Recently added

Aug 28, 2026

1. obsidian-markdown22stars

   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.

   Codex1 skill
2. obsidian-bases22stars

   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.

   Codex1 skill
3. model-routing22stars

   Install and maintain a "model routing" section in a project's CLAUDE.md that teaches Claude Code which model to use for which work, including delegating to GPT models via the Codex CLI. Use when adding model-picking guidance to CLAUDE.md, setting up Codex/GPT as a delegation target or fallback, or routing subagent and workflow tasks across models by cost, intelligence, and taste.

   Codex1 skill
4. mermaid-cli22stars

   Generate, validate, and fix diagrams from Mermaid markup using mmdc. Use when creating flowcharts, sequence diagrams, class diagrams, converting .mmd files to images/SVG/PDF, or validating and fixing Mermaid diagram syntax.

   Codex1 skill
5. long-form-math22stars

   Write mathematics in a long-form, understanding-focused style with detailed proofs and rich exposition. Use when explaining mathematical concepts, writing proofs, tutoring math, creating educational math content, or when the user asks for mathematical explanations. Inspired by Jay Cummings' Real Analysis and Chartrand's Mathematical Proofs.

   Codex1 skill
6. linear22stars

   Managing Linear issues, projects, and teams. Use when working with Linear tasks, creating issues, updating status, querying projects, or managing team workflows.

   Codex1 skill
7. kubernetes22stars

   Author and operate Kubernetes workloads with kubectl and YAML manifests — the kubectl CLI plus core resource authoring (Deployments, StatefulSets, Jobs/CronJobs, Services, Ingress, ConfigMaps/Secrets, PV/PVC, RBAC). Use when writing/debugging manifests, running kubectl (apply/diff/rollout/logs/exec/debug), fixing CrashLoopBackOff/Pending pods, managing contexts, or checking RBAC with auth can-i. Includes `(k8s 1.X+)` annotations. For installing/running a lightweight cluster see the k3s skill.

   Codex1 skill
8. k3s22stars

   The k3s lightweight CNCF-certified Kubernetes distribution as a single binary (bundles containerd, flannel, CoreDNS, Traefik, ServiceLB, local-path-provisioner, metrics-server). Use when installing/running a lightweight cluster, bootstrapping single-node or HA control planes, joining agent nodes, embedded etcd vs external datastore, managing tokens, rotating certs, etcd snapshots, secrets encryption, airgap installs, disabling components, or upgrading k3s. Includes `(k3s vX.Y+)` annotations.

   Codex1 skill
9. jq22stars

   jq — the command-line JSON processor and its filter language for filtering, transforming, and reshaping JSON. Use when extracting fields/nested paths on the CLI, `select`-ing arrays of objects, building new JSON, emitting CSV/TSV with `@csv`/`@tsv`, getting raw strings with `jq -r`, slurping (`-s`) and aggregating (`add`, `group_by`), NDJSON pipelines (`-c`), or injecting shell values with `--arg`/`--argjson`. Includes `(jq 1.X+)` annotations; the jq CLI/filter language, not bindings (jaq/gojq).

   Codex1 skill
10. jj22stars

    Jujutsu (jj) version control system - a Git-compatible VCS with novel features. Use when working with jj repositories, managing stacked commits, needing automatic rebasing with first-class conflict handling, using revsets to select commits, or wanting enhanced Git workflows. Triggers on mentions of 'jj', 'jujutsu', change IDs, or operation log.

    Codex1 skill
11. jj-hunk22stars

    Programmatic hunk selection for the jj (Jujutsu) VCS. Select individual diff hunks with a query language instead of an interactive TUI, then split, commit, squash, diffedit, restore, or absorb them. Use when splitting a jj commit, committing or squashing part of the working copy, undoing single hunks, selecting changes by file/content/function/class, or when `jj split -i` would need an editor an agent cannot drive.

    Codex1 skill
12. hledger22stars

    Plain-text double-entry accounting with hledger. Use when recording transactions, checking balances, generating financial reports, importing CSV bank statements, budgeting, tracking time, managing multiple currencies, or doing year-end closing.

