{"slug": "compete-a-claude-code-plugin-for-interactive-competitor-intelligence", "title": "Compete – A Claude Code plugin for interactive competitor intelligence", "summary": "Forthright Tech released Compete, a Claude Code plugin that automatically generates competitive intelligence reports from any software repository. The tool analyzes code, manifests, and README files to identify a product, then builds a multi-dimensional database covering competitors' product, technology, business, marketing, SEO, social media, customers, sales, hiring, funding, and brand positioning. It outputs a self-contained interactive HTML report with dashboards, comparison matrices, and prioritized recommendations, aiming to streamline competitive analysis for developers.", "body_md": "A Claude Code Skill that turns your repository into a complete competitive intelligence report.\n\n`compete`\n\nanalyzes the current repository to identify your product, then\ndiscovers competitors and builds a complete competitive intelligence database\nspanning product, technology, business, marketing, SEO, social media, customers,\nsales, hiring, funding, and brand positioning. It is an AI product research\nassistant — not just a comparison generator.\n\nEverything is collected into normalized, **confidence-annotated** JSON datasets\nand rendered into a self-contained interactive HTML report (the **InsightKit**\nreport) with dashboards, comparison matrices, capability radars, pricing\nladders, a positioning scatter, SWOT accordions, and prioritized\nrecommendations.\n\n**Repo-aware**— reads your code, manifests, and README to identify the product before searching the web. No manual product brief required.**Multi-dimensional intelligence**— company profile, pricing, tech stack, social presence, marketing, and SEO for every competitor.** Confidence everywhere**— every field is wrapped with a confidence score, source, provenance, and an explicit`unknown`\n\nfallback. Nothing is asserted without showing its work. Verify before acting.**Normalized data contract**— all stages write JSON validated against the schemas in, joined by`skills/compete/schemas/`\n\n`entity_ref`\n\n. Visualizations consume the data, never scrape directly.**Self-contained report**— one`report.html`\n\nfile (~570 KB) opens standalone in any browser. The only external dependencies are the Chart.js and D3 CDN bundles.\n\nA walkthrough of the seven tabbed views in a generated **InsightKit** report\n(this repository analyzed against its own competitive landscape):\n\n`compete`\n\nis packaged as a **Claude Code plugin**. The plugin bundles\nthree things that work together:\n\n- the\n(`compete`\n\nskill`skills/compete/`\n\n) — the workflow, scripts, schemas, and report template; - the\n(`/compete`\n\nslash command`commands/compete.md`\n\n) — a one-shot entry point that drives the whole pipeline; - the plugin manifest (\n`.claude-plugin/plugin.json`\n\n).\n\n```\n/plugin marketplace add forthrighttech/compete\n/plugin install compete\n```\n\nThe first command registers this repository as a plugin marketplace (it ships a\n[ .claude-plugin/marketplace.json](/lbj96347/compete/blob/main/.claude-plugin/marketplace.json)); the second\ninstalls the plugin. Restart or start a new session and confirm with\n\n`/plugin`\n\n— `compete`\n\nshould be listed as enabled, the `/compete`\n\ncommand\navailable, and the `compete`\n\nskill discoverable via `/skills`\n\n.\n\n```\ngit clone https://github.com/forthrighttech/compete.git \\\n  ~/.claude/plugins/compete\n```\n\nThe plugin must live at a directory whose root contains\n`.claude-plugin/plugin.json`\n\n(with `skills/`\n\nand `commands/`\n\nalongside it).\nClaude Code discovers it on the next session.\n\nIf you only want the skill without the slash command, clone just the skill subtree into your skills folder:\n\n```\n# Personal (all projects)\ngit clone https://github.com/forthrighttech/compete.git /tmp/compete && \\\n  cp -r /tmp/compete/skills/compete ~/.claude/skills/compete\n\n# Project-scoped (one repository)\ncp -r /tmp/compete/skills/compete \\\n  /path/to/your-repo/.claude/skills/compete\n```\n\nThe skill must live at `.../.claude/skills/compete/`\n\nwith `SKILL.md`\n\nat\nits root. Confirm with `/skills`\n\n(it should appear as `compete`\n\n). You\ntrigger it in natural language rather than with `/compete`\n\n.