emacs and Emacs Lisp work — modern Elisp conventions (lexical-binding, use-package, keymap-set, setopt, defvar-keymap, if-let*, tree-sitter ts-mode), authoring major modes (define-derived-mode, font-lock, indent-line-function, syntax tables, treesit-simple-indent-rules), package publishing (MELPA / GNU ELPA / NonGNU ELPA, ;;;###autoload, package-lint, checkdoc), code review (linting, byte-compile, obsolete API detection), ERT testing, debugging (--debug-init, Edebug, profiler, native-comp), gptel + MCP integration, introspection (describe-*, apropos, find-function), and keybinding design (keymap layers, key-valid-p). Read the matching reference before acting.

0
installs
▌
Go · jylhis bundle
Use for modern Go work keyed to the project's Go version — `any` over `interface{}`, errors.Is / errors.Join, slices / maps / cmp packages (Contains, Index, SortFunc, Sorted, Collect, Clone, Copy, Keys, Values), sync.OnceFunc / OnceValue, context.AfterFunc / WithCancelCause, atomic.Bool / Int64 / Pointer[T], `for i := range n` loops, cmp.Or, http.ServeMux method-and-path patterns + r.PathValue, t.Context() in tests, omitzero JSON tags, b.Loop() benchmarks, strings.SplitSeq / FieldsSeq iterators, sync.WaitGroup wg.Go(fn), errors.AsType[T], `new(value)` pointer expressions. Read the matching reference before reviewing Go code for outdated patterns.

0
installs
▌
Jvm · jylhis bundle
Use for JVM build, packaging, testing, and failure triage — Gradle 8.10+ with Kotlin DSL, libs.versions.toml version catalogs, java/kotlin toolchains, convention plugins (buildSrc / build-logic), configuration cache + parallel builds; publishing libraries to Maven Central via maven-publish + nmcp + JReleaser, signing with useInMemoryPgpKeys, JPMS module-info, GitHub Actions release-on-tag; testing with JUnit 5 (Jupiter), AssertJ, kotest (Kotlin), mockk / mockito, Testcontainers, JaCoCo, awaitility; diagnosing Kotlin/Spring failures from stack traces and logs (root cause vs wrapper exceptions, startup failures, noisy nested traces). Read the matching reference before acting.

0
installs
▌
Nix · jylhis bundle
Use for Nix, Nixpkgs, and NixOS work — language fundamentals (lambdas, attrsets, derivations, lib functions), flakes (inputs/outputs, devShells, flake-parts), Nixpkgs packaging (mkDerivation, callPackage, overlays, builders), NixOS modules (mkOption, services, systemd, secrets), nix-darwin macOS config, home-manager dotfiles, devenv developer shells, container builds (dockerTools), nixosTests VMs, debugging (infinite recursion, IFD, hash mismatch), linting (statix/deadnix/nixfmt), performance (closure size, IFD avoidance), Emacs packaging in Nix, and hybrid non-flake + flake repos. Read the matching reference before acting.

0
installs
▌
Systemd · jylhis bundle
Use for systemd, the Linux init system and service manager (PID 1) and its tooling. Covers writing and debugging unit files (.service, .socket, .timer, .target, .mount, .path, .slice, .scope), systemctl / journalctl / systemd-analyze, drop-in overrides and precedence, service dependencies and ordering, socket activation, timers as a cron replacement, security sandboxing (Protect*/Private*/Restrict*, DynamicUser, SystemCallFilter), cgroup v2 resource control (MemoryMax, CPUQuota, slices), user services, journald/logind/networkd/resolved, credentials, and boot performance. Trigger on "systemd", "systemctl", "journalctl", "unit file", "daemon won't start", "enable a service", "systemd timer", "harden a service", "limit CPU/memory of a process", "socket activation", or debugging a failed/looping Linux service. Read the matching reference before editing units or advising changes.

0
installs
▌
Bash · jylhis
Bash and shell-scripting guidance: choose the right script form, keep error handling explicit, prefer exact probes, and keep shell lint suppressions narrow.

