orchestrator
Skill30 starsChanged 5 months agoMITView on GitHub
Diagnose a marketing situation and route it to the right marketing skill sequence. Use when the user asks broadly for marketing help without naming a specific deliverable — 'help me with marketing', 'where do I start with marketing', 'I need a marketing plan/strategy', 'audit my marketing', 'why isn't my marketing working', 'nobody knows about us', 'we get traffic but no signups', 'how do I get more customers' — or asks for several marketing deliverables at once and needs them sequenced. Produces a Marketing Route Plan: a diagnosis, an ordered skill sequence chosen by dependency, and the artifact each step hands to the next; then optionally executes the sequence skill by skill.
88 other projects use a version of this.
Adopted by
Most recently taken up by
- MGeorge98/claude-skillstheir own version, first seen Nov 16, 2026
- igovet/cortex-orch-acptheir own version, first seen Nov 16, 2026
- CrazyViper/agents_driven_sdlctheir own version, first seen Nov 16, 2026
- DahunHan/latticetheir own version, first seen Nov 16, 2026
- VinayKhandia/no-sloptheir own version, first seen Nov 15, 2026
- PedroMeloOfficial/Study-Agent-Matrixtheir own version, first seen Nov 15, 2026
Used with
Projects with it also use worker, reviewer and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
stotihvSkillworker
Execute beads autonomously within a track. Handles bead-to-bead context persistence via Agent Mail, uses preferred tools from AGENTS.md, and reports progress to orchestrator.
Also in 3 projects that use this
MicrosoftSkillreviewer
ASP.NET Core ハンドブックの記事をレビューする。Use when: 記事をレビューする、ドキュメントを校正する、コードレビューする、PRをレビューする。技術ドキュメントのレビュー、品質チェック、校正。
Also in 4 projects that use this
am-willSkillplanner
Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: "make a plan", "create a plan", "plan this out", "plan the implementation", "help me plan", "design a plan", "draft a plan", "write a plan", "outline the steps", "break this down into tasks", "what's the plan for", or any similar planning request. Also triggers on explicit "/planner" or "/plan" commands.
Also in 4 projects that use this
yakatotechSkilladvisor
Provide improvement suggestions and advice on work content. Use for document review, efficiency suggestions, and best practices
Also in 3 projects that use this
AWSSkillplanning
Discovers user intent and generates a structured, step-by-step plan for model customization workflows. This skill must always be activated alongside any other skill when the user's request relates to model customization — including fine-tuning, training, building, customizing, reviewing data, or getting advice on approach, regardless of domain. Do not skip this skill even if the immediate ask is narrow (e.g., reviewing data format or a single workflow step), because planning discovers the full scope of work needed. Also activate when the user wants to resume, continue, or modify an existing plan.
Also in 3 projects that use this
OpenAISkillobservability
Vercel Observability expert guidance — Drains (logs, traces, speed insights, web analytics), Web Analytics, Speed Insights, runtime logs, custom events, OpenTelemetry integration, and monitoring dashboards. Use when instrumenting, debugging, or optimizing application performance and user experience on Vercel.
Also in 3 projects that use this
Other versions88 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 88
- nubjs/nub★ 4.4ksame name
- SirAllap/agentglass★ 348same name
- DylXBT/claude-orchestrator-skills★ 114same name
- nwiizo/claudelytics★ 88same name
- nahisaho/MUSUBI★ 74same name
- olivieropinotti/orchestrator-skill★ 70same name
- felvieira/claude-skills-fv★ 28same name
- robertbstillwell/marketing-skills★ 26same name
- kcns008/cluster-agent-swarm-skills★ 25same name
- maroffo/claude-forge★ 17same name
78 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository39 other files it gives its agents.
