Coding & Dev Tools
Coding agent skills teach AI agents repeatable engineering workflows: reviewing pull requests, writing tests, refactoring safely, and enforcing house style. Install one SKILL.md and your agent applies the same checklist every time, whether you use Claude Code, Cursor, Codex, or another agent.
-
tonydzi Skill NotebooklmDrive NotebookLM over a programmatic CLI with no browser: turn a vault slice into an audio overview, study guide or mind map, and fold the artifacts back into the vault. Browser automation is the fallback if CLI auth breaks. Triggers: "/notebooklm", "make an audio digest of <topic>", "podcast from the vault".
Audited -
tonydzi Skill Health SyncPull fresh messages from a set of health-related Telegram chats (medicine, supplements, longevity, fasting) into an Obsidian vault. Incremental and idempotent by message id, and the manual counterpart of the weekly job. Triggers: "/health-sync", "pull the health chats".
-
tonydzi Skill Issue MatchMeasure a target repository's queue and find a live open issue the contribution would close, before opening a pull request there. Reports how many PRs are open, how many of the last N closed ones were actually merged, and which issue to attach to, because a cold PR into a dead queue is a wasted artifact. Triggers: "/issue-match", "is this repo worth a PR", "measure the queue".
Audited -
tonydzi Skill Resume LastCollect the last human session, or a specific one by id, into a seed on the clipboard, so a new session continues where the old one broke off, including after a crash or on a machine where native resume does not work. Triggers: "/resume-last", "/resume", "continue the last session".
Audited -
tonydzi Bundle Skill ForgeCreate a node-local skill on a follower machine and prepare its promotion into the shared set through a gate. Use when a new skill idea appears on a peer and should not wait for the hub. Triggers: "/skill-forge <idea>".
-
tonydzi Skill Taste CheckReview content quality before anything is shown or sent (vault notes, outgoing drafts, dedup merges, service files) and return an explicit pass, fail or manual-review verdict. The counterpart of a post-build test gate: that one asks whether the build works, this one whether the writing is fit to show. Triggers: "/taste-check <path|text>", "/taste", "check this note".
Audited -
tonydzi Skill Alpha ReviewOpen the alpha review screen to mark judge keepers as gold or miss, read per-miner precision, and print the eval state. Use when tuning a miner's accuracy. Thin launcher over the existing harvest engine and local review server. Triggers: "/alpha-review", "alpha screen", "open the review screen".
Audited -
tonydzi Skill Chatgpt SyncPull fresh ChatGPT conversations into an Obsidian vault on demand, the manual twin of the nightly job. Incremental and idempotent by conversation id: never clobbers enriched notes, never duplicates. Triggers: "/chatgpt-sync", "pull chatgpt", "sync chatgpt chats".
-
tonydzi Skill Reality ShowKeep serialized build-in-public content continuous: read one canon file of season, arcs, beats and loops and say which narrative beat to advance next, so episodes chain into a series. Pairs with the episode adapter, which does the writing. Triggers: "/reality-show", "season state", "what arcs are open".
Audited -
tonydzi Skill Whatsapp SyncRefresh WhatsApp text into an Obsidian vault (data layer, dashboard, group labels, contact notes). Text only, never downloads media, and pulls the recent window the live companion bridge exposes rather than a full multi-year archive. Semi-automatic by design: it drives the live bridge and needs the phone nearby. Triggers: "/whatsapp-sync", "pull whatsapp".
-
tonydzi Bundle Canon RevisionRestructure an always-loaded rules file such as CLAUDE.md or MEMORY.md: build a top block of key rules plus numbered categories, move rule bodies verbatim with a script that proves zero byte loss, fold heavy mechanics into trigger-plus-pointer form, then guards, a canary window and fleet rollout. For scheduled maintenance, not ad-hoc trimming. Triggers: "/canon-revision", "revise the canon".
-
tonydzi Skill Notpeople WaveRun an investor-outreach wave end to end: assemble the batch of targets, personalize pitches from real templates, send from the designated account, and log every touch in the CRM. Walks the exact checklist with rate limits and dedup against everyone already contacted. Triggers: "/notpeople-wave", "next outreach batch".