0
installs
▌
Rust · jylhis
Rust implementation contract: typed boundaries and newtypes, exhaustive enums as single source of truth, error discipline (typed public APIs, n0-error), deterministic testing via injected host context, and channel-first concurrency. Use when writing or reviewing Rust (bins, libs, build scripts).

0
installs
▌
Azure · jylhis
Azure cloud umbrella — routes to the right Azure sub-skill for the task. Use when the user mentions Azure generally or asks for help with Azure without naming a specific service, or when you need to figure out which Azure skill applies. Covers: AI services (Search, Speech, OpenAI, Document Intelligence), cost management (historical costs, forecasting, optimization), compliance and security audits (azqr, Key Vault expiration), deployment (azd up, bicep, terraform apply for already-prepared apps), AKS (cluster creation, Automatic readiness), and Storage (blob, files, queues, tables, Data Lake). Read the routing table below, then load the specific sub-skill.

0
installs
▌
Query · jylhis
Run SQL queries against the attached DuckDB database or ad-hoc against files. Accepts raw SQL or natural language questions. Uses DuckDB Friendly SQL idioms.

0
installs
▌
Tdd · jylhis bundle
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

0
installs
▌
Gitlab · jylhis bundle
Use for GitLab work focused on push + merge-request creation — authoring `.gitlab-ci.yml` pipelines (templates, downstream pipelines, Docker builds, caching, runner config, artifacts vs cache, pipeline inputs, duplicate pipeline traps) and the `glab` CLI for creating MRs, syncing forks, and debugging your own CI failures. Read the matching reference before editing pipelines or running glab.

0
installs
▌
Security · jylhis bundle
Use for code security review and safe alternatives across language ecosystems — Python (subprocess command injection, pickle / yaml.load deserialization, SSRF, SQL injection, path traversal, secrets, bcrypt/argon2, cryptography, TLS verify); TypeScript / Node (child_process exec/shell, prototype pollution, XSS via DOMPurify, SSRF, secrets handling, Zod validation, npm audit, Helmet, CSP); JVM (JNDI / Log4Shell, Java serialization, XXE, SSRF, SQL injection, secrets, crypto APIs). Also covers framework-specific secure-by-default guidance (Django, FastAPI, Flask, Express, React, Next.js, Vue, Go), repository threat modeling, security ownership mapping, and CodeQL static analysis. Read the matching reference before reviewing untrusted-input handlers.

0
installs
▌
Python · jylhis bundle
Use for Python 3.12+ work — modern code style (PEP 8, match, pathlib, f-strings), asyncio (TaskGroup, gather, cancellation), error handling (Exception design, ExceptionGroup), type hints (PEP 695 generics, TypedDict, Protocol, pyright), dataclasses vs Pydantic, Ruff (format & lint), packaging with uv, and pytest testing (fixtures, parametrize, asyncio, mocking, coverage). Read the matching reference before acting.

0
installs
▌
Grafana · jylhis
Grafana observability umbrella — routes to the right Grafana sub-skill for the task. Use when the user mentions Grafana generally or asks about observability, dashboards, alerting, or monitoring without naming a specific sub-area, or when you need to figure out which Grafana skill applies. Covers: alerting and IRM (alert rules, contact points, notification policies, on-call, SLOs), dashboard authoring (panel types, JSON, variables, transformations, API push), OpenTelemetry instrumentation (SDK, OTLP, Alloy, sampling), Grafana OSS (provisioning, data sources, grafana.ini, roles), and PromQL (rate, aggregation, histogram_quantile, recording rules, cardinality). Read the routing table below, then load the specific sub-skill.

0
installs
▌
Spatial · jylhis bundle
Answer questions about spatial data using DuckDB. Use when the user mentions locations, coordinates, lat/lng, distances, maps, addresses, "near", "within", "closest", geographic names, or spatial file formats (GeoJSON, Shapefile, GeoPackage, GPX, GeoParquet). Also triggers when the user wants to find places, buildings, or roads — Overture Maps provides free global data on S3 with zero API keys. Handles spatial joins, distance calculations, containment checks, density analysis, and format conversions for geographic data.

