Competitive Research Stinger logo

Competitive Research Stinger

Organization
legioncodeinc
competitive-research-stinger

Build competitor workbooks and reports. Use for market mapping, feature gaps, or sales battlecards. Read guides/ for the decision path.

Overview

Publisherlegioncodeinc
Repositoryvibe-coding-tools
Skill namecompetitive-research-stinger
Stars
94
Forks
44
Bundled files
26
LicenseAGPL-3.0-or-later
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 26 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by legioncodeinc on GitHub. Read the source before you install it.

Installation

Install the Competitive Research Stinger AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/legioncodeinc/vibe-coding-tools/tree/main/plugins/growth-and-customer-tools/skills/competitive-research-stinger
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/legioncodeinc/vibe-coding-tools.git /tmp/vibe-coding-tools
mkdir -p .claude/skills
cp -r /tmp/vibe-coding-tools/plugins/growth-and-customer-tools/skills/competitive-research-stinger .claude/skills/competitive-research-stinger
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Competitive Research Stinger in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Competitive Research Stinger on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Competitive Research Stinger is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Competitive Research Stinger

Purpose

Produces two linked deliverables from one research pass: an XLSX competitor-landscape workbook (benchmark row against the subject company, category-organized comparison rows, optional feature-gap-analysis tab) and a brand-matched PDF report (executive summary, computed market-pattern insights, per-category competitor tables, sales battlecards, feature roadmap). The differentiator versus a generic "make me a spreadsheet" pass is that observed claims have source/date evidence, sample statistics are computed from the collected records, and qualitative interpretations are labeled, the PDF is styled with the SUBJECT company's actual, verified brand kit, and the whole pipeline is guarded against four specific, field-verified defects (invisible logo, orphaned blank pages, banned punctuation, an inaccessible chart palette).

When to use

  • Building a competitor comparison spreadsheet or "who else is in this space" workbook
  • A request to research and report on competitors, alternatives, or a market category
  • Turning a bounded web-research question into a dated source/claim ledger with acquisition and passage-support receipts
  • Turning an existing competitor list into a feature-gap analysis ("what should we build to compete")
  • A branded PDF version of competitive research, for internal or sales use
  • Sales battlecards or "how do we win against X" enablement material
  • A follow-up request to add more insight/data/analysis to a competitive deliverable that currently reads as just tables and bullets

When not to use

  • A single company's own SEO, marketing copy, or brand-voice work with no competitive comparison involved, that is a content or brand-voice skill's job, not this one
  • Valuation or calibrated financial forecasting; supplied-input reachable-account scenarios are supported by guide 08, with unmeasured inputs and uncertainty explicit
  • Building the actual product features identified as gaps; this stinger's output is the roadmap and rationale, implementation is the relevant engineering Drone's job

Procedure

  1. Scope. Confirm the subject company, the category boundary, and the deliverable shape (Markdown evidence packet, XLSX only, PDF only, or both) per guides/01-scoping-and-taxonomy.md before any research tool call.
  2. For a bounded web-research evidence packet, load guide 10 and its acquisition worksheet; Markdown-only receipts are supported when requested. For buyer alternatives, reachable-account scenarios, wedge tests or dated refresh, read guides 07-09 and the competitive evidence schema before selecting the research. Keep vendor statements separate from observed proof.
  3. Research. Run the aggregator-first sweep in guides/02-research-sweep.md: fetch the subject's own site first, then 2-3 roundup articles per category, sorting every discovered company by the five-role competitive taxonomy.
  4. When XLSX is requested, build the XLSX per guides/03-building-the-xlsx-workbook.md and references/xlsx-workbook-template.md. Read the base xlsx skill first for the general openpyxl/recalc mechanics this guide builds on top of.
  5. If a PDF is in scope, discover and confirm the correct brand kit, then build per guides/04-building-the-branded-pdf.md and references/pdf-report-outline.md. Read the base pdf skill and, if any chart shows more than one hue at once, the dataviz skill's validator, before writing chart code.
  6. Raise the deliverable from a table to an asset using guides/05-market-insights-and-battlecards.md: compute real statistics, write the market-pattern page in prose, build Fact/Impact/Act battlecards for the closest competitors. Do this by default when the deliverable includes a PDF or when the user asks for insight/analysis, not only when explicitly told the first draft was too plain.
  7. Run the full guides/06-qa-checklist.md before delivery. Every unchecked item needs a fix or a stated reason it does not apply.
  8. Deliver through the actual authorized local-file/media surface with artifact paths and evidence limits. A historical SendUserFile/device example does not establish a tool or authorize a commit, send or publication. Preserve revisions in the authorized output path.

