agentleFS
marcus-at-localhostmarcus-at-localhost/market-context-kit/skills/help/SKILL.md

help

Skill0 starsChanged 3 months agoMITView on GitHub

Index of the Market Context Kit commands. Manual reference only.

  • Installs packages

76 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use create-stories, story-done 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.
  • lilangMaxSkill

    create-stories

    Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.

    Also in 9 projects that use this

  • lilangMaxSkill

    story-done

    End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.

    Also in 9 projects that use this

  • +10 more from lilangMax

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 57 edited versions we read keep these.

  • 0

    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
  1. Very specific:

    Every command writes MARKETKIT - <PURPOSE> - <SCOPE>.<extension> into the active Audit/ folder — see …

    line 15

“Common” is measured: kept by at least 6 in 10 of the 57 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Market Context Kit — Command Index

Fifteen marketing skills for analyzing websites, generating content, auditing funnels, and producing client deliverables. Each one is its own command — invoke it directly. There is no routing step.

The suite loads as a plugin, so the marketkit: prefix is part of every trigger. Dropping it does not resolve.

Every command writes MARKETKIT - <PURPOSE> - <SCOPE>.<extension> into the active Audit/ folder — see ${CLAUDE_PLUGIN_ROOT}/references/output-location.md. SCOPE is the exact target domain for URL-based commands; topic-only commands ask for an explicit domain or customer scope first.

CommandWhat it doesPurpose
/marketkit:audit <url>Full marketing audit, 5 parallel subagents, scored 0-100MARKETING-AUDIT
/marketkit:copy <url>Copy analysis and before/after rewritesCOPY-SUGGESTIONS
/marketkit:seo <url>SEO content audit, on-page + E-E-A-T + technicalSEO-AUDIT
/marketkit:landing <url>Landing page CRO, section by sectionLANDING-CRO
/marketkit:funnel <url>Funnel mapping and drop-off analysisFUNNEL-ANALYSIS
/marketkit:competitors <url>Competitive intelligence and gap analysisCOMPETITOR-REPORT
/marketkit:brand <url>Brand voice analysis and guidelinesBRAND-VOICE
/marketkit:content-plan <url>Topic research, content plan, article draftsCONTENT-PLAN + ARTICLE-<SLUG>
/marketkit:emails <topic-or-url>Email sequences with subject lines and cadenceEMAIL-SEQUENCES
/marketkit:social <topic-or-url>30-day social calendar and platform postsSOCIAL-CALENDAR
/marketkit:ads <url>Ad creative, targeting, and budget planAD-CAMPAIGNS
/marketkit:launch <product>Launch playbook and timelineLAUNCH-PLAYBOOK
/marketkit:proposal <client>Client-ready services proposalCLIENT-PROPOSAL
/marketkit:report <url>Combined Markdown report from prior outputsMARKETING-REPORT (.md)
/marketkit:report-pdf <url>Same report as a branded PDF with chartsMARKETING-REPORT (.pdf) + REPORT-DATA (.json, flat under data/)

Namespaced forms also work: /marketkit:audit. Claude invokes these on its own when a request matches — you do not have to type the command.

Which one to start with

  • Whole site, do not know where to start → /marketkit:audit
  • One page underperforming → /marketkit:landing, or /marketkit:copy for wording only
  • Not enough traffic → /marketkit:seo, then /marketkit:content-plan
  • Traffic but no leads → /marketkit:funnel
  • Pitching a client → /marketkit:audit, then /marketkit:report-pdf, then /marketkit:proposal

How they chain

These skills read each other's output from the active audit folder's exact same-scope filenames when present, so order matters:

  • /marketkit:audit — incorporates MARKETKIT - COMPETITOR-REPORT - <domain>.md and MARKETKIT - BRAND-VOICE - <domain>.md if they exist
  • /marketkit:copy — sharper after /marketkit:brand
  • /marketkit:emails — uses /marketkit:funnel findings
  • /marketkit:content-plan — consumes /marketkit:brand, /marketkit:competitors, /marketkit:seo; offers to run them if missing
  • /marketkit:report and /marketkit:report-pdf — compile everything available

None of them search an older audit folder automatically — a prior day's run must be named explicitly.

Grounding and business context

Every command starts by looking for a _grounding/ folder in the working directory or its parents. One customer project keeps one shared _grounding/. If one exists, the client's own positioning, target industries, competitor set and claim rules override the suite's defaults, and each output names the files it loaded. See ${CLAUDE_PLUGIN_ROOT}/references/grounding.md.

Each command then resolves the business type and loads exactly one example pack — consumer-online or b2b-technical — so hooks, CTAs, objections and launch plans match how the business actually sells. See ${CLAUDE_PLUGIN_ROOT}/references/business-context.md. When the type is unclear, no pack is loaded and examples are derived from the site's own copy.

Report metadata

Optional attribution reads from config/reporting.config.json at the Git project root; a legacy root-level reporting.config.json still works but warns to move. See ${CLAUDE_PLUGIN_ROOT}/references/output-location.md.

Requirements

Python 3 for the bundled scripts (analyze_page.py, competitor_scanner.py, social_calendar.py, generate_pdf_report.py) — stdlib only, no install needed. /marketkit:report-pdf additionally needs reportlab; competitor_scanner.py optionally uses trafilatura for cleaner content extraction if present, and falls back to its stdlib parser if not:

pip install reportlab
pip install trafilatura   # optional

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.