Showing 2341–2370 of 10164 skills
Use to identify missing instructions in another skill based on its output.
topoteretes/cognee
This skill should be used when the user asks to "create bash scripts", "automate Linux tasks", "monitor system resources", "backup files", "manage users", or "write production shell scripts". It provides ready-to-use shell script templates for system administration.
zebbern/claude-code-guide
Best practices for writing Remotion animations that stay intuitive for agents and editable in Remotion Studio Visual Mode.
guanyang/open-agent-hub
Coordinate external AI tool integration (OpenAI Codex, Google Gemini) for cross-model adversarial review and delegated implementation.
a5c-ai/babysitter
Generate headless Claude Code cron jobs with safety.
notque/vexjoy-agent
Coder-agent working-file budget discipline: keep the editable working set (files you /add into writable context) under ~25k tokens, separate "read" from "edit", delegate breadth to a read-only repo-map, and drop files once edited. Use when an LLM coder-agent edits multiple files, when the working set must stay focused, or when the model starts editing the wrong file / missing targets because too much context dilutes attention. Search keywords: context window full, agent edits wrong file, too much context, /add /drop files, working file budget, context dilution, lost in the middle.
agentsope/SkillAlchemy
SOP for writing, loading, and evolving a project-level convention file (CONVENTIONS.md / CLAUDE.md / .cursor/rules / .clinerules / AGENTS.md) so that a coder-agent reliably respects your codebase's style choices every session. Tool-agnostic; covers the four load mechanics (read-only attachment, ancestor-walk auto-load, glob-scoped rules, agent backstory) and the conflict resolution between pinned conventions and the existing code.
agentsope/SkillAlchemy
SOP for building LLM applications on Dify — visual workflow + chatflow + agent + RAG knowledge base + plugin marketplace + observability, self-hostable. Use when shipping LLM apps fast with a "no-code to pro-code" gradient, especially when non-engineers need to co-author the flow.
agentsope/SkillAlchemy
Build and govern a 50-200 example domain-specific held-out benchmark sampled from real traffic. Distinct from public benchmarks (MMLU/HumanEval/GSM8K via lm-evaluation-harness) which measure GENERAL capability. Only a held-out domain set predicts whether THIS system works on YOUR data. Collect real examples, label, hold out (never train/prompt on it), size 50-200, version it, refresh on drift.
agentsope/SkillAlchemy
Decision protocol for wrapping a REST / GraphQL / RPC API as a tool an LLM agent can call. The load-bearing premise: the *tool surface* is an LM-friendly subset of the *API surface* — one tool per user intent, not one per endpoint. Activates when a coder agent must expose an external HTTP API to a model (function calling, tool_use, MCP, LangChain `@tool`, CrewAI `BaseTool`). Encodes the *what to surface, how to name, how to shape, how to fail* — not any single framework's API. ~80% of agent tools in production are HTTP wrappers; this is the SOP for getting them right.
agentsope/SkillAlchemy
Cross-engine decision rubric for self-hosting or recommending an LLM serving stack. Picks among vLLM, SGLang, TensorRT-LLM, TGI, llama.cpp, Ollama, and MLX as a function of (hardware × workload × constraint), not "which is fastest". Activates whenever a coder-agent must choose, defend, or migrate a serving runtime.
agentsope/SkillAlchemy
Decision protocol for making side-effectful agent tools idempotent — so when an LLM tool call is retried (timeout, framework resume, user re-run, model duplicate emit), the second call is a no-op instead of a double-send. The load-bearing premise: the LM cannot promise it'll call exactly once; the tool must promise the second call is safe. Framework-agnostic — applies to LangGraph node bodies that re-run on resume, MCP tools, OpenAI tool-calling retries, CrewAI delegated tool invocations, and direct HTTP wrappers. Search keywords: duplicate email sent, charged twice, exactly-once, idempotency key, tool called twice, retry side effect, double-send, at-least-once delivery.
agentsope/SkillAlchemy
Lifecycle SOP for **per-model prompt artifacts** — the compiled prompts, instructions, few-shot demos, edit-format pins, and embedding-bound indices that change behavior when the underlying LM, dataset, or framework version changes. Activate when adopting compiled prompts (DSPy, GEPA, BootstrapFewShot output), when supporting multiple LMs in production, when a provider deprecates a model snapshot, or when a framework deprecates a config surface (LlamaIndex `ServiceContext` → `Settings`, Aider edit-format defaults). Do NOT activate for one-off raw prompt edits or for truly model-agnostic system prompts that have been swap-tested. Search keywords: prompt portability, model swap, recompile prompt, model deprecation, prompt per model, prompt breaks on new model, version compiled prompts.
agentsope/SkillAlchemy
The compile-readiness gate for prompt auto-optimization. Decide whether you have earned the right to run an optimizer (DSPy MIPROv2 / GEPA / BootstrapFewShot) before spending compute. Two preconditions only — a real metric, and enough examples for the optimizer you picked. Garbage metric in, garbage prompt out. Pick the optimizer by data scale; GEPA inverts the scale assumption (~10 examples + textual feedback).
