dev-audit
Post-mortem on what the user has already published on dev.to - which posts actually worked, why, and what to stop doing. Uses the user's own analytics plus ~/.claude/devto/log.md history.
38,472 Skills
Search uses this published catalog; rankings and counts are snapshots.
Post-mortem on what the user has already published on dev.to - which posts actually worked, why, and what to stop doing. Uses the user's own analytics plus ~/.claude/devto/log.md history.
Write a helpful dev.to comment on someone else's article. Produces three angle options, one full comment, and a copy-ready block. Never posts automatically (dev.to's public API has no comment-create endpoint).
Close the dev.to feedback loop after an audit - promote winning title formulas and tags, demote losers, and feed the updated weights back into the next dev-post draft. Run after /dev-audit once the post log has data.
Turn one raw idea into a dev.to article that sounds like you. Produces three title options, one full draft, and a copy-ready block. Never publishes without an explicit yes. Optional: can publish via Forem API if DEVTO_API_KEY is present.
Score a dev.to profile out of 100 against a 13-part rubric and rewrite the parts that lose points - bio, avatar, currently-hacking-on, available-for, pronouns, website, social links, experience level, featured repos, tags followed, orgs, badges, SEO. Use when the user says "optim
Turn one long asset (blog post, docs, newsletter, transcript, client call) into a dev.to article with canonical URL back to the source. Produces title options, tags, body markdown, cover prompt, and a copy-ready block. Never publishes without an explicit yes.
Use when delegating a coding task to mimo (the mimo CLI / Xiaomi opencode fork) — offloading implementation to mimo, resuming a mimo session, or running work on a chosen provider/model. Triggers on "/mimo-code", "run mimo", "delegate to mimo", "resume the mimo session", "offload
Use when one milestone is too large for a single specification or plan and must ship as several ordered stages across sessions.
Turn a vague or underspecified task into a crisp requirements + testable acceptance-criteria document by closing the gap between what was asked and what is actually wanted. Use at the start of any non-trivial task before planning, whenever the goal is fuzzy ("make it faster", "ma
Deliver one change end to end as a single pull request — clarify → plan → implement → simplify → review → validate → open-pr — resuming from wherever it left off. Use to take a task from intent to an open, mergeable PR with each phase run as a focused sub-agent. This is the defau
Build a verified, read-only understanding of a codebase or a slice of it — entry points, code flow, architecture, module boundaries, dependencies, data flow, build/test systems, and existing patterns. A shared sub-skill that clarify, plan, implement, and review call on demand whe
Execute an implementation plan (from `plan`) task by task, writing the code and tests and leaving the system green at every step. Use once you have an agreed plan or a clear next slice of work to build. It does not plan and does not open a PR — it turns a plan into working, teste
Turn a clarified requirements artifact into a concrete, executable implementation plan — a decisive architecture blueprint and a phased build sequence with exact file paths. Use after requirements are pinned down (e.g. by `clarify`) and before writing code, whenever a multi-step
Use when you need to rebase the current branch onto main, resolve merge conflicts, and force-push
Review a change for correctness, quality, and guideline compliance using a library of specialized reviewer roles. Use before opening a PR, after finishing a chunk of work, or to review an existing PR. Two output modes — a local severity-ranked report for a fix loop (default), or
Catalog captured:2026-11-21