「agent-instructions」の検索結果

[omh] Agent instruction file for a repo -- AGENTS.md, CLAUDE.md, a Cursor rule: write or update what an agent cannot derive from the code, inside a marked region, with every command verified or marked unverified and no counts that drift. Use when the user says: agent-instructions, agents.md, claude.md, gemini.md, copilot-instructions.md, .cursorrules, cursor rules, cursor rule.

日本語の概要は準備中です。原文の説明を表示しています。

Reviews one SKILL.md against the format rules and returns a findings table: strict YAML front matter with exactly name and description, name equal to the folder, description as the trigger, the eight-heading skeleton, capability-neutral wording, safety boundaries. Each finding carries severity, rule identifier, location, quoted evidence and replacement text; the verdict READY, REVISE or BLOCKED is an apparent state and the owner decides. Use when the user asks to "review this SKILL.md", "check my skill file before upload", "lint this skill description", "validate the front matter of this skill" or "score this skill folder". Do not use to write an agent's instructions field, use agent-instructions-drafter instead; for injection or leakage exposures use agent-instructions-red-team; for launch tests use agent-evaluation-plan. Drafts for human review; never approves, authorises or signs off.

日本語の概要は準備中です。原文の説明を表示しています。

Use when defining or refining the tone, voice, and behavioral personality of an Agentforce agent: system instruction encoding, brand voice alignment, adaptive response formats, multi-persona strategies. NOT for writing the actual conversational copy — utterances, fallback messages, escalation phrasing — use admin/agent-conversation-design. NOT for topic scope design — use agentforce/agent-topic-design.

日本語の概要は準備中です。原文の説明を表示しています。

Use this skill when designing, auditing, or troubleshooting behavioral boundaries for Agentforce agents — including topic (now subagent) Scope fields, agent-level system instructions, topic/action filters, the Escalation topic, restricted topics, and Instruction Adherence monitoring. Trigger keywords: agent guardrails, agent out of scope, restrict agent behavior, topic scope, subagent scope, agent fallback, Escalation topic, abuse prevention, action filters. NOT for Trust Layer content filtering (Einstein Trust Layer is a separate product concern), NOT for general topic routing design (use agentforce/agent-topic-design), NOT for prompt template construction (use agentforce/prompt-builder-templates).

日本語の概要は準備中です。原文の説明を表示しています。

Drafts the instructions field of a declarative agent that orchestrates a set of custom skills, under a character cap (default 8,000), from the skills' names and descriptions: role and scope, one routing rule per skill, workflow order, gates written as workflow holds, global rules, output format and what the agent never does. Returns the text in a fenced block with its character count labelled counted or estimated, plus a skill inventory, routing table, gate table, rules trace and open questions for the owner. Use when the user asks to "write the instructions for my agent", "draft a system prompt that ties these skills together", "tighten these agent instructions to fit the cap", "how should the agent route between these skills" or "revise my agent's orchestration text". Do not use to review a single SKILL.md, use skill-file-reviewer instead. Drafts for human review; never approves, authorises or signs off.

日本語の概要は準備中です。原文の説明を表示しています。

Reviews the instructions text and skills of a declarative agent, with its stated capabilities, knowledge sources and audience, for prompt-injection exposure, data-leakage paths, over-broad permissions and missing refusals, and returns an attack-surface map, a findings table with severity, quoted evidence and attack path, one pasteable fix per finding, a probe pack the owner can run and a refusal-coverage table. Use when the user asks to "red-team this agent", "check these instructions for prompt injection", "could this agent leak data", "review the permissions on my agent" or "what should this agent refuse". Do not use for checking a SKILL.md against the format rules, use skill-file-reviewer instead; do not use for designing the launch test set, use agent-evaluation-plan instead. Drafts for human review; never approves, authorises or signs off.

日本語の概要は準備中です。原文の説明を表示しています。

Designs a pre-launch evaluation plan for a declarative agent from its instructions text, skills, capabilities, knowledge sources and sample requests: a behaviour contract of testable statements quoted from the text, test prompts by scenario family and tier with setup, expected behaviour, pass and fail criteria and red flags, a red-flag catalogue, a blank scoring sheet, a coverage table and a go or no-go checklist the owner completes and decides. Use when the user asks to "write test cases for my agent", "how do I evaluate this agent before launch", "build a test plan for the agent", "what should I check before publishing this agent" or "give me a go no-go checklist". Do not use for finding injection or leakage exposures in the instructions, use agent-instructions-red-team instead; do not use for reviewing one SKILL.md, use skill-file-reviewer instead. Drafts for human review; never approves, authorises or signs off.

日本語の概要は準備中です。原文の説明を表示しています。

Audit the project's agent / LLM instruction files for vague rules, missing examples, drifted compliance, and mechanical-enforcement opportunities.

日本語の概要は準備中です。原文の説明を表示しています。