References map

  • guides/10-web-research-to-evidence-ledger.md, references/templates/web-research-receipt.md, examples/web-research-evidence/README.md: load for acquisition provenance, passage support, contradictions and partial-source limits.

  • guides/07-buyer-alternatives-and-wedge.md, guides/08-reachable-market-scenarios.md, guides/09-fact-ledger-and-refresh.md: load for dated outcome-based competitive decisions.

  • references/competitive-evidence-schema.md, references/templates/competitive-evidence.json, scripts/README-competitive-evidence.md: explicit bookkeeping/assumption contract and optional bounded checker.

  • references/research/2026-10-outcome-enhancement/distilled.md: fresh update facts and limitations. This is source-repository research that is not shipped with the plugin, so do not require it; guides 07 to 09 carry its conclusions.

  • references/xlsx-workbook-template.md, load when building or reviewing the XLSX tab structure and column set

  • references/pdf-report-outline.md, load when building or reviewing the PDF's page sequence

  • references/research/distilled-competitive-research.md, load when a procedural claim in a guide needs verification (competitor taxonomy, defect root causes, what raises a deliverable's value)

  • Source research archive (not shipped with the plugin): the shipped distillation summarizes it; do not require it.

Related drones and stingers

  • xlsx (external skill, not bundled in Wasp Nest; use only when actually available): base spreadsheet mechanics (openpyxl, recalc, formula discipline) this stinger's XLSX guide builds on top of; read it first for any formula-bearing tab
  • pdf (external skill, not bundled in Wasp Nest; use only when actually available): base PDF manipulation mechanics; this stinger's PDF guide covers the HTML-to-PDF-via-Playwright construction path specifically, not covered there
  • dataviz (external skill, not bundled in Wasp Nest; use only when actually available): chart form, color, and accessibility method; load its validator before any multi-hue chart in the PDF
  • csv-xlsx-import-export-stinger: a different domain (building an in-product spreadsheet upload/export FEATURE); do not confuse with this stinger, which produces a one-off research deliverable, not application code
  • competitive-research-wasp-drone: the paired Drone; delegate to it for a scoped competitive-research task rather than running this stinger inline mid-conversation on an unrelated Drone's work
  • icp-research-stinger: evidence-backed ideal customer profile from a company domain; its market and customers lanes are useful input to a competitor landscape

Audience document packets

Use library-packets-stinger to turn existing sources into role-specific Markdown, Word, branded PDF and citation packets. Source authoring remains with this skill.

Critical Directive

  • You must read all files and context contained within your skill.
  • In the event your core knowledge does not provide sufficient guidance you must make every attempt to search the internet, related knowledge base documentation files, and other available resources to supplement your knowledge prior to proceeding with your task.
  • Additional related skills can be found here:
    • xlsx (external skill, not bundled in Wasp Nest; use only when actually available): base spreadsheet mechanics this stinger builds on
    • pdf (external skill, not bundled in Wasp Nest; use only when actually available): base PDF mechanics this stinger builds on
    • dataviz (external skill, not bundled in Wasp Nest; use only when actually available): required before authoring any multi-series chart

Ship Gate removed: research-only stinger, produces XLSX and PDF deliverables, never committable application code.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Competitive Research Stinger AI skill do?

Build competitor workbooks and reports. Use for market mapping, feature gaps, or sales battlecards. Read guides/ for the decision path.

Why use Competitive Research Stinger on TypingMind?

Because you install it once and use it with any model. Competitive Research Stinger is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Competitive Research Stinger in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/legioncodeinc/vibe-coding-tools/tree/main/plugins/growth-and-customer-tools/skills/competitive-research-stinger. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Competitive Research Stinger?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Competitive Research Stinger?

As many as you like. As long as a model supports skills, you can use Competitive Research Stinger with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Competitive Research Stinger AI skill free?

Yes. It is published on GitHub by legioncodeinc under the AGPL-3.0-or-later license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