Agent skill

Competitor Research

by openlegion-ai in openlegion-ai/openlegion

Research a competitor across the web and produce a cited, structured brief.

MITAuto-check passedAgent Workflows

Install Competitor Research

skills CLI
$ npx skills add openlegion-ai/openlegion --skill competitor-research -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install openlegion-ai/openlegion competitor-research --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/openlegion-ai/openlegion.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/competitor-research .claude/skills/competitor-research && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
competitor-research
GitHub stars
124
Token cost
~395 tokens
SKILL.md length
204 words
Files
3 (incl. scripts, references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Research a competitor across the web and produce a cited, structured brief.

  • Works in 5 steps: Establish the basics: official site,… → Gather 5–10 distinct sources. Prefer… → Cross-check anything surprising against… → …
  • Tasks that involve Competitor analysis
  • Runs Python scripts from its folder; calls python

What it does

Competitor Research is an agent skill from openlegion-ai/openlegion. Research a competitor across the web and produce a cited, structured brief.

Its SKILL.md is about 400 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts and reference files (for example `references/brief-template.md` and `scripts/dedupe_sources.py`).

It sits in Agent Workflows, covering Competitor analysis. It works with Docker and Model Context Protocol. The repository describes itself as: Secure autonomous AI agent framework and platform. Build AI teams by describing what you want. Orchestrate agents that can do everything a human can do. The licence is MIT.

When your agent uses it

  • Tasks that involve Competitor analysis

Example prompts

  • “/competitor-research”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Establish the basics: official site, what they sell, who they sell to.
  2. Gather 5–10 distinct sources. Prefer primary sources (the company's own
  3. Cross-check anything surprising against a second source before stating it.
  4. De-duplicate your source URLs before writing — run
  5. Assemble the brief using the structure in

What it can do on your machine

Read from SKILL.md and the folder at commit 24efd6e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Competitor Research loads about 395 tokens when it runs, and up to ~523 if it reads all its reference files. Until then it costs about 24 tokens; SKILL.md has 204 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~24
When it runs · the whole SKILL.md, loaded when a task matches
~395
With references · SKILL.md plus every file in references/, read only if the agent opens them
~523

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from openlegion-ai/openlegion at commit 24efd6e, republished under its MIT licence (© openlegion-ai). 204 words, ~395 tokens.

Download SKILL.mdSave it as .claude/skills/competitor-research/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
competitor-research
description
Research a competitor across the web and produce a cited, structured brief.
version
1.0.0
license
MIT
metadata.requires_toolsets
web_search, http_request

When to Use

Use this skill when asked to "research", "look into", or "produce a brief on" a specific competitor or company. It assumes you already have web_search and http_request; it adds no new capability — only a procedure.

Procedure

  1. Establish the basics: official site, what they sell, who they sell to. Run web_search for the company name plus "pricing", "product", "funding".
  2. Gather 5–10 distinct sources. Prefer primary sources (the company's own pages, filings, docs) over secondary commentary. Record the URL for each claim as you go — every fact in the brief must be traceable.
  3. Cross-check anything surprising against a second source before stating it. If two sources conflict, say so in the brief rather than picking one.
  4. De-duplicate your source URLs before writing — run python ${SKILL_DIR}/scripts/dedupe_sources.py url1 url2 ...; it prints the unique set so you don't cite the same page twice.
  5. Assemble the brief using the structure in references/brief-template.md (read it with skill_view if unsure).

Pitfalls / Verification

  • Do not state pricing, headcount, or funding numbers without a dated source.
  • Marketing copy is not a source for capability claims — verify in docs.
  • Before reporting done, confirm every section of the template is filled and every non-obvious claim has a citation.

© openlegion-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts, references) in skills/competitor-research of openlegion-ai/openlegion.