    Codex1 skill
13. handoff22stars

    Compact the current conversation into a handoff document for another agent to pick up. Use when ending a session with unfinished work, transferring context to a fresh agent or a new session, approaching context limits, or when the user says "handoff", "write a handoff doc", or "continue this in another session".

    Codex1 skill
14. gogcli22stars

    Drive Google Workspace from the terminal with the `gog` CLI (gogcli). Use when sending/searching Gmail, managing Calendar events, uploading to Drive, editing Docs/Sheets/Slides, posting to Chat, managing Tasks/Contacts, administering Workspace via DWD, or building agent workflows needing JSON output, OAuth/service-account auth, Pub/Sub watches, and a command sandbox. Covers Gmail, Calendar, Drive, Docs, Slides, Sheets, Chat, Tasks, Contacts, Classroom, Forms, Keep, Admin.

    Codex1 skill
15. git22stars

    Advanced Git CLI mastery, recovery, and troubleshooting (git 2.54+). Use when recovering lost commits/branches/stashes (reflog, fsck), undoing a bad reset/merge/rebase, rewriting history (interactive rebase, filter-repo), resolving conflicts (rerere), worktrees, bisect, cherry-pick, stash, refspecs and --force-with-lease, .gitattributes/hooks, git internals, or confusing git errors. For commit messages use conventional-commits; stacked branches git-chain; auto-fixup git-absorb; Jujutsu jj.

    Codex1 skill
16. git-chain22stars

    Manage and rebase chains of dependent Git branches (stacked branches). Use when working with multiple dependent PRs, feature branches that build on each other, or maintaining clean branch hierarchies. Automates rebasing or merging entire branch chains.

    Codex1 skill
17. git-absorb22stars

    Automatically fold uncommitted changes into appropriate commits. Use for applying review feedback and maintaining atomic commit history.

    Codex1 skill
18. fzf22stars

    Command-line fuzzy finder for interactive filtering. Use when searching files, command history (CTRL-R), creating interactive menus, or integrating with ripgrep, fd, and git. Triggers on fzf, fuzzy finder, ** completion, or CTRL-T/CTRL-R/ALT-C keybindings.

    Codex1 skill
19. fuzzy-search22stars

    MCP server exposing fuzzy content/file/document search tools built on ripgrep + fzf (plus ripgrep-all and PyMuPDF for PDFs). Use when searching code, files, or documents with fuzzy filtering, or extracting/inspecting PDF pages and outlines.

    CodexClaude Code1 MCP server
20. fuzzy-filter22stars

    The non-interactive `rg`/`fd`/`rga` → `fzf --filter` pipeline — scan with a regex tool, then fuzzy-rank the lines without a TUI. Use when fuzzy-matching file paths, code lines, or document/PDF text from a script or one-shot command, reproducing the fuzzy-search MCP on the bare CLI, or piping fuzzy-ranked results into xargs/an editor. The CLI technique; for the INTERACTIVE picker use the fzf skill, for tool-call ergonomics use the fuzzy-search MCP.

    Codex1 skill
21. file-search22stars

    MCP server exposing search_files and filter_files tools for fast file-NAME discovery powered by fd (regex/glob) and fzf (fuzzy matching). Use when locating files by name or partial path — not for searching file contents.

    CodexClaude Code1 MCP server
22. fd22stars

    Fast, user-friendly command-line file/directory search with the `fd` tool (a simpler, faster `find` replacement). Use when searching for files or directories by name or regex/glob pattern, filtering by type/extension/size/modified-time, respecting .gitignore, or running a command per result with -x/-X. Triggers on mentions of fd or fdfind. The fd CLI tool, distinct from the file-search MCP server.

    Codex1 skill
23. duckdb22stars

    DuckDB — in-process columnar OLAP SQL engine in a single binary ("SQLite for analytics"). Use when querying Parquet/CSV/JSON files directly with SQL, using the `duckdb` CLI shell (REPL or `-c`/`-json` one-shots), friendly SQL (FROM-first, `SELECT * EXCLUDE`, `GROUP BY ALL`, `SUMMARIZE`, `PIVOT`), converting CSV↔Parquet↔JSON via `COPY`, reading HTTP/S3 via httpfs, or `ATTACH`-ing Postgres/MySQL/SQLite. Includes `(duckdb vX.Y+)` annotations; the CLI/SQL engine, not client libraries.

