helpin-ai/agent-runtime/competitive-intelligence-digest
Claude Code and agent skill by helpin-ai/agent-runtime
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Researches recent competitor product updates and creates a concise marketing digest task.
Install
npx vskill@latest install helpin-ai/agent-runtime/competitive-intelligence-digestSKILL.md
- Use
update_planfirst and keep it current as you research, synthesize, and create the task. - Follow any configured target company, target domain, competitor list, lookback window, and task destination in the agent's own instructions. Treat those values as already resolved and authoritative.
- Do not plan or perform a step to discover configuration variables, workspace context, teams, stages, cadence, or lookback settings. Use the configured values directly.
- Use configured competitors when provided. If competitors are configured, do not discover additional competitors. If no competitors are configured, discover competitors with
web_search; do not invent competitors without sources. - Use
web_searchto understand the target company and find official competitor changelogs, release notes, product-update pages, product blogs, help-center "What's New" sections, and public roadmap tools. - Use
fetch_urlon each exact source URL before citing it. Do not cite a search result unless the fetched page content supports the claim. - If search results are thin or a competitor's update page is likely under a docs/blog subdomain, use
crawl_urlon the official site or docs host with changelog/update keywords before markingno_public_changelog. - For each competitor, extract notable changes shipped within the configured lookback window. Convert all relative dates to absolute
YYYY-MM-DDdates. - Skip routine bug fixes and cosmetic tweaks unless they are strategically notable. Mark thin or contradictory evidence as
low_confidenceinstead of guessing. - Write a markdown brief under 500 words with TL;DR, themes, per-competitor highlights, and threats/opportunities for the target company. Cite a source URL for every claim.
- Create exactly one task with
create_task. Pass the configured destination team directly asteam_id; include the configured destination state directly asstate_idonly when it is present. Do not call team or workflow listing tools to resolve these IDs first. - Use task type
chore. Set priorityhighif any competitor shipped something directly overlapping the target's core positioning,mediumfor notable changes, andlowif no notable changes were found. - Include acceptance criteria in the task description because
create_taskdoes not accept a separate acceptance-criteria field. - Include an appendix in the task description listing every competitor considered and any
no_public_changelogorlow_confidencefindings. - After
create_taskreturns, include the created task ID or ref in the final response.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckinginternal/skills/system/competitive_intelligence_digest/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/helpin-ai/agent-runtime/competitive-intelligence-digest)