0
installs
▌
Graphify · jylhis
Build and query a knowledge graph over a repo, docs folder, papers, or notes corpus using the graphify CLI. Use when the user asks to graphify a directory, map a codebase or research corpus into a knowledge graph, find connections between concepts or files, explain how entities relate, or export a graph as an Obsidian vault, HTML visualization, GraphML, or Neo4j.

0
installs
▌
LLM Wiki · jylhis bundle
Maintain a persistent, LLM-curated markdown wiki over a collection of raw sources. Use when the user wants to build or maintain a personal knowledge base, second brain, or research wiki; ingest an article, paper, or note into a wiki; query an existing wiki for synthesized answers; or lint a wiki for contradictions, stale claims, and orphan pages.

0
installs
▌
Filesystems · jylhis bundle
Use for low-level filesystem topics on macOS, Linux, and NixOS — APFS (clonefile, copy-on-write, Spotlight exclusion, Time Machine snapshots, /nix synthetic mounts, dedicated APFS volumes), Btrfs (flat subvolume layout, impermanence + erase-your-darlings root rollback, compress=zstd, NOCOW vs SQLite WAL, bees deduplication, cross-subvolume reflinks), and ZFS / OpenZFS (pool / dataset layout, recordsize, ashift, compression, ARC sizing, block cloning, mirrors vs RAIDZ, sanoid / syncoid replication, NixOS generations + ZFS snapshots). Read the matching reference before recommending filesystem changes.

0
installs
▌
To Prd · jylhis
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

0
installs
▌
Read File · jylhis
Read any data file (CSV, JSON, Parquet, Avro, Excel, spatial, SQLite) or remote URL (S3, HTTPS). Use when user references a data file, asks "what's in this file", or wants to preview/profile a dataset. Not for source code.

0
installs
▌
Terraform · jylhis bundle
Use for Terraform and HCL infrastructure-as-code work. Covers writing and reviewing HCL to HashiCorp's style guide (file layout, naming, variables and outputs, for_each vs count, version pinning), writing and running tests with .tftest.hcl (run and assert blocks, mock providers, CI wiring), refactoring monolithic configs into reusable modules (interface design, moved-block state migration), and authoring Terraform Stacks (.tfcomponent.hcl and .tfdeploy.hcl components, deployments, linked Stacks). Read the matching reference before writing or reviewing Terraform.

0
installs
▌
S3 Explore · jylhis
Explore and query data on S3, Cloudflare R2, GCS, MinIO, or any S3-compatible storage. Use when the user mentions an s3://, r2://, gs://, or gcs:// URL, asks "what's in this bucket", wants to list remote files, preview remote Parquet/CSV/JSON, or query data on object storage without downloading it. Also triggers when the user wants to know the size, schema, or row count of remote datasets.

0
installs
▌
Using Skills · jylhis
Meta-skill that explains how the jylhis-skills catalogue is organized and how to route a task to the right skill. Use at session start, when the user says "which skill should I use for X", "what skills do I have", "list skills", "is there a skill for Y", or when you're about to tackle a task and want to check whether a purpose-built skill already exists.

0
installs
▌
Diagnose · jylhis bundle
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

0
installs
▌
Ponytail · jylhis bundle
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Also covers over-engineering-only code review, whole-repo bloat audits, and the ponytail-comment debt ledger (see references/). Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).

0
installs
▌
Typescript · jylhis bundle
Use for TypeScript 5.9+ on Node 22 LTS — code style (naming, ESM-first, import order, readonly), type system depth (generics, conditional types, infer, narrowing, satisfies, branded types), async (Promise, AbortController, async iterators, structured concurrency), error handling (Error subclassing, Result types, AggregateError), Node patterns (fs/promises, child_process, streams, workers, pino, graceful shutdown), Zod runtime validation at trust boundaries (safeParse, z.infer, refinements, discriminated unions), Prettier formatting, ESLint 9 flat config, packaging (pnpm workspaces, exports), and Vitest testing. Read the matching reference before acting.

0
installs
▌
Para Method · jylhis
Organize notes, files, or an Obsidian vault with the PARA method (Projects, Areas, Resources, Archives). Use when the user asks to structure or restructure a knowledge base, vault, folder tree, or cloud drive; decide where a note or document belongs; separate active work from reference material; or clean up an overgrown collection by actionability.