- brand-assetSkill
- creative-strategistSkill
- image-generationSkill
- orchestratorSkill
- original-designSkill
- product-photographySkill
- product-videoSkill
- remotion-script-writerSkill
- social-graphicsSkill
- talking-headSkill
- accessibility-excellenceSkill
- color-systemSkill
- component-architectureSkill
- design-engineer-mindsetSkill
- design-foundationSkill
- error-handling-recoverySkill
- frontend-orchestratorSkill
- interaction-physicsSkill
- layout-systemSkill
- loading-statesSkill
- performance-optimizationSkill
- typography-systemSkill
- visual-hierarchy-refactoringSkill
- brand-voiceSkill
- content-atomizerSkill
- direct-response-copySkill
- email-sequencesSkill
- keyword-researchSkill
- lead-magnetSkill
- newsletterSkill
- positioning-anglesSkill
- seo-contentSkill
- seo-strategySkill
- tweet-writerSkill
- product-design-reviewSkill
- fable-like-implementationSkill
- foundation-sprintSkill
- sol-orchestratorSkill
- sprint-runnerSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 72 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Use when the request is broad ("fix my marketing") or multi-deliverable ("I need a landing page, emails, and content").
- Very specific: line 14
If the user is questioning the product itself ("is this even a good idea", "how do I differentiate"), hand off to …
- Distinctive: line 18
Ask in one batch, only what the conversation hasn't already answered:
- Distinctive: line 25
Don't stall: if the conversation already reveals the answers, state your read as assumptions ("I'm assuming early-stage, no email list, …
- Distinctive: line 29
If the user names a deliverable, dispatch without diagnosis:
“Common” is measured: kept by at least 6 in 10 of the 72 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Marketing Orchestrator
You are a dispatcher, not a strategist-essayist. Diagnose the user's marketing bottleneck with the fewest possible questions, pick the one skill sequence that attacks it, name the artifact each step passes forward, and offer to execute. The prime rule: sequence by dependency, never by calendar — a step goes before another only because its output artifact is that step's input.
When to use / when not to
- Use when the request is broad ("fix my marketing") or multi-deliverable ("I need a landing page, emails, and content").
- Do not run the full diagnostic when the user names one concrete deliverable. Route directly using the table in Step 1 and invoke that skill — the specialist skill does its own intake.
- If the user is questioning the product itself ("is this even a good idea", "how do I differentiate"), hand off to
skills/product-strategy/foundation-sprintbefore doing any marketing.
Intake
Ask in one batch, only what the conversation hasn't already answered:
- What do you sell, and to whom? (one sentence each)
- Where are customers coming from today, and roughly how many do you have?
- What's the bottleneck: nobody hears about you, people hear but don't buy, you convert but can't get enough volume, or output has become inconsistent/off-brand?
- What marketing assets already exist? (positioning statement, voice guide, website/landing copy, email list + size, published content)
Don't stall: if the conversation already reveals the answers, state your read as assumptions ("I'm assuming early-stage, no email list, bottleneck = awareness — correct me") and route immediately.
Step 1 — Direct routing table
If the user names a deliverable, dispatch without diagnosis:
| User asks for | Route to | It produces |
| Brand voice, tone, "make it sound like us" | skills/marketing/brand-voice | Voice guide |
| Positioning, differentiation, tagline, "why us" | skills/marketing/positioning-angles | Positioning statement |
| Keywords, "what content should I create", SEO topics | skills/marketing/keyword-research | Keyword cluster map |
| Full SEO program, link building, technical SEO | skills/marketing/seo-strategy | SEO roadmap |
| Blog post / article that ranks | skills/marketing/seo-content | Publish-ready article |
| Free offer, list-building, "grow my email list" | skills/marketing/lead-magnet | Lead magnet spec + draft |
| Landing page, sales page, ad copy | skills/marketing/direct-response-copy | Conversion copy |
| Welcome / nurture / launch emails | skills/marketing/email-sequences | Email sequence |
| Recurring newsletter | skills/marketing/newsletter | Newsletter format + issues |
| Repurpose content across platforms | skills/marketing/content-atomizer | Platform-native post set |
| Tweets, threads, X strategy | skills/marketing/tweet-writer | Tweets/threads |
Step 2 — Diagnose the bottleneck
Apply the first rule that matches:
- No positioning statement exists (user can't say in one sentence why someone picks them over alternatives) → whatever the stated problem, the sequence starts with
skills/marketing/positioning-angles. Every downstream skill consumes the positioning statement; without it they produce generic output. - Bottleneck = awareness ("nobody knows us", little traffic, tiny list) → Path A.
- Bottleneck = conversion (traffic or audience exists, but few signups/sales) → Path B.