  • SKILL.md
  • references/brief-template.md
  • scripts/dedupe_sources.py

Open the folder on GitHubat commit 24efd6e

Compare with similar skills

Competitor Research next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Competitor Research compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Competitor Research this skillopenlegion-ai/openlegion124—~395Automated safety check: PassMIT
Codebase Managementgiancarloerra/SocratiCode3.3k1 repos~1.8kAutomated safety check: PassAGPL-3.0
MCP Setupayuayue/PiDeck1k—~650Automated safety check: PassMIT
Project Releaseswimmwatch/cloakbrowser-mcp164—~1.9kAutomated safety check: PassMIT
MCP Builderjezweb/claude-skills1.1k—~3.1kAutomated safety check: NotesMIT
Setup Xhs MCPautoclaw-cc/xiaohongshu-mcp-skills272—~678Automated safety check: PassMIT

Similar skills

  • Codebase Management

    giancarloerra/SocratiCode

    Set up, index, and manage SocratiCode codebase indexing. An agent skill from giancarloerra/SocratiCode.

    3.3k GitHub starsUsed in 1 repo~1.8k tokens
    AI & LLM EngineeringAuto-check passed
  • MCP Setup

    ayuayue/PiDeck

    帮用户接入/配置 MCP(Model Context Protocol)服务。当用户说「帮我接 MCP」「连上某个服务的 MCP」「配置 Model Context Protocol」「加个工具服务器」「为什么 MCP 连不上」等时使用。按服务官方文档把配置写进 pi 的 mcp.json,并用 pi mcp list 验证连接,全程不破坏用户已有配置。

    1k GitHub stars~650 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Project Release

    swimmwatch/cloakbrowser-mcp

    Prepare, publish, verify, or recover a cloakbrowser-mcp release only when the user explicitly requests release work.

    164 GitHub stars~1.9k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • MCP Builder

    jezweb/claude-skills

    Build MCP servers in Python with FastMCP. An agent skill from jezweb/claude-skills.

    1.1k GitHub stars~3.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes
  • Setup Xhs MCP

    autoclaw-cc/xiaohongshu-mcp-skills

    安装部署 xiaohongshu-mcp 服务并配置 MCP 连接,引导用户完成从零到可用的全流程. An agent skill from autoclaw-cc/xiaohongshu-mcp-skills.

    272 GitHub stars~678 tokensUpdated 7 mo ago
    Agent WorkflowsAuto-check passed
  • Devcontainer Dev

    stacklok/toolhive-studio

    Spin up and interact with ToolHive Studio's containerized dev environment (Xvfb + noVNC + DinD).

    171 GitHub stars~3.8k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes

Questions about Competitor Research

What does Competitor Research do?

Research a competitor across the web and produce a cited, structured brief. Competitor Research is an agent skill from openlegion-ai/openlegion. Research a competitor across the web and produce a cited, structured brief.

When should I use Competitor Research?

Competitor Research fits situations like: tasks that involve Competitor analysis.

How do I install Competitor Research in Claude Code?

Run `npx skills add openlegion-ai/openlegion --skill competitor-research -a claude-code`. Or copy the skill folder (skills/competitor-research in openlegion-ai/openlegion) into .claude/skills/competitor-research in your project. Claude Code loads it when a task matches its description.

How do I install Competitor Research in Codex?

Run `npx skills add openlegion-ai/openlegion --skill competitor-research -a codex`. Or copy the skill folder (skills/competitor-research in openlegion-ai/openlegion) into .agents/skills/competitor-research in your project. Codex loads it when a task matches its description.

Can I use Competitor Research in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openlegion-ai/openlegion --skill competitor-research -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/competitor-research, .gemini/skills/competitor-research, .github/skills/competitor-research and .opencode/skills/competitor-research in your project.

What does Competitor Research need to run?

Going by SKILL.md and its folder, Competitor Research needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Competitor Research access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Competitor Research safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Competitor Research use?

Competitor Research is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Competitor Research use?

About 395 tokens (SKILL.md is roughly 1.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 128 tokens, read only when the agent opens those files.

What are the alternatives to Competitor Research?

Skills that share tags, products or a category with Competitor Research: Codebase Management (giancarloerra/SocratiCode, 3.3k stars), MCP Setup (ayuayue/PiDeck, 1k stars), Project Release (swimmwatch/cloakbrowser-mcp, 164 stars) and MCP Builder (jezweb/claude-skills, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Competitor Research?

openlegion-ai (a GitHub organization) maintains it in openlegion-ai/openlegion, which has 124 GitHub stars. The repository was last updated on August 23, 2026.

Source: openlegion-ai/openlegion on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.