Search the docs, videos, blog, apps, teams, skills and release notes.
At a glance
What it is
Plan how to get found in search without paying per click. Pick realistic queries, group them into topic clusters, write page briefs and track rankings.
A skill is a written procedure a bot loads when a job calls for it. This one is a single file, SKILL.md, and the whole file is on this page.
The whole file, exactly as it downloads. Read it before you rely on it.
SKILL.md
71 lines · 726 words
As of: 2026-05-16
Mode skill. Default-enabled on the Channels specialist.
Use when the user wants to be found through search, Google, YouTube, AI-answer engines, without paying per click. Use when planning content that earns traffic over months, not days. Use when the brief mentions blog, content marketing, organic discovery, or "ranking" for a topic.
Trigger phrases:
Plan how to get found in search without paying per click. Pick realistic queries, group them into topic clusters, write page briefs and track rankings.
Nothing. It ships with Murage, which is open source. Your bots run on the AI plan you already have.
Yes. Open it in Settings → Skills to read, edit or duplicate it. Skill Guard scans it again after every edit.
Download the app, connect the AI you already pay for, and tell your Chief of Staff what needs doing. Plan on about ten minutes from install to a working team.
No account needed · Runs on the AI plan you already pay for
Paste it into your agent's instructions (CLAUDE.md, AGENTS.md or a custom GPT), or add it to a bot in Murage.
Ask Ember for the bot, then switch the skill on in its settings.
Step 1
Send your Chief of Staff this message. It proposes the bot and its role first, and creates it when you say go.
Send this to Ember
“Create a bot that uses the Organic SEO skill, and show me the plan first.”
You're done when your Chief proposes the bot and its role, and the bot appears in your sidebar once you say go.
Step 2
You're done when you see the bot’s skills and the library.
Step 3
You're done when the skill shows as on for that bot.
Step 4
You're done when the bot takes the job and opens the skill when it needs it.
Prefer to do it yourself? Choose + in the sidebar, then New Bot.Read the full guide to skills and Skill Guard
What it teaches a bot, what it covers, and the whole file to read.
The principle
**Mode skill.** Default-enabled on the Channels specialist.
What it covers
When to use
Procedure
Decision rules
Anti-patterns
Before / after
Each of these library teams gives its bots this skill. Import one and look inside first.
"Help me with SEO."
"What should our blog cover?"
"We need more organic traffic."
If Research has posted audience query patterns to TEAM_MEMORY.md, start at step 2.
1. Map queries to stages. Pull the actual search queries the audience uses and tag each by Awareness / Consideration / Buying.
Consideration queries: informational ("how to fix X", "what is Y", comparisons, alternatives lists).
Buying queries: transactional ("buy X", "X pricing", "X demo", branded terms, "near me").
Awareness queries: category-defining or trend terms with high volume and low intent, useful for topical authority signals, not direct conversion.
2. Triage by realism. For each query, score (a) monthly volume, (b) keyword difficulty / domain-authority gap, (c) commercial intent. Reject queries where difficulty exceeds current authority by more than one standard step. Pick clusters where you can plausibly rank within 6-12 months given current site authority.
3. Cluster, then write briefs. Group related queries into topic clusters. For each cluster, define one pillar page (broad, intent-matching the main query) and 3-7 supporting pages (specific sub-queries linking to the pillar). Each brief specifies: target query, search intent (informational / commercial / transactional), word-count range based on top-10 SERP analysis, must-cover sub-topics, primary CTA appropriate to stage.
4. Spec the structural requirements. Title tag pattern, meta description posture, H1-H2 hierarchy, internal-link map (which cluster pages link to which pillar), schema markup type (Article, Product, FAQ, HowTo), canonical strategy. Pass the brief to Copy for the words.
5. Define measurement. Per cluster: target ranking position by month 3, 6, 12; impression growth; click-through rate against position; assisted conversions. Stage-appropriate, do not grade a consideration-stage cluster on direct revenue in month one.
Intent match beats keyword stuffing. If the top-10 SERP for a query is all how-to guides, your product page will not rank, and should not. Match the intent.
AI-answer surfaces need explicit answers. Lead each section with a one-sentence direct answer to the question in the H2. Generative answer engines extract the first declarative sentence.
Domain authority gates ambition. A new site cannot win head terms. Earn long-tail wins first; aggregate them into topical authority; raise the ambition over quarters.
One target query per page. Pages targeting "the cheap option" and "the premium option" need separate URLs; cannibalization splits ranking signals.
As of 2026-05-16: search-engine UX continues shifting to AI summaries. Optimize for being the cited source, not only for blue-link clicks. Flag any pre-2025 SEO playbook the user references as stale.
Writing for keywords humans never search. Use real query data, not assumptions.
Chasing high-volume head terms before earning authority on the long tail.
Treating SEO as a writing project. It is a research-driven content engineering project; words are the last step.
Single-page "ultimate guides" that target 30 keywords. Split into clusters.
Skipping the technical layer (page speed, indexability, internal linking) because content feels more glamorous.
Quoting ranking timelines as guarantees. Search is a probabilistic game; commit to inputs, not outputs.
Brief: "We want to rank for project management."
Before (head-term ambition, no cluster):
Write a 5,000-word guide titled "The Ultimate Guide to Project Management."
After (intent-mapped cluster, 2026-05-16):
Pillar: "Project management for [vertical]", target consideration-stage commercial intent (KD: medium-high, plausibly rankable in 9-12 months with 30 supporting pages). Supporting cluster: 12 long-tail how-to queries (KD: low, rankable in 3-6 months) + 6 comparison queries vs. named competitors (buying-stage). Each support page links to pillar; pillar links to product. Lead every H2 with a one-sentence direct answer for AI-answer surfaces. Measure: impression growth on cluster, top-3 ranks on 8 long-tails by month 6.
SKILL.md
71 lines · 726 words
The text of SKILL.md is shown as it downloads, under the Apache-2.0 license, by Ferrox Labs. The license is the one in the file's own frontmatter.
Your new bot
Organic SEO bot
Waiting in your sidebar once you say go.
No account needed · Runs on the AI plan you already pay for