    Codex1 skill
24. design-principles22stars

    Guide AI-assisted UI generation toward enterprise-grade design. Use when building UIs, creating dashboards, designing SaaS applications, or generating styled frontend code. Enforces 4px grids, typography hierarchies, and consistent depth strategies.

    Codex1 skill
25. conventional-commits22stars

    Format git commit messages following Conventional Commits 1.0.0 specification. Use when the user asks to commit changes, create a git commit, or mentions committing code. Ensures consistent, semantic commit messages that support automated changelog generation and semantic versioning.

    Codex1 skill
26. comment-slop22stars

    Find and remove redundant comments and docstring content while retaining rationale, contracts, and documentation/tooling functions. Apply a source-based keep/delete/reduce/rewrite review; optionally consult Jev on redundancy and whether a proposed edit loses useful information. Reuses the configurable general Jev helper and skips it without helper or credentials. Use when cleaning up AI-slop comments, auditing a diff, reducing mixed docstrings, or checking a comment rewrite.

    Codex1 skill
27. code-walkthrough22stars

    Create self-contained interactive HTML documents that teach a code change (branch, PR, diff, subsystem) to a reviewer with no prior knowledge — before/after code toggles, mermaid diagrams, step-through code walkers, and playground widgets. Use when the user wants an interactive walkthrough/teaching document of a branch or PR, before/after visuals, or to learn a codebase area from zero.

    Codex1 skill
28. chrome-cdp22stars

    Interact with local Chrome browser session via Chrome DevTools Protocol. Use when asked to inspect, debug, or interact with a page open in Chrome, take screenshots, read accessibility trees, evaluate JavaScript, click elements, or navigate pages.

    Codex1 skill
29. ansible22stars

    ansible-core — the agentless, push-based SSH automation engine that runs idempotent tasks from declarative YAML playbooks. Use when writing/running playbooks, ad-hoc commands, inventory, roles, collections (ansible-galaxy), Ansible Vault, ansible.cfg, or ansible-doc lookups. Covers the ten ansible* CLIs, FQCN, become, variable precedence, and check/diff mode, with `(ansible-core X.Y+)` annotations. This is ansible-core, not the community package's collection modules.

    Codex1 skill
30. anki-flashcards22stars

    Create and manage Anki flashcards via the AnkiConnect API. Use when the user wants to create flashcards, add cards to Anki, manage Anki decks, review Anki statistics, or interact with Anki in any way. Requires Anki desktop app running with AnkiConnect add-on installed.

    Codex1 skill
31. ai-friendly-cli22stars

    Build and refactor CLIs for AI agent compatibility. Use when making CLI tools machine-readable with structured JSON output, input hardening, schema introspection, dry-run safety, and MCP surfaces.

    Codex1 skill
32. agent-skill-init22stars

    Create a repo-local Agent Skill following the open agentskills.io specification. Use when the user wants to create, scaffold, or initialize a new skill in the current repo, mentions a 'repo-local skill' or the agentskills.io spec, or needs a spec-compliant SKILL.md placed under .agents/skills/ (or .claude/skills/). Scaffolds the directory, writes valid name/description frontmatter, and validates with skills-ref.

    Codex1 skill
33. partner-vendor-topic26stars

    Partner plugin skeleton — replace this with your contribution. Examples: partner-commercial_foundry-commercial_pdk, community-class-rfic, vendor-tester-acme.

    Claude Code1 skill
34. vibe-ic26stars

    AI-Native IC Design plugin for Claude Code — one install bundles and auto-registers the MCP-EDA server that wraps the open-source EDA toolchain and lab hardware. Two entry points into one Phase 1: (A) natural-language prompt/dialogue, or (B) existing design docs → layered design JSON (L-docs). Phase 2: RTL → lint → sim → formal → FPGA SOF + on-board test. Phase 3: synth → STA → DFT → PnR → DRC/LVS → GDS → tapeout. Analog A1-A9 (sizing → layout → hardmacro) and Mixed-signal M1-M4 (merge → AMS co-sim → PV) interleaved per phase. Strict canonical-flow compliance gate plus an anti-fabrication doctrine enforced as deterministic gates (provenance audit-chain, chip-AGNOSTIC source guard, real-artifact + SHA256 attestation, gate self-assertion, benchmark-path consistency) — no fabrication, no hallucinated PASS.

