onboard
Skill6 starsChanged 4 months agoMITView on GitHub
Builds your entire canonical marketing brief in one guided pass (business, market, customer, competitors, positioning, offer, channels, voice, numbers) and saves it as marketing-brief.md so the whole department loads it into every future session automatically. Use once, first, when setting up.
165 other projects use a version of this.
Adopted by
Most recently taken up by
- ggoosen/Digital-Workforcetheir own version, first seen Nov 8, 2026
- joeldevz/skynex-pitheir own version, first seen Nov 8, 2026
- eggs-gd/career-spacetheir own version, first seen Nov 8, 2026
- Codename-11/SubFrametheir own version, first seen Nov 8, 2026
- passion4it-gmbh/passionfruit-sitetheir own version, first seen Nov 5, 2026
- striderZA/OpenCodeGameStudiostheir own version, first seen Nov 4, 2026
Used with
Projects with it also use soak-test, team-live-ops 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.
lilangMaxSkillsoak-test
Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.
Also in 9 projects that use this
lilangMaxSkillteam-live-ops
Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.
Also in 9 projects that use this
HK-hubSkillteach-impeccable
One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.
Also in 19 projects that use this
CoralGameSkillproject-stage-detect
Automatically analyze project state, detect stage, identify gaps, and recommend next steps based on existing artifacts.
Also in 15 projects that use this
CoralGameSkillteam-level
Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.
Also in 11 projects that use this
- +5 more from lilangMax
- +2 more from CoralGame
Other versions165 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 165
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- nateherkai/AIS-OS★ 1.4ksame name
- poshan0126/dotclaude★ 871same name
- talesofai/cohub★ 585same name
- me2resh/apexyard★ 542same name
- nexmoe/DayBee★ 424same name
- nexmoe/eve★ 424same name
155 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 repository29 other files it gives its agents.
- ad-scriptsSkill
- battlecardSkill
- brand-voiceSkill
- campaign-debriefSkill
- case-study-writerSkill
- channel-pickerSkill
- cmoSkill
- competitor-teardownSkill
- content-calendarSkill
- creative-briefSkill
- customer-deep-diveSkill
- email-sequenceSkill
- experiment-backlogSkill
- funnel-mapSkill
- hook-factorySkill
- kpi-treeSkill
- landing-pageSkill
- launch-planSkill
- lead-magnet-builderSkill
- marketing-auditSkill
- market-research-sprintSkill
- message-mapSkill
- objection-mapSkill
- offer-builderSkill
- positioning-workshopSkill
- pricing-testSkill
- repurposeSkill
- research-to-briefSkill
- weekly-reviewSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 153 edited versions we read keep these.
2
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 13
If little is provided, ask for the few highest-value inputs first (website, who buys and why in their words, the main competitors, the …
- Very specific: line 16
Create marketing-brief.md in the project root from marketing-brief.example.md (in this plugin) and fill it in this order, carrying each …
- Distinctive: line 36
If a section deserves deeper work, name the specialist for it (e.g.
“Common” is measured: kept by at least 6 in 10 of the 153 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
Onboard — brief the department once
This is the one-command setup. A marketing department is only as good as its shared context, so before anyone writes a hook or sizes a market, the department gets briefed — once. This skill captures the business, market, customer, competitors, positioning, offer, channels, voice, and numbers into a single canonical marketing-brief.md, which the SessionStart hook then loads into every future session. One briefing, 50 specialists on the same page forever.
Inputs
- Company and website, plus any evidence available to paste: won-deal notes, customer quotes or reviews, call notes, competitor names, pricing, current channel numbers: $ARGUMENTS
- If little is provided, ask for the few highest-value inputs first (website, who buys and why in their words, the main competitors, the price) rather than blocking on everything.
Do this — build the brief section by section
Create marketing-brief.md in the project root from marketing-brief.example.md (in this plugin) and fill it in this order, carrying each section forward as context for the next:
- The business — what is sold, to whom, at what price, delivered how, and the revenue goal marketing is accountable for. One tight paragraph.
- The customer — ICP (firmographics, qualifiers, disqualifiers from real wins/losses), avatar sketch, top 5 pains and desired outcomes in the buyer's own words, known objections, and a starter language bank from any verbatim material pasted. This is the section copy gets written from — spend the most care here.
- The competitors — the 3–5 alternatives buyers actually weigh (including "do nothing"), each with offer, claimed position, and exploitable weakness.
- The market — a working TAM/SAM/SOM (bottom-up, assumptions graded T1 sourced / T2 estimate / T3 guess), the beachhead segment, and the category rules.
- Positioning & message — the position sentence (for WHO, against ALTERNATIVE, the one DIFFERENCE, the PROOF), core message, three pillars with proof each, and the banned-phrases list.
- The offer — outcome promised, value stack, price logic, risk reversal, real urgency.
- Channels & funnel — the one primary channel and why, supporting channels, funnel stages with current numbers where known.
- Voice — do/don't rules and 2–3 calibration examples if writing samples exist; otherwise mark the section as pending and suggest
/marketing:brand-voice. - Numbers that matter — north-star metric, drivers, CAC targets, current baseline, all date-stamped.
Grade every section as you go: mark anything built on guesswork T3 so the research backlog is visible in the brief itself.
Output
A complete marketing-brief.md in the project root. Finish with a one-screen readback — the ICP in a line, the top 3 pains, the position sentence, the offer sentence — and ask what to sharpen. Tell the user it now loads automatically every session, and that /marketing:cmo is the next command to run.
Rules
- Evidence over invention at every step. Never fabricate customers, quotes, or metrics to make a section look finished — a thin section marked T3 is more valuable than a confident fiction.
- The buyer's words beat the company's words. Wherever the user pastes verbatim material, harvest it into the language bank.
- Confirm the ICP and the offer with the user before treating the brief as canonical — everything downstream leans on those two.
- If a section deserves deeper work, name the specialist for it (e.g. market sizing → the market-sizer agent, avatar depth → avatar-builder) rather than padding the brief now.
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.

