Skill Spotter is a Claude Code plugin that notices tasks you keep repeating and offers to save them as a skill you can run with /name. It compares what Claude did, not just what you typed, so a rephrased request still counts.
Be the first to rate Skill Spotter. Your feedback helps other users decide.
After the third request of a kind, a band offers to create a named skill; Claude drafts it, and next time /name does the task.
It compares the commands, files and tools Claude used as well as your prompt, and it also spots multi-prompt workflows.
When you add the same instruction to many different requests, it offers to put it in CLAUDE.md instead.
Similar tools in the same category — compare side-by-side
App Factory is a Claude Code plugin marketplace of 42 skills in eight opt-in tracks that build, desc...
Heldkeys answers one question: if a prompt injection hijacked the AI agent running here, which crede...
Termexo is a Windows workbench where one AI operates your other coding agents. It works with Claude ...
Guides and comparisons about code tools
Eight new tools that hand a coding agent the shape of your project: repeated tasks become skills, design systems become readable, and DONE becomes checkable.
Nine tools that constrain what an agent can produce and reach: slop-detecting lint rules, declared sandbox tiers, cheaper crawling and signed messaging.
Twenty-five coding tools sorted by what they do: autocomplete, codebase comprehension, testing, or self-hostable models, from CodeGeeX to Codestral.
Coding agents increased output but not shipped software. The gap is verification, context and drift. Here is what converts agent output into working systems.
Agents need guardrails. Blocklists and judge models fail because they cannot see data flow. Deterministic engines track labels across tool calls instead.