\n\n**Claude Code** with web access (`WebSearch`\n\n/`WebFetch`\n\n) for competitor discovery and intelligence collection.**Python 3.9+** for the helper scripts in. The collection and rendering scripts use only the standard library — no`skills/compete/scripts/`\n\n`pip install`\n\nrequired.\n\nOpen Claude Code in the repository you want analyzed and run:\n\n```\n/compete\n```\n\nWith no argument, Stage 1 **auto-detects** the product from the current repo and\nthe command runs the full pipeline end to end, writing the report to\n`./insightkit-output/`\n\n.\n\nYou can also pass an **optional seed** — a competitor URL or name:\n\n```\n/compete https://www.crayon.co\n/compete Klue\n```\n\nA seed is folded into Discovery as a known competitor candidate and is used to\nanchor the product's market/category, instead of relying solely on\nauto-detection. The seed is slugified into an `entity_ref`\n\n(e.g. `crayon`\n\n),\nclassified, and appears in the roster alongside the auto-discovered competitors.\n\nIf you installed the skill without the command — or just prefer plain language — ask Claude directly. The skill triggers on phrases such as:\n\n\"Find my competitors\" \"Run a competitive analysis on this repo\" \"Who are my competitors and how do I compare?\" \"Build me a competitive landscape / positioning matrix / SWOT\"\n\nClaude runs the pipeline end to end. You can also drive any stage yourself:\n\n```\n# 1. Product Intelligence — analyze the repo, write product.json\npython skills/compete/scripts/analyze_repo.py --repo . --validate\n\n# 2. Competitor Discovery — plan searches, then normalize results\npython skills/compete/scripts/discover_competitors.py plan  --product product.json\n#    (Claude runs the plan with WebSearch/WebFetch → candidates.json)\npython skills/compete/scripts/discover_competitors.py build --product product.json \\\n  --candidates candidates.json --validate\n\n# 3. Intelligence Collection — per-competitor company/pricing/tech/social/marketing/SEO\npython skills/compete/scripts/collect_intelligence.py plan  --competitors competitors.json\n#    (Claude runs the plan with WebSearch/WebFetch → findings.json)\npython skills/compete/scripts/collect_intelligence.py build --competitors competitors.json \\\n  --findings findings.json --validate\n\n# 4 + 5. Knowledge Graph + Visualization — synthesize report.json and render report.html\npython skills/compete/scripts/build_report.py --input-dir . --output-dir ./insightkit-output\n#    add --open to also launch the report in a browser\n```\n\nOpen the result:\n\n```\nopen ./insightkit-output/report.html\n```\n\nA fully rendered example ships in [ insightkit-output/](/lbj96347/compete/blob/main/insightkit-output) so\nyou can see the report without running the pipeline:\n\n| File | What it is |\n|---|---|\n`report.html` |\n\n`report.json`\n\n`screenshots/overview.png`\n\nThe sample analyzes this very repository (`compete`\n\n) against **17\ndiscovered competitors**, classifying each by type and competitive threat. The\nreport has seven tabbed views:\n\n**Overview**— stat cards, competitor-classification and threat-distribution doughnuts, and the executive summary.** Comparison**— sortable matrix with confidence-bar cells per dimension.** Radar**— six transparent 0–100 capability axes, self vs. competitors, toggleable series.** Pricing**— entry-price bar chart plus a plan-ladder table.** Positioning**— D3 scatter of price × scale, bubble size = similarity, color = threat.** SWOT**— expandable strengths/weaknesses/opportunities/threats per competitor.** Opportunities**— market gaps and prioritized recommendations.\n\nEvery judgment in the report carries a `method`\n\nnote explaining the heuristic\nbehind it.