performance-evidence
Use when optimizing speed, memory, latency, startup time, throughput, token cost, build time, or runtime resource use.
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-16 00:04
41,214 results
Use when optimizing speed, memory, latency, startup time, throughput, token cost, build time, or runtime resource use.
Use when operations may be retried after timeouts, transient errors, duplicate delivery, process interruption, or uncertain acknowledgement.
Use for Saints Row 3/4 PC modding and the srforge workbench.
Orchestrate a new Skyrim SE/AE mod or major feature from requirements through implementation, validation, packaging, and release. This skill coordinates…
ServiceNow Agile Development 2.0 — the rm_team → rm_sprint → rm_story → rm_epic model, the state and point values ServiceNow actually accepts, how a story is…
This skill should be used when the user asks to "build a fluent app", "create a servicenow app in typescript", or mentions "servicenow sdk", "now-sdk",…
What a Table API read through this MCP actually returns — the 200-character truncation in snow_query_table, the three different display_value defaults,…
Migrate a Dart web server from Shelf to Relic. Side-by-side reference for every API change. Use when converting Shelf code to Relic, replacing…
Code style for SGLang large classes `Scheduler`, `TokenizerManager`, and `ModelRunner`: frozen-code conventions and `__init__` orchestration style. Use when…
Transform an AI agent into a tasteful, disciplined development partner. Not just a code generator, but a collaborator with professional standards, transparent…
Add a desktop upload destination under src/desktop/plugins. Do not use for configuring an existing plugin.
Explain code, architecture, debugging traces, PRs, and language-model outputs through STE-inspired writing, diagrams, interactive HTML, or narrated videos. Use…
Curated upstream guidance for Apify Integration Development; use when the workflow matches the user goal.
Babysit a pull request through its bot review rounds: verify, fix, reply, resolve. Use for any babysit or watch-the-PR ask.
Delegate coding tasks to the Cline CLI (`cline`) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.
Authorized source-code security review and SAST workflows: Semgrep and CodeQL pattern hunting, dangerous API identification, and fix verification.
Onboard a developer to a repository using Ontoly graph summaries. Use when asked to explain a new codebase, identify entrypoints, map packages, or suggest…
Delegate coding tasks to the OpenAI Codex CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.
Analyze internal and package dependencies using Ontoly graph traversal. Use when asked which modules, packages, services, or files depend on each other.
Five-axis code review checklist (correctness, security, readability, performance, test coverage) producing actionable comments instead of style nitpicks. Use…
Implement a piece of work based on a PRD or set of issues.
Implement multi-layer LLM caching with exact match, semantic similarity, and provider-side prompt caching.
One API and one credential for frontier and open-source LLMs, built into your Neon branch and powered by Databricks.
Commit and push skill changes to the configured skills repository after review and validation.