Audited -
tonydzi Skill Cofounder WatchWatch a live lead funnel with a zero-token dispatcher and surface salient events as short advice: replied but no scheduling link, link sent with no booking in 24h, awaiting reply. Deduped so it never nags twice, and read-only. Triggers: "/cofounder-watch", "what does the cofounder see", "funnel signals".
Audited -
tonydzi Skill Obsidian BackupRun the vault data-safety runbook: 3-2-1 backup, the never-deleted originals archive, the schedulers that keep it running, and the restore or new-machine migration procedure. Verifies by reading state rather than trusting exit codes. Triggers: "make a backup", "verify the backup", "the backup looks broken", "restore the vault".
Audited -
tonydzi Bundle Telegram ReimportFold a fresh export of an already-imported Telegram chat into a vault, adding only the new messages. Idempotent by message id, so it never duplicates. Triggers: "re-import <chat>", "update the telegram import".
-
tonydzi Skill Telegram AssistantRun Telegram as a scoped auto-reply assistant grounded in the owner's vault and written in their voice: whitelisted low-stakes chats are answered autonomously, while anything financial, committing, sensitive or from an unknown contact becomes a draft for the owner. Triggers: "handle my telegram", "reply for me in <chat>", or a new message in a whitelisted chat.
-
tonydzi Skill Telegram Lead OutreachWork leads in Telegram: find prospects by topic, keep only those who self-mentioned it, resolve their handle including through shared groups, pitch personalized and grounded in real templates, run a two-step scheduling close, triage follow-ups, and capture everyone in the CRM. Triggers: "find leads for <topic>", "pitch this prospect", "run outreach".
Audited -
kimtth Skill PythonUse when: write or review idiomatic, typed, well-structured Python that is easy to test and maintain.
-
kimtth Skill MockingUse when: use test doubles correctly — mock true boundaries, not the code under test.
-
kimtth Skill CritiqueUse when: give structured, specific design critique with actionable fixes, not vague feedback.
-
kimtth Skill Grill MeUse when: pressure-test your own reasoning or a plan before committing to it.
-
kimtth Skill RefactorUse when: improve code structure, readability, type safety, or maintainability without changing external behavior.
-
kimtth Skill Zoom OutUse when: step back from unfamiliar code and map surrounding modules, callers, concepts, and ownership before editing.
-
kimtth Skill Git BisectUse when: find the commit that introduced a bug with a binary search over history.
-
kimtth Skill Git CommitUse when: create a conventional git commit from the current diff with logical staging and message analysis.
-
kimtth Skill Git RebaseUse when: clean up or reorder commits with rebase while keeping history safe and reviewable.
-
kimtth Skill TypescriptUse when: write or review TypeScript that maximizes type safety without fighting the compiler.
-
kimtth Skill ConcurrencyUse when: write or review concurrent code that avoids races, deadlocks, and shared-state bugs.
-
kimtth Skill Watch VideoUse when: answer questions about a video URL or local file by seeing its frames and reading its transcript.
-
kimtth Skill Load TestingUse when: measure system behavior under load to find limits, bottlenecks, and regressions.
-
kimtth Skill AuthorizationUse when: design or review access control so users can only do what they are permitted to do.
-
kimtth Skill BrainstormingUse when: explore options or decompose an ambiguous problem before committing to one approach.
-
kimtth Skill ObservabilityUse when: instrument a system with logs, metrics, and traces to understand it in production.
-
kimtth Skill Rate LimitingUse when: protect a service with rate limiting and backpressure without harming legitimate users.
-
kimtth Skill AuthenticationUse when: implement or review authentication flows, sessions, tokens, and password handling securely.
-
kimtth Skill Clean CodebaseClean up dead code, obsolete paths, and contradictions in the codebase to keep it small, correct, and aligned with reality.
Frequently asked questions
What are Coding & Dev Tools agent skills?
Coding agent skills teach AI agents repeatable engineering workflows: reviewing pull requests, writing tests, refactoring safely, and enforcing house style. Install one SKILL.md and your agent applies the same checklist every time, whether you use Claude Code, Cursor, Codex, or another agent.
Which Coding & Dev Tools skills are most installed?
Popular Coding & Dev Tools skills on SkillMD right now include grill-me, notebooklm, health-sync. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Coding & Dev Tools skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.