0
installs
▌
Handoff · jylhis
Compact the current conversation into a handoff document for another agent to pick up.

0
installs
▌
Duckdb Docs · jylhis
Search DuckDB and DuckLake documentation and blog posts. Returns relevant doc chunks for a question or keyword using full-text search against a locally cached index.

0
installs
▌
Grafana Oss · jylhis bundle
Configure Grafana OSS — provisions dashboards from YAML, sets up data sources (Prometheus / Loki / Tempo / Pyroscope), writes dashboard JSON with template variables, builds panel queries, assigns built-in roles (Viewer / Editor / Admin / GrafanaAdmin), mints service-account tokens, edits grafana.ini server config, creates annotations, installs plugins via provisioning, and validates each step with a health-check curl. Use when building dashboards, configuring data sources, setting up provisioning YAML, picking a panel type, writing template variables, managing users and roles, configuring SMTP/OAuth in grafana.ini, creating annotations via API, troubleshooting why a provisioned dashboard isn't showing up, or running Grafana OSS locally — even when the user says "set up a Prometheus data source", "provision dashboards from git", "make a service account", or "configure SSO in OSS" without saying "Grafana OSS".

0
installs
▌
Convert File · jylhis
Convert any data file to another format: CSV, Parquet, JSON, Excel, GeoJSON, and more. Use when the user says "convert to parquet", "save as xlsx", "export as JSON", "make this a CSV", "turn into parquet", or any variation of format-to-format conversion for data files. Also triggers when the user wants to write Parquet, Excel, or other binary formats that Claude cannot produce natively.

0
installs
▌
Skill Improver · jylhis bundle
Use this skill when the user asks to improve, iterate on, audit, or refine a specific skill in this repo. Reads filtered entries from the improvement-memory JSONL, buckets them by category, and proposes concrete SKILL.md edits. Triggers on phrases like "improve <skill>", "iterate on <skill>", "what did I correct about <skill>", "tune the <skill> skill", or any direct ask about reviewing past corrections.

0
installs
▌
Roadmap Update · jylhis
Update, create, or reprioritize your product roadmap. Use when adding a new initiative and deciding what moves to make room, shifting priorities after new information comes in, moving timelines due to a dependency slip, or building a Now/Next/Later view from scratch.

0
installs
▌
Humanizer · jylhis bundle
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

0
installs
▌
Read Memories · jylhis
Search past Claude Code session logs to recall prior decisions, patterns, or unresolved work. Use when user says "do you remember", "what did we do", references past conversations, or you need context from prior sessions.

0
installs
▌
Skill Extractor · jylhis bundle
Extracts reusable skills from work sessions. Use when (1) a non-obvious problem was solved worth preserving, (2) a pattern was discovered that would help future sessions, or (3) a workaround or debugging technique needs documentation. Manual invocation only via /skill-extractor command — no automatic triggers or hooks.

0
installs
▌
Code Review · jylhis
Review code changes for security, performance, and correctness. Trigger with a PR URL or diff, 'review this before I merge', 'is this code safe?', or when checking a change for N+1 queries, injection risks, missing edge cases, or error handling gaps.

0
installs
▌
Obsidian Bases · jylhis bundle
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.

0
installs
▌
Sprint Planning · jylhis
Plan a sprint — scope work, estimate capacity, set goals, and draft a sprint plan. Use when kicking off a new sprint, sizing a backlog against team availability (accounting for PTO and meetings), deciding what's P0 vs. stretch, or handling carryover from the last sprint.

0
installs
▌
Job Search · jylhis bundle
Candidate-side job-search umbrella: tailor a resume/CV and cover letter to a specific posting, and track applications. Triggers on: 'help me apply', 'tailor my resume', 'tailor my CV', 'write a cover letter', 'apply for this role', 'match my resume to this job', 'application tracker', 'I am job hunting', 'job search', or any request to prepare or track a job application as a candidate. Produces documents only; never submits an application or sends email without explicit confirmation. Does NOT write job posts or screen applicants (that is the employer-side job-post-builder).