    Claude Code50 skills1 MCP server
35. teach1stars

    Turn the current directory into a teaching workspace - a mission, curated sources, short interactive lessons, and a record of what you have actually learned

    Claude Code1 skill
36. dev1stars

    Development workflow for Claude Code - six flat /dev commands, each self-contained, plus a worker and five review agents

    Claude Code6 skills
37. cardinal0stars

    Connect Claude Code to Cardinal: telemetry to the Outcomes Dashboard + unified Cardinal MCP tools, with a per-turn git_state hook that derives initiative name and type from the current branch so the Outcomes Dashboard can map sessions to repos/branches/PRs/initiatives.

    Claude Code7 skills
38. charly-vm0stars

    Schema authoring reference for `kind: vm` + bootc VM catalog — libvirt/QEMU backends, cloud_image vs bootc sources.

    CodexClaude Code7 skills
39. charly-versa0stars

    Self-contained skills + MCP wiring for the versa image — a marimo notebook environment (marimo + Airflow + OSM/GTFS analytics + martin vector tiles + five PMTiles generation pipelines: tippecanoe / gpq-tiles / DuckDB ST_AsMVT / DuckDB → freestiler / Shortbread-via-Tilemaker, plus PMTiles Viewer SPA on port 28001 + VersaTiles Frontend on port 28002 + versatiles serve as second tile server on port 28090). Ships marimo (port 22718) and airflow (port 29999) MCP servers.

    CodexClaude Code16 skills1 MCP server
40. charly-tools0stars

    CLI utilities and the charly binary deploy artifacts — ripgrep, himalaya, whisper, nano-pdf, summarize, ordercli, gogcli, sherpa-onnx, plus the `charly` binary deployment skill.

    CodexClaude Code23 skills
41. charly-selkies0stars

    Self-contained skills + MCP wiring for the selkies-desktop family (Wayland desktop in a container with VNC + Chrome). Ships the chrome-devtools MCP server (port 9224).

    CodexClaude Code43 skills1 MCP server
42. charly-pod0stars

    Schema authoring for `kind: pod` and `kind: deploy` — charly.yml shapes, nested deploys, sidecars.

    CodexClaude Code1 skill
43. charly-openwebui0stars

    Self-contained skills for the openwebui chat-frontend image. Consumes the jupyter MCP server (enable charly-jupyter alongside) for in-chat code execution.

    CodexClaude Code2 skills
44. charly-openclaw0stars

    Self-contained skills for the openclaw image family (CachyOS base): the headless openclaw gateway and the maximal non-browser openclaw-full.

    CodexClaude Code7 skills
45. charly-ollama0stars

    Self-contained skills for running the ollama LLM-server image. Pair with charly-jupyter to expose Ollama models to Jupyter notebooks via the jupyter MCP.

    CodexClaude Code3 skills
46. charly-local0stars

    Schema authoring for `kind: local` — local templates, ssh-host targets, managed ssh-config fragment.

    CodexClaude Code3 skills
47. charly-languages0stars

    Programming language runtimes and package managers — python, python-ml, pixi (others like golang/rust/nodejs live in `charly-coder`).

    CodexClaude Code4 skills
48. charly-kubernetes0stars

    Schema authoring for `kind: kubernetes` — Kustomize manifests, cluster probes via the `kube:` check verb, and the helm words (`helm-release` install step + `helm:` check verb).

    CodexClaude Code4 skills
49. charly-jupyter0stars

    Self-contained skills + MCP wiring for the jupyter image family (jupyter, jupyter-ml, jupyter-ml-notebook, unsloth-studio). Ships the jupyter MCP server (port 8888).

    CodexClaude Code15 skills1 MCP server
50. charly-internals0stars

    Development internals for charly contributors — Go source map, install-plan IR, capabilities/OCI labels, vm-spec, libvirt/cloud-init renderers, cutover-policy, strict-policy, disposable, ovmf, generate-source, skill maintenance, and the agents/workflows/teams guide. Ships five agents (root-cause-analyzer, layer-validator, testing-validator, check-bed-runner, deploy-verifier).

    CodexClaude Code23 skills