skill-autobench
Author an eval for an existing skill from its REAL usage history, not its spec. Mine invocations from the brain's conversation archive (conversations/) and…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-18 00:15
53,922 results
Author an eval for an existing skill from its REAL usage history, not its spec. Mine invocations from the brain's conversation archive (conversations/) and…
Create new skills following the GBrain conformance standard. Generates SKILL.md with frontmatter, Contract, Phases, Output Format, and Anti-Patterns.…
Ingest a voice note with exact-phrasing preservation (never paraphrased). Routes content to originals/, concepts/, people/, companies/, ideas/, personal/, or…
Generic framework for converting external events (SMS, meetings, social mentions) into brain-ingestible signals. Define a transform function, register a…
Explain a feature, flow, or concept by grounding in source-of-truth, leading with the answer, and diagramming each load-bearing mental model. TRIGGER when:…
Multi-reviewer panel on N focused questions about a near-final artifact (plan, design, code, prose). R0 (you) plus two parallel reviewer subagents,…
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText,…
Prefect CLI commands for mutations. The MCP server is read-only - use this skill when you need to trigger deployments, cancel flow runs, create automations, or…
Manage open-source GitHub issue backlogs (especially PrefectHQ/prefect) in batches. Use for backlog cleanup days, stale review, duplicate pruning, missing-info…
Update a PrestaShop store by using the Module Update Assistant. Use when the user asks to update a store or assess the compatibility with the newer versions of…
Cuts the next release of the unified Prisma CLI: bumps the root package.json version (on the Prisma 8 RC line: 8.0.0-rc.N → rc.N+1), propagates it to every…
Reviews argumentative prose - essays, proposals, position papers, recommendation memos, strategy docs, and op-eds - against the Toulmin model of argument:…
Write vanilla JavaScript for Web Components with functional core, imperative shell. Use when creating JavaScript files, building interactive components, or…
Implement environment variable management with .env files, validation, and environment-specific configs. Use when setting up configuration, handling secrets,…
Interactive issue management with menu-driven CRUD operations. Use when managing issues, viewing issue status, editing issue fields, performing bulk…
Transform and optimize text content with intelligent formatting. Output BBCode + Markdown hybrid format optimized for forums. Triggers on "format text", "text…
Apply when wiring configuration, validation, error handling, or the adapter code between the program and its host, its callers, or its dependencies. Validate,…
Apply when work applies one recipe across files, records, or runs, or produces files or answers a tool could produce. Where work follows a recipe, the recipe…
Apply when the same instruction is about to be written a second time, or the same correction comes back. A recurring fix goes into a mechanism (a tool, code,…
Apply when a claim rests on a measured number: a benchmark, a speedup, a latency, a size, a pass rate, or a count of runs. A measured number is only as good as…
Apply when a fix would add a guard, a catch, or a comment defending it, when the same cause could recur elsewhere, or when a failure shows only after a…
Apply when about to add a file, a layer, a dependency, or a parameter. Get the most result out of the least code and the fewest moving parts.
Apply when work reaches a choice that the spec and the code leave open. Work stops for the user only where the user's answer is what is missing.
Apply when a spec plans a rewrite or a migration in phases. A planned migration aims at its end state.