0
installs
▌
Grafana Promql · jylhis bundle
Write, validate, and optimize PromQL for Prometheus / Grafana Mimir / Grafana Cloud Metrics. Covers `rate` vs `irate` vs `increase`, label matchers and regex, `sum / avg / topk / by / without` aggregation, classic + native `histogram_quantile`, ratios with divide-by-zero guards, `absent` / `changes` for staleness, time offsets and `predict_linear`, recording-rule naming, SLO + burn-rate math, and a cardinality-hunting playbook. Use when writing a metric query, fixing wrong p95s, building an error-budget alert, debugging "query is slow", finding the noisy label that blew up cardinality, or migrating a dashboard query to a recording rule — even when the user says "calculate the error rate", "p99 latency", "sum by service", "why is this query slow", or "what's filling Mimir" without naming PromQL.

0
installs
▌
Install Duckdb · jylhis bundle
Install or update DuckDB extensions. Each argument is either a plain extension name (installs from core) or name@repo (e.g. magic@community). Pass --update to update extensions instead of installing.

0
installs
▌
Upstream Tracker · jylhis bundle
Track external upstream skill repositories: import a skill from upstream into this catalogue, modify it locally without losing the baseline, monitor the upstream for new commits since the last review, and review each upstream commit one-by-one to accept, skip, defer, or cherry-pick it into the local copy. Use when the user says "import skill from <repo>", "vendor <repo>", "monitor upstream for new commits", "what's changed upstream", "check upstream for updates", "review upstream commit", "backport <sha>", or "follow <repo> for new skills". Operates on `upstream/sources.yaml` (manifest), `upstream/decisions/<id>.log` (per-source review cursor), and `.cache/upstream/<id>.git` (local bare partial clone). Helper scripts under this skill's `scripts/` do the deterministic git work; the agent following this SKILL.md drives the decisions.

0
installs
▌
Offline Docs · jylhis bundle
Discover and use offline documentation on Unix systems (Linux, macOS, FreeBSD). Use when the user asks about CLI tool usage, flags, options, or behavior; needs to look up a man page or info page; wants to find configuration references; asks 'how do I use <tool>'; needs help finding documentation for an unfamiliar command; asks what a flag does; or wants to explore available system documentation. Prefer local docs over web search -- they are authoritative and version-matched to installed software.

0
installs
▌
Job Post Builder · jylhis bundle
Builds end-to-end hiring packets — job post, structured interview guide with scoring rubric, and offer letter template — from a hiring brief. Triggers on: 'help me hire', 'we're hiring for', 'write a job post', 'job description', 'JD', 'open role', 'create a job ad', 'interview questions', 'scoring rubric', 'draft an offer letter', 'send an offer', 'make a hiring packet', or any request to recruit for a position. When in doubt, trigger — covers the full hiring workflow from job post through DocuSign envelope creation via browser. Does NOT screen or rank applicants.

0
installs
▌
Code Comments · jylhis bundle
Write and review code comments: when a comment earns its place versus self-documenting code, explaining why and intent rather than restating what, doc comments (docstrings, JSDoc/TSDoc, godoc, rustdoc, Javadoc) versus inline notes, TODO and FIXME conventions, avoiding comment rot and commented-out code, and the AI tendency to over-comment. Use when writing or reviewing comments, documenting an API, or cleaning up noisy or redundant comments.

0
installs
▌
Competitive Brief · jylhis
Create a competitive analysis brief for one or more competitors or a feature area. Use when informing product strategy or feature prioritization, building sales battle cards, prepping board or investor materials, or deciding where to differentiate vs. achieve parity.

0
installs
▌
Grafana Alerting · jylhis bundle
Configure Grafana Alerting, Incident Response Management (IRM), and SLOs end-to-end — provisions Grafana-managed and data-source-managed alert rules, contact points (Slack/PagerDuty/email/webhook), notification policies with hierarchical matchers, silences, mute timings, on-call schedules and escalation chains, incident-management integrations, and SLOs with multi-window burn-rate alerts. Use when configuring alerts, debugging notification routing, setting up on-call rotations, declaring or managing incidents, defining SLOs, provisioning alerting via YAML or API, picking matchers for a notification policy, building a PagerDuty/Slack webhook receiver, or troubleshooting why an alert isn't firing — even when the user says "page me on errors", "alert me when X happens", "route this to the platform team", or "set up an SLO" without naming Alerting or IRM.

