code-kit
claudePlan → Confirm → Implement → Verify discipline for software work: hooks, skills, review agents and a CLAUDE.md ruleset.
40 skills · 6 agents · hooks
Research → Position → Create → Gate → Measure for marketing your own product: a MARKETING_MAP.md evidence file, hooks that block unsourced social proof and gate publishing, skills and review agents.
Plugin marketing-kit from marketplace tansuasici in tansuasici/claude-plugins. Commands read from the repo's manifest — 2 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
briefFill MARKETING_MAP.md (Product, Audience, Positioning, Voice) one section at a time, from the repo first and then short questions to the user. Use when the map is still the template or the user asks to (re)write the brief.
campaign-reportWrite one results report for one launch or campaign, with what went out against the plan, every number with its source, read date and time window, the change from baseline and target, what the data can't show and what changes next time, then add the lines the user approves to MARKETING_MAP.md → Lear
claim-auditCheck every claim in a draft against MARKETING_MAP.md → Evidence, mark the unbacked ones [NEEDS PROOF], flag overstatements and the claims that need approval, and report each with its sentence and row. Use before calling any copy done.
competitor-briefWrite one internal page on one alternative the buyer uses today (a tool, a script, doing nothing), using only facts you can link, with what it does better, what we do better (each backed by Evidence) and when to recommend it instead. Use before positioning against it or writing a comparison.
email-sequenceWrite one short email sequence for one trigger (a signup, an install, a launch list) from MARKETING_MAP.md and Evidence, with one idea and one next step per email, three subject lines each, a send time, an exit condition and [NEEDS PROOF] on every unbacked claim. Drafts only; never sends or loads an
landing-copyWrite or revise the copy for one landing page from MARKETING_MAP.md (Positioning, Evidence, Customer language), section by section, with three hero options, labelled slots for assets and [NEEDS PROOF] on every unbacked claim. Use when the user asks for a landing page, homepage or product page.
launch-planWrite one launch plan for one real release or product, in one file, with a readiness check run against the product, the one idea and its proof, a table of pieces (channel, format, skill, time, status), a go/no-go line, and what to measure. No reach forecasts and no vote-gathering. Plans only; never
positioningTest the Positioning in MARKETING_MAP.md against what changed since it was written (changelog, user feedback, Learnings), propose a sharper or new position next to the old one with its evidence, and after approval update the map, log it in Changes and list the drafts that carry the old line. Use whe
repurposeRewrite one idea from an existing draft, changelog entry, README section or page for other channels, one draft per channel, with the opening and format picked again, the same claims and Evidence rows, [NEEDS PROOF] marks carried over, no new claims and counted lengths. Rewrites, never truncates. Dra
seo-auditCheck one page for what stops it being found or read in search, covering indexing (status, robots, noindex, canonical, sitemap), title, description, headings, links, image alt text and structured data, plus whether its words match Audience, Category and Customer language. Each check says how it was
slop-auditCheck a draft for hype words, filler, structural tells and sentences a competitor could post unchanged, judge each against MARKETING_MAP.md → Voice, and propose a specific rewrite for every one. Use before calling any copy done.
social-postWrite one post for one channel (X, LinkedIn, Instagram, Facebook, YouTube, TikTok) about one idea, from MARKETING_MAP.md and an Evidence row, with three openings, a format picked on purpose, counted lengths and [NEEDS PROOF] on every unbacked claim. Drafts only; never publishes. Use when the user as
social-publishSend one finished draft through a scheduler connector the user set up, opt-in and per channel, after checking the channel's publish flag, the account, open marks, counted lengths, links and media links, and only after the user says yes to the exact text, channel, account and time. Reads the post bac
video-scriptWrite one video script for one channel (Instagram Reels, YouTube, TikTok) about one idea the product can show, with three openings for the first 1-2 seconds, a scene list of what is shown, said and on screen, subtitle lines, counted words and estimated seconds, and [NEEDS PROOF] on every unbacked cl
voice-of-customerCollect what real users said about the problem and the product from issues, discussions, reviews, support threads and call notes, word for word with source, date and quote permission, grouped by theme in one research file, then add the lines the user picks to MARKETING_MAP.md → Customer language. Ne
brand-voice-reviewerRead one finished draft from a fresh context that didn't write it and report where it breaks MARKETING_MAP.md → Voice, Banned words and the competitor test, quoting each sentence with a proposed rewrite. Read-only. Doesn't check claims or lengths. Use when a draft is finished and needs a read from s
claim-checkerCheck one finished draft from a fresh context that didn't write it, comparing every claim with MARKETING_MAP.md → Evidence and reporting what is unbacked, overstated, stale or waiting on approval, with the sentence and the row for each. Read-only. Doesn't check voice or lengths. Use when a draft is
skeptical-buyerRead one finished draft from a fresh context as the skeptical person in MARKETING_MAP.md → Audience, and report where they'd stop, what they wouldn't believe from what's on the page, which objections go unanswered and whether the next step is clear. Read-only. Names what would answer each gap and wr
"${CLAUDE_PLUGIN_ROOT}"/.claude/hooks/session-start.sh
"${CLAUDE_PLUGIN_ROOT}"/.claude/hooks/prompt-router.sh
"${CLAUDE_PLUGIN_ROOT}"/.claude/hooks/branch-protect.sh
"${CLAUDE_PLUGIN_ROOT}"/.claude/hooks/block-dangerous-commands.sh
"${CLAUDE_PLUGIN_ROOT}"/.claude/hooks/claim-scan.sh
"${CLAUDE_PLUGIN_ROOT}"/.claude/hooks/publish-gate.sh
"${CLAUDE_PLUGIN_ROOT}"/.claude/hooks/slop-scan.sh
"${CLAUDE_PLUGIN_ROOT}"/.claude/hooks/claim-scan.sh
"${CLAUDE_PLUGIN_ROOT}"/.claude/hooks/channel-limits.sh
Plan → Confirm → Implement → Verify discipline for software work: hooks, skills, review agents and a CLAUDE.md ruleset.
40 skills · 6 agents · hooks
Question → Evidence → Draft → Verify → Cite discipline for scholarly writing in LaTeX and BibTeX, with citation enforcement.
23 skills · 5 agents · hooks
Brief → Direction → Build → Audit for interface work: a DESIGN_MAP.md direction file, slop and motion hooks, design skills and review agents.
9 skills · 3 agents · hooks
Ingest → Select → Cut → Compose → Render → QC for editing your own video: an EDIT_MAP.md, read-only source footage, a licence register and checked renders.
hooks
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
AI-supervised issue tracker for coding workflows
1 skill · 1 agent · hooks
MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows
18 skills
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.
2 skills · hooks
GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.
72 skills · 72 commands · 64 agents · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.