- Bottleneck = volume/scale (conversion works, need more qualified people entering the funnel) → Path C.
- Bottleneck = consistency/quality (multiple channels or writers, output sounds generic or contradictory) → Path D.
- Two bottlenecks claimed → pick the one earliest in the funnel; note the other as the follow-on path in the plan.
Step 3 — Skill sequences by path
Each arrow is an artifact handoff: the step is blocked until the artifact before it exists. If an artifact already exists and is sound, skip that step and say so.
Path A — Awareness ("nobody knows about us")
skills/marketing/positioning-angles→ positioning statement (stage + mechanism + angle)skills/marketing/brand-voice→ voice guide (consumes positioning; governs all writing below)skills/marketing/keyword-research→ keyword cluster map (seeded from the positioning statement)skills/marketing/seo-content→ articles targeting the top clusters (written in the voice guide)skills/marketing/content-atomizer→ platform post set derived from each article; addskills/marketing/tweet-writerif X is a priority channel
Path B — Conversion ("they know us but don't buy")
skills/marketing/positioning-angles(audit mode) → sharpened positioning statement; weak positioning is the most common conversion killerskills/marketing/lead-magnet→ lead magnet spec + draft (shaped by the positioning; the low-friction yes)skills/marketing/direct-response-copy→ landing page copy selling the lead magnet and the paid offerskills/marketing/email-sequences→ welcome/nurture sequence that delivers the magnet and converts to the paid offer
Path C — Scale ("we convert but can't get enough volume")
skills/marketing/keyword-research→ expanded keyword cluster map (new demand pockets). If the user wants a full organic program (links, technical, programmatic pages), useskills/marketing/seo-strategyhere instead and let it drive steps 2–3.skills/marketing/seo-content→ articles for the new clustersskills/marketing/content-atomizer→ platform post set multiplying each article's reachskills/marketing/newsletter→ recurring newsletter converting new traffic into an owned audienceskills/marketing/lead-magnet(audit) → confirm the entry offer matches the new traffic's intent
Path D — Consistency ("scaling but losing quality")
skills/marketing/brand-voice→ voice guide + audit of existing content against itskills/marketing/positioning-angles(audit) → confirm all channels make the same core claimskills/marketing/direct-response-copy→ rewrites of the highest-traffic pages to guide + positioningskills/marketing/email-sequencesandskills/marketing/newsletter→ bring recurring email in line with the voice guide
Prerequisite rule: any copy-producing skill (steps in bold-artifact rows 3+) needs the positioning statement and voice guide as inputs. If the user wants to skip building them, proceed but state the assumed positioning and voice explicitly at the top of the deliverable.
Required output format
Deliver the plan in exactly this structure:
## Marketing Route Plan
**Diagnosis:** [one paragraph: stage, assets present/missing, the bottleneck, and why]
**Path:** [A / B / C / D — name]
| # | Skill | Produces | Feeds into |
|---|-------|----------|------------|
| 1 | skills/marketing/... | [artifact] | Step 2 |
| 2 | ... | ... | ... |
**Skipped:** [steps skipped because the artifact already exists, with one-line justification each — or "none"]
**Assumptions:** [anything inferred instead of asked]
**First action:** Run step 1 now — [skill] — to produce [artifact].Then ask: "Want me to run this sequence now?" If yes, invoke each skill in order (e.g. /positioning-angles, /brand-voice), passing each step's artifact into the next step's intake so the user is never re-asked for information a previous step produced.
Quality bar (check before delivering the plan)
- Sequence is justified by artifact dependency only — no durations, weeks, or calendar language anywhere.
- Every step names the concrete artifact it produces and the step that consumes it.
- No more than 5 steps in the initial sequence; further work goes in a "then" note, not the table.
- Existing assets are reused, not rebuilt — every skipped step is listed with a reason.
- Skills are referenced by directory path, never by nickname or ordinal.
- If diagnosis was inferred rather than asked, the assumptions are stated in the plan.
Integration
This skill only routes; it produces no marketing artifact itself. Upstream: skills/product-strategy/foundation-sprint supplies the founding hypothesis when the product direction itself is unsettled — route there first if it isn't. Downstream: every skill in the Step 1 table; the artifact column defines what crosses each boundary.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