0
installs
▌
Skill Creator Lang · jylhis bundle
Scaffold a new opinionated specialist skill for a programming language or stack (one SKILL.md plus references/ tree). Use when the user says "create a skill for X", "add a python skill", "scaffold a new language plugin", "write a skill that captures expert knowledge for Y", or otherwise asks to author a new entry under skills/<category>/<name>/. Meta skill that produces other skills.

0
installs
▌
Microsoft Docs · jylhis
Understand Microsoft technologies by querying official documentation. Use whenever the user asks how something works, wants tutorials, needs configuration options, limits, quotas, or best practices for any Microsoft technology (Azure, .NET, M365, Windows, Power Platform, etc.)—even if they don't mention "docs." If the question is about understanding a concept rather than writing code, this is the right skill.

0
installs
▌
Obsidian Markdown · jylhis bundle
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.

0
installs
▌
Commit Messages · jylhis bundle
Write clear, atomic git commit messages: an imperative subject line, a body that explains why over what (most-important-first), Conventional Commits or freeform matched to the repo, issue and PR linking, and splitting work into one-decision commits. Use when preparing a commit, writing or rewording a commit message, auditing a branch log before opening or merging a PR, or generating a changelog.

0
installs
▌
Task Management · jylhis
Simple task management using a shared TASKS.md file. Reference this when the user asks about their tasks, wants to add/complete tasks, or needs help tracking commitments.

0
installs
▌
Tax Season Organizer · jylhis bundle
Prepares tax-season materials for small business owners — framed as deliverables for their accountant, not tax advice. Two modes: (1) quarterly estimated tax calculation — pulls YTD net income from QuickBooks and calculates the federal income tax + self-employment tax liability and quarterly payment due; (2) year-end 1099 prep — scans QuickBooks, PayPal, and Stripe for contractors paid over $600, builds a 1099-NEC candidate list with missing W-9 flags, and produces a plain-English summary a CPA can work from directly. Trigger this skill whenever the user mentions: quarterly taxes, estimated tax payment, how much to set aside for taxes, 1099s, 1099-NEC, year-end tax prep, contractor payments, W-9s, or any phrase suggesting they are preparing for a tax deadline or handing materials to an accountant. Also trigger proactively when a user asks about net profit or YTD income in a context that suggests they are worried about their tax bill.

0
installs
▌
Memory Management · jylhis
Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.

0
installs
▌
Grafana Opentelemetry · jylhis bundle
Instrument any app with OpenTelemetry and ship metrics / logs / traces to Grafana Cloud or self-hosted Mimir / Loki / Tempo / Pyroscope. Covers SDK auto-instrumentation for Go, Java (Grafana JVM agent), Python (`opentelemetry-instrument`), Node.js, .NET (`Grafana.OpenTelemetry`), Beyla eBPF for zero-code; Grafana Cloud OTLP gateway + Basic-auth (instanceID + API key, base64); env-var config (`OTEL_EXPORTER_OTLP_*`, `OTEL_RESOURCE_ATTRIBUTES`); Alloy / OTel-Collector pipelines; Kubernetes Operator inject-annotations; and head + tail sampling. Use when instrumenting a service, pointing OTLP at Grafana Cloud, switching from Jaeger / Datadog / New Relic, choosing head- vs tail-sampling, or debugging "spans aren't showing in Explore" — even when the user says "auto-instrument my Java app", "send traces to Grafana", "what env vars do I set", "OTLP endpoint", or "Operator inject" without naming OpenTelemetry.

0
installs
▌
Trunk Based Development · jylhis bundle
Trunk-based development with short-lived branches, daily integration, and never-break-main. Use when branching, planning commit cadence, handling work that spans more than a day, or deciding whether to fix-forward or revert.

0
installs

71 published skills