Nous Research 为 Hermes Agent 添加 /learn 技能学习命令

Nous Research has expanded the Skills System inside Hermes Agent, its open-source self-improving agent. The new addition is /learn, a command that writes a reusable skill for you. Point it at a document page, a local SDK, a past conversation, or pasted notes. The live agent gathers the material, then authors a SKILL.md on your behalf. Hermes Agent can now /learn from anything: feed it directories of any source material (code, API docs, manuals, PDFs, configs) and it distills a verifiable reusable skill pic.twitter.com/oRznwCRF3E— Nous Research (@NousResearch) June 23, 2026 Hermes Skills System Skills are on-demand knowledge documents the agent loads when needed. Each one is a folder containing a SKILL.md file with instructions. They follow a progressive disclosure pattern to keep token usage low. The format is compatible with the agentskills.io open standard. All skills live in ~/.hermes/skills/, the single source of truth. On a fresh install, bundled skills are copied from the repo. Hub-installed and agent-created skills land there too. Every installed skill becomes a slash command automatically. Running /plan or /axolotl loads that skill’s instructions into the turn. Think of a skill as a reference document the agent reads only when relevant. Memory, by contrast, holds small durable facts that should always stay in context. How /learn Works /learn removes the hand-writing step. You describe a source, and the agent does the sourcing with tools it already has. It reads local directories with read_file and search_files. It fetches online docs with web_extract. It can also capture a workflow you just walked it through. Copy CodeCopiedUse a different Browser# A local SDK or doc directory /learn the REST client in ~/projects/acme-sdk, focus on auth + pagination # An online doc page /learn https://docs.example.com/api/quickstart # The workflow you just completed in this conversation /learn how I just deployed the staging server # Pasted notes or a described procedure /learn filing an expense: open the portal, New > Expense, attach receipt, submit The agent then authors a skill that follows the house authoring standards. That means a description under 60 characters, the standard section order, and Hermes-tool framing. It does not invent commands that do not exist. There is no separate ingestion engine. /learn builds a standards-guided prompt and hands it to the agent as a normal turn. So it works the same in the CLI, the messaging gateway, the TUI, and the dashboard. It also works on any terminal backend, whether local, Docker, or remote. The dashboard adds a Learn a skill button with a directory field, a URL field, and a text box. The agent saves the result with the skill_manage tool. If you have the write-approval gate on, that approval step still applies. Why Skills Stay Cheap Skills load in three levels, so the agent pays only for what it uses. LevelCallReturnsApprox. cost0skills_list()Names, descriptions, categories~3k tokens1skill_view(name)Full content plus metadataVaries2skill_view(name, path)A specific reference fileVaries The agent sees a compact index at all times. It loads full skill content only when a task needs it. This keeps a large skill library from flooding the context window. Four Ways to Create a Skill /learn is one path among several. The right choice depends on who authors the skill and where the source lives. MethodWho authorsSource inputReview gateBest forHand-write SKILL.mdYouYour own knowledgeNoneFull control over wording/learnThe live agentDir, URL, conversation, notesskill_manage gateTurning existing material into a skill fastskill_manage (auto)The agent itselfA workflow it just solvedwrite_approval gateCapturing procedural memory after hard tasksSkills Hub installA third partyRegistry or GitHub repoSecurity scannerReusing community or vendor skills Agent-created skills are the agent’s procedural memory. The agent may save an approach after a complex task of five or more tool calls. It also saves when it hit a dead end and found the working path. By default, write_approval is false, so the agent writes freely. Set it to true to stage every write for review under ~/.hermes/pending/skills/. Use Cases With Examples Onboarding an internal API: Run /learn on your private docs URL. The agent produces a skill covering auth, pagination, and common calls. New teammates then invoke it as a slash command. Capturing a deploy runbook: Walk the agent through one staging deploy. Then run /learn how I just deployed the staging server. The procedure becomes repeatable across the CLI and chat platforms. Grouping a recurring task: Use a skill bundle to load several skills at once. One slash command then pulls in review, test, and PR skills together. Copy CodeCopiedUse a different Browser# ~/.hermes/skill-bundles/backend-dev.yaml name: backend-dev description: Backend feature work — review, test, PR workflow. skills: - github-code-review - test-driven-development - github-pr-workflow instruction: | Always start by writing failing tests, then implement. A Look at the SKILL.md Format A skill is mostly a markdown file with YAML frontmatter. The body follows a fixed section order. /learn targets this exact shape so output stays consistent. Copy CodeCopiedUse a different Browser--- name: my-skill description: Brief description of what this skill does version: 1.0.0 platforms: [macos, linux] # Optional — restrict to specific OS metadata: hermes: tags: [python, automation] category: devops --- # Skill Title ## When to Use Trigger conditions for this skill. ## Procedure 1. Step one 2. Step two ## Pitfalls - Known failure modes and fixes ## Verification How to confirm it worked. The platforms field can hide a skill on incompatible operating systems. Conditional fields can also show a skill only when certain toolsets are present or absent. Interactive Explainer Local directory</div> <div class="tab" data-src="url"><img src="https://s.w.org/images/core/emoji/17.0.2/72x72/1f517.png" alt="🔗" class="wp-smiley" style="height: 1em; max-height: 1em;" /> Doc URL</div> <div class="tab" data-src="conv"><img src="https://s.w.org/images/core/emoji/17.0.2/72x72/1f4ac.png" alt="💬" class="wp-smiley" style="height: 1em; max-height: 1em;" /> Conversation</div> <div class="tab" data-src="notes"><img src="https://s.w.org/images/core/emoji/17.0.2/72x72/1f4dd.png" alt="📝" class="wp-smiley" style="height: 1em; max-height: 1em;" /> Pasted notes</div> </div> <div class="row"> <div> <label>Skill name (slug)</label> <input id="hl-name" value="acme-api" maxlength="40" placeholder="lowercase-with-hyphens"> </div> <div> <label>Category</label> <input id="hl-cat" value="devops" maxlength="24" placeholder="e.g. devops"> </div> </div> <label>Description (house standard: ≤ 60 characters)</label> <input id="hl-desc" value="Acme REST API: auth, pagination, common calls" maxlength="90"> <div class="ct" id="hl-ct">45 / 60</div> <label id="hl-srclabel">Directory path</label> <input id="hl-src" value="~/projects/acme-sdk"> <label id="hl-foclabel">Focus / instruction (optional)</label> <input id="hl-focus" value="focus on auth + pagination"> <div class="cmdprev cmd" id="hl-cmdprev"></div> <button class="run" id="hl-run">Run /learn ▸</button> <div class="out" id="hl-out"> <div class="pd"> <div class="lv"><b>Level 0</b><span>skills_list() · ~3k tokens</span></div> <div class="lv"><b>Level

原文超出正文长度上限，此处截断——上游还有内容，完整版见上方「原文 ↗」。