\n\n```\nrepo ──▶ analyze_repo.py ──▶ product.json\n                                 │\n                                 ▼\n        discover_competitors.py ──▶ competitors.json\n                                 │\n                                 ▼\n        collect_intelligence.py ──▶ companies/pricing/techstack/\n                                 │   social/marketing/seo.json\n                                 ▼\n            build_report.py ──▶ report.json ──▶ report.html\n```\n\nThe normalized JSON datasets are the contract between stages. Each is validated\nagainst a schema in [ skills/compete/schemas/](/lbj96347/compete/blob/main/skills/compete/schemas); the rules (confidence-wrapped\nfields,\n\n`unknown`\n\nfallback, `entity_ref`\n\njoins) are documented in\n[.](/lbj96347/compete/blob/main/skills/compete/references/data-schema.md)\n\n`skills/compete/references/data-schema.md`\n\n| Path | Purpose |\n|---|---|\n`.claude-plugin/plugin.json` |\n\n`.claude-plugin/marketplace.json`\n\n`/plugin install`\n\n.`commands/compete.md`\n\n`/compete`\n\nslash command (optional seed argument).`skills/compete/SKILL.md`\n\n`PRD.md`\n\n`skills/compete/references/`\n\n`skills/compete/scripts/`\n\n`skills/compete/templates/`\n\n`report.html`\n\ntemplate.`skills/compete/schemas/`\n\n`insightkit-output/`\n\n`compete`\n\nv1 ships the full **one-shot** pipeline: product\nintelligence → discovery → multi-dimensional collection → knowledge graph →\ninteractive report. The following are deliberately deferred to **v2**.\n\nv1 collects a solid breadth-first profile across all dimensions. v2 goes deep:\n\n**Deep SEO**— keyword universe and rankings, backlink graph and authority, content gap analysis, SERP-feature ownership, and traffic-trend estimates (beyond v1's meta/structure snapshot).**Deep social**— engagement-rate and follower-growth time series, share-of- voice, sentiment, and channel-mix breakdowns per competitor.**Hiring intelligence**— open-roles tracking, team-growth and org-shape signals, and the strategic bets implied by what each competitor is hiring for.**Sales intelligence**— go-to-market motion (PLG vs. sales-led), funnel and packaging signals, win/loss themes, and target-segment inference.\n\nv1 produces a point-in-time report. v2 adds a monitoring mode that re-runs the\npipeline on a schedule and surfaces **diffs** — turning InsightKit from a\none-time report generator into a continuous competitive-intelligence platform.\nDaily or weekly it would track:\n\n- pricing changes\n- new features\n- new blog posts\n- hiring trends\n- GitHub releases\n- social-media activity\n- funding news\n- SEO changes\n\nSee [ PRD.md](/lbj96347/compete/blob/main/PRD.md) for the complete v1 research scope and the v2 vision.\n\nContributions are welcome — see [ CONTRIBUTING.md](/lbj96347/compete/blob/main/CONTRIBUTING.md) for the\ndata-contract rules, schema-validation workflow, and how to regenerate the\nsample report.\n\n`compete`\n\nis an open-source project built by [forthrighttech](https://x.com/lbjhkg),\ndeveloped with the help of a few products I build:\n\n— private AI that runs local LLMs on your machine.[tokkong](http://tokkong.forthrighttech.com)— an AI keyboard with on-device, local transcription.[whiskey](https://whiskey.asktobuild.app)— a macOS menu bar manager, with support for macOS 27.[lounge](https://lounge.asktobuild.app)\n\nFind me on X: [@lbjhkg](https://x.com/lbjhkg).\n\n[MIT](/lbj96347/compete/blob/main/LICENSE) © 2026 forthrighttech", "url": "https://wpnews.pro/news/compete-a-claude-code-plugin-for-interactive-competitor-intelligence", "canonical_source": "https://github.com/lbj96347/compete", "published_at": "2026-06-28 13:31:24+00:00", "updated_at": "2026-06-28 14:04:52.732145+00:00", "lang": "en", "topics": ["ai-tools", "developer-tools", "ai-agents"], "entities": ["Forthright Tech", "Claude Code", "Compete", "InsightKit", "Chart.js", "D3"], "alternates": {"html": "https://wpnews.pro/news/compete-a-claude-code-plugin-for-interactive-competitor-intelligence", "markdown": "https://wpnews.pro/news/compete-a-claude-code-plugin-for-interactive-competitor-intelligence.md", "text": "https://wpnews.pro/news/compete-a-claude-code-plugin-for-interactive-competitor-intelligence.txt", "jsonld": "https://wpnews.pro/news/compete-a-claude-code-plugin-for-interactive-competitor-intelligence.jsonld"}}