agentsope/SkillAlchemy
A 5-minute gate the coder runs at project kickoff (and again whenever the repo shape changes). Classifies the workspace into Greenfield / Brownfield-large / Mid-size-familiar / Library-SDK, then maps the state to an agent strategy (autonomy, context primitive, tool choice). Use BEFORE picking Cursor vs Claude Code vs Aider, BEFORE turning on repo-map, BEFORE writing the first prompt. Skip only if the same repo was gated within the last day and nothing changed. Search keywords: greenfield vs brownfield, new project vs existing codebase, project setup strategy, legacy codebase agent, where to start a coding agent.
agentsope/SkillAlchemy
Adds and tunes a reranker stage for RAG using the retrieve-wide, rerank-narrow pattern. Use when relevant documents appear in the initial top-N but are buried by noise, top-1 precision or MRR is low despite adequate recall, or too many marginal chunks consume context. Covers cross-encoder, API, and local rerankers; N-to-k selection; and latency/cost tradeoffs. Do not use when retrieval recall itself is failing.
agentsope/SkillAlchemy
Project-kickoff rubric for the self-host vs managed-cloud decision — when is running your own inference engine / LLM platform worth the ops cost vs paying per-token for a managed API? Decide on two axes — VOLUME (a cost-crossover slider) and COMPLIANCE (a hard gate). Use at kickoff when choosing where to run inference, or when cost / data-residency pressure forces a re-evaluation.
agentsope/SkillAlchemy
Decision protocol for managing the context/session state of an AI coding tool: when to /clear, when to keep context, and how to detect "context bleed" — the failure mode where stale conversation history biases the model against the current task. Surfaces a discipline that Aider (/clear), Claude Code (/clear), CrewAI (memory=False, re-instantiate), and LangGraph (new thread_id, subgraph isolation) all encode separately but none name as a skill.
agentsope/SkillAlchemy
Decide where to enforce structured LM output (constrain at decode time with Outlines vs validate-and-retry with Instructor vs grammar with Guidance) and which failure stance to take (Assert/hard-fail vs Suggest/soft-retry). Use when an LM's output is parsed or typed by downstream code and you must pick one enforcement library plus its failure handling, when malformed output is burning tokens on retries, or when choosing between decode-time vs validation-time constraints for local vs API models.
agentsope/SkillAlchemy
Enhancement overlay for multi-agent / tool-using coder agents. Encodes the per-agent tool- scoping discipline that role-based frameworks (CrewAI, LangChain) document only as a passing best-practice: which agent gets which tool, and why blanket-sharing every tool to every agent is a correctness and blast-radius risk. Activates when an agent system has tools AND there is more than one agent (or one agent holding many tools). Treat a tool as a capability grant; scope by least-privilege. ENHANCE overlay — read alongside [[crewai]], [[agentsop-http-tool-wrapping]], [[agentsop-llm-tool-idempotency]]. Search keywords: which tools per agent, least-privilege agent, agent tool access, tool permissions, limit agent tools, scope tools to roles.overlay_type: enhancement
agentsope/SkillAlchemy
SOP for distilling reusable semantic operators (data-science operation skills) from agent execution trajectories: read action/observation traces, classify per-task failures, bind data-semantic constraints (input semantics / operation decision / output constraints / validation), and feed bounded edits back through an optimizer such as SkillOpt. Use when mining agent runs for cross-task operation knowledge, when a data-science skill keeps failing on the same operation family (join cardinality, group granularity, unit, time alignment), or when wiring trajectory history into a skill optimizer without polluting the skill body.
agentsope/SkillAlchemy
Decision SOP for serving LLMs with vLLM. Covers PagedAttention mental model, quantization/parallelism/batching tradeoffs, OOM triage, and when NOT to use vLLM. Activates when a coder-agent is choosing or tuning an inference engine, debugging vLLM throughput/latency/OOM, or comparing vLLM against TGI/SGLang/TensorRT-LLM/llama.cpp.
agentsope/SkillAlchemy
ALWAYS USE THIS SKILL to assign permission sets to org users. Assign one or more permission sets to org users using the sf org assign permset command. TRIGGER when the user asks to assign, grant, give, add, or apply permission sets to users, admins, specific orgs, or specific users. Supports granting permissions, giving access, and adding permission sets to default admin or specific users via --on-behalf-of. DO NOT TRIGGER for listing permission sets or checking user permissions.
