market-research-sprint
Skill6 starsChanged 4 months agoMITView on GitHub
Builds the full market picture in one run — size with the working shown, ranked segments and a beachhead call, trends with timing, channel shortlist, category rules, and whitespace — then writes it into marketing-brief.md. Use when entering a market, picking a beachhead, or replacing hunches with a defensible market view.
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
- message-mapSkill
- objection-mapSkill
- offer-builderSkill
- onboardSkill
- positioning-workshopSkill
- pricing-testSkill
- repurposeSkill
- research-to-briefSkill
- weekly-reviewSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 31
Never present a T3 as a finding.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Market Research Sprint — the whole market picture in one run
Market research fails in two ways: it never gets done, or it becomes a six-week report nobody uses. This sprint does the whole job in one pass — sized, segmented, trend-checked, channel-mapped — with every number graded by confidence, and it ends written into the brief where the rest of the department will actually use it.
Inputs
- The market or product, and the decision this research must drive: $ARGUMENTS
- From
marketing-brief.mdif present: the business (what is sold, at what price), any existing market numbers to verify rather than redo, and the ICP to anchor segmentation.
Do this
Inside Claude Code, steps 2–7 can run in parallel via the market-research agents by name — market-sizer, segment-mapper, trend-tracker, channel-scout, category-analyst, whitespace-finder — with research-synthesiser handling step 8. The steps below are the full method either way.
- Fix the research question. Name the decision this research must drive — enter or skip, which beachhead, how to price, where to distribute. Everything that follows is scoped to that decision.
- Size it bottom-up. TAM, SAM, and SOM built from countable units (number of target businesses × plausible spend), every assumption written out and graded T1 sourced, T2 reasoned estimate, T3 guess. Sanity-check against one top-down source.
- Segment and score. Cut the market two or three ways, score each segment on size, pain intensity, reachability, and willingness to pay, and call the beachhead candidate.
- Read the trends. What is rising and falling — search interest, funding, hiring, community chatter. Separate trend from fad by naming the driver: structural drivers persist, fashionable ones fade.
- Map the channels. Where these buyers already pool — communities, newsletters, events, platforms, voices they trust — with a first read on the cost of reaching them.
- Learn the category rules. Table stakes versus differentiators, how buyers compare options, how mature the category is — worth competing in as-is, or worth reframing.
- Find the whitespace. Cross-reference buyer complaints, gaps in competitor coverage, and emerging segments for ground worth owning.
- Synthesise into one market brief: keep only decision-relevant findings, keep the confidence grades visible, and write it into The market section of
marketing-brief.md(create the file from the plugin's example if it does not exist).
Output
The market brief — sized market with the working shown, segment scorecard and beachhead call, three trends with timing windows, channel shortlist, category rules, whitespace list — written into marketing-brief.md. End with the three decisions this research should drive and the finding you are least confident in.
Rules
- Never present a T3 as a finding. A guess wearing a percentage sign is still a guess — grade it and move on.
- Bottom-up beats top-down. A top-down number is a sanity check, never the headline.
- One beachhead. If two segments tie, pick the more reachable one and note the runner-up.
- Findings serve the named decision. Anything that does not move it gets one appendix line, not brief space.
- Date-stamp the section. Market numbers rot — a dated number can be refreshed, an undated one can only be doubted.
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.