forcedotcom/sf-skills
Use to enable Salesforce Change Data Capture (CDC) on a standard or custom object, configure a custom event channel, set a filter expression, or add enrichment fields. TRIGGER broadly on any of: 'enable CDC', 'enable Change Data Capture', 'turn on CDC', 'subscribe X to change events', 'only emit events for', 'filter change events', 'enrich change events', 'create a custom event channel'; or any mention of CDC, change events, PlatformEventChannel, PlatformEventChannelMember, EnrichedField, ChangeEvents channel, enrichment fields, change event filter; or when the user wants a downstream system to receive Salesforce data changes; or when the user touches .platformEventChannelMember-meta.xml / .platformEventChannel-meta.xml files. SKIP when publishing platform events, Pub/Sub API or REST/SOAP (use integration-connectivity-generate), or ManagedEventSubscription (out of scope for CDC). Always use this skill for CDC channel-membership metadata.
forcedotcom/sf-skills
Create, read, update, and delete ManagedEventSubscription metadata in Salesforce. Use this skill for any work involving managed event subscriptions, platform event subscriptions, event channel subscribers, or .managedEventSubscription-meta.xml files. TRIGGER when: user asks to subscribe to a platform event, create a managed subscription, set up event replay, configure an event channel subscriber, update replay preset, activate or deactivate a subscription, delete a subscription, or manage ManagedEventSubscription metadata. SKIP when: user needs to create the platform event channel itself (use platform-custom-object-generate skill) or needs Flow-based event subscriptions (use automation-flow-generate skill).
forcedotcom/sf-skills
Generate AgentforcePlatformTracingSettings metadata to enable or disable Agentforce agent execution trace spans flowing to Data Cloud. Use this skill for any AgentforcePlatformTracingSettings metadata work. TRIGGER when: user mentions Agentforce tracing, agent trace spans, Data Cloud tracing, AgentforcePlatformTracingSettings, platform observability tracing, enable agent tracing, wants agent execution spans in Data Cloud, mentions .settings-meta.xml for AgentforcePlatformTracing, or asks about enabling observability for Agentforce agents. DO NOT TRIGGER when: user wants Platform Tracing for TraceSpanEvent (use platform-tracing-configure), wants to query or analyze existing agent trace data in Data Cloud (use agentforce-observe), wants Event Log Files or ELF configuration, wants Change Data Capture (use integration-eventing-cdc-configure), or wants ManagedEventSubscription (use integration-eventing-subscription-configure).
forcedotcom/sf-skills
Generate EventSettings metadata to enable or disable Platform Tracing (TraceSpanEvent publishing) in Event Monitoring. Use this skill for any EventSettings enablePlatformTracing metadata work. TRIGGER when: user mentions Platform Tracing, TraceSpanEvent, enable tracing in Event Monitoring Settings, event monitoring tracing toggle, enablePlatformTracing, .settings-meta.xml for Event settings tracing, turn on trace span events, or stop publishing trace spans. DO NOT TRIGGER when: user wants Agentforce agent tracing to Data Cloud (use platform-tracing-agentforce-configure), wants Event Log Files or ELF generation, wants Change Data Capture (use integration-eventing-cdc-configure), or wants ManagedEventSubscription (use integration-eventing-subscription-configure).
forcedotcom/sf-skills
Use this skill when users need to create, modify, or validate Salesforce Validation Rules. Trigger when users mention validation rules, field validation, data quality rules, formula validation, error messages, or validation logic. Also use when users encounter validation errors, need to update formulas, or want to enforce business rules at the data layer. Always use this skill for any validation rule work.
forcedotcom/sf-skills
ALWAYS USE THIS SKILL to create, check the status of, list, or delete scratch org snapshots. A snapshot is a point-in-time copy of a scratch org's metadata AND data, referenced by name in the `snapshot` field of a scratch org definition file. Use when the user asks to create/take a snapshot, check a snapshot's status or creation progress, list/show/view existing snapshots (including filtering for snapshots expiring soon), or delete/remove a snapshot. Requires a Dev Hub with Scratch Org Snapshots enabled. DO NOT TRIGGER for creating org shapes (use dx-org-shape-manage) or for creating scratch orgs, including from an existing snapshot via `--snapshot` (use dx-org-manage).
forcedotcom/sf-skills
Author a Salesforce Digital Experience brand (a "brand.json") so the VS Code Brand Toolkit can load, edit, and preview it. Use this skill whenever someone wants to: create a brand, make a new brand, generate a brand from a description or a color/logo/mood, add a brand to a project so the Brand Toolkit picks it up, scaffold a brand.json, theme a Digital Experience site, or turn a brand idea ("a dark luxury brand", "match our logo", "coral + rounded + friendly") into a loadable brand. Also use it when the user mentions "Brand Toolkit", "theme manager brand", "brand token", "colorScheme", "primaryAccent", ".digitalExperience/brands", "sfdc_cms:title", or a "brand.json" that should show up in the Brand Toolkit. Do NOT use this skill to apply an existing brand's voice, tone, or guidelines to generated content (use experience-cms-brand-apply), to search Salesforce CMS for existing brands, or to search for images, media, or logos (use experience-search-coordinate).
forcedotcom/sf-skills