<Devsly/>
NotebookLM Watermark Remover
Remove the NotebookLM watermark from PDF slide exports — free, unlimited, and 100% in your browser.
View
NotebookLM Video Watermark Remover
Remove the NotebookLM watermark from every frame of your MP4 and auto-trim the end card — free and unlimited.
View
Gemini Watermark Remover
Remove the Gemini (Veo) sparkle watermark from every frame of your AI-generated MP4 — free and unlimited.
View
MCP https://devsly.io/mcp MCP Tools Best Skills API Docs

Keyboard Shortcuts

Navigation

Quick Search
⌘ / Ctrl + K
Toggle Dark Mode
⌘ / Ctrl + D
Close Dialogs
Esc

Tool Actions

Execute / Process
⌘ / Ctrl + Enter
Clear Input
⌘ / Ctrl + Shift + C
Copy Output
⌘ / Ctrl + Shift + X

Editor

Select All
⌘ / Ctrl + A
Undo
⌘ / Ctrl + Z
Redo
⌘ / Ctrl + Shift + Z

Updated 1w ago

by spirosbax

insaight

LinkedIn prospect intelligence inside Claude — MCP server + 8 skills that research people, companies and comment threads, draft outreach, and learn what gets replies.

  • Active — Updated in the last 14 days
Works with
  • Claude

32 GitHub stars (32)

Steady at 32 stars — no new stars in the 16 days since Sep 30.

  • 8 skills (8 skills found in its SKILL.md files)
  • 3 forks (3 forks)
  • 1w ago last update (Last updated 1w ago)

Install

Skills CLI

npx skills add spirosbax/insaight

Asks which skills and agents to install. Just one: npx skills add spirosbax/insaight --skill draft-outreach — add -g for every project.

Claude Code

git clone https://github.com/spirosbax/insaightcp -r "insaight/skills/draft-outreach" ~/.claude/skills/

Copies the draft-outreach skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.

Plugin

/plugin marketplace add spirosbax/insaight

Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.

Skills can run code on your machine — read the SKILL.md first.

What it does

In the author's own words, from each skill's SKILL.md.

  • draft-outreach

    Draft a personalized cold LinkedIn DM or email from three inputs: the intelligence in a prior Insaight research brief, the learned style memory (insaight:get_memory — the user's distilled voice plus the playbook of what actually earns replies), and a prior-contact check against the outreach ledger (insaight:list_outreach) so nobody gets cold-opened twice. Returns two angles (warm/story-led and di…

    skills/draft-outreach/SKILL.md on GitHub (opens in a new tab)
  • draft-post

    Draft a LinkedIn post for the user's own company page, in that company's own voice, plus an optional visual brief. Reads COMPANY_NAME and COMPANY_LINKEDIN from insaight:get_config, loads the company's real past posts through the Insaight MCP, extracts their hook, structure, length, emoji, hashtag and language patterns, then writes two variants against that reference. If the user pastes a link, fe…

    skills/draft-post/SKILL.md on GitHub (opens in a new tab)
  • reflect

    Run a reflection over the Insaight outreach ledger: analyze recent sends and their outcomes, then propose evidence-backed updates to the two memory files (style.md — the user's voice; playbook.md — the strategies that get replies). Every proposal is shown with the counts and quotes behind it and is applied only on approval, never silently. Trigger this whenever insaight:record_outcome returns ref…

    skills/reflect/SKILL.md on GitHub (opens in a new tab)
  • research-company

    Build a structured intelligence brief on a company from its LinkedIn page posts plus the personal posts of up to three of its executives, using the Insaight MCP server, then score it as a prospect on fit, pain signals and decision-maker visibility. Covers where the company came from, what it is shipping and hiring for now, and where it is heading. Use this skill whenever the user points at a comp…

    skills/research-company/SKILL.md on GitHub (opens in a new tab)
  • research-person

    Build a structured intelligence brief on one person from their LinkedIn posts and their full profile — experience, education, skills, languages, volunteer work — using the Insaight MCP server. Covers role and career trajectory, content themes, decision-maker signals, outreach hooks, and uncommon commonalities to open a cold message with. Use this skill whenever the user points at a named individu…

    skills/research-person/SKILL.md on GitHub (opens in a new tab)
  • research-post

    Mine a LinkedIn post AND its comment thread for leads, using the Insaight MCP connector: who engaged, what they said, recurring themes, buying signals, decision-makers hiding in the replies, competitor and vendor mentions, and ranked warm leads with the hook each one hands you. Use this whenever a LinkedIn post URL appears and the user is curious about the reaction to it — 'research this post', '…

    skills/research-post/SKILL.md on GitHub (opens in a new tab)
  • save-notion

    Persist an Insaight research brief (person, company, or post) to Notion as a structured page under the research parent page named by insaight:get_config, updating the existing page for that subject instead of creating a duplicate. This skill is mostly NOT triggered by the user directly — the research skills (research-person, research-company, research-post) invoke it automatically as their last s…

    skills/save-notion/SKILL.md on GitHub (opens in a new tab)
  • track-outreach

    Record outreach sends and their outcomes in the local Insaight ledger using insaight:log_outreach and insaight:record_outcome. Trigger this skill whenever the user mentions — even in passing, as a throwaway aside mid-conversation — that a message went out or that a prospect responded or went quiet; these remarks are almost never phrased as requests, so act on them proactively instead of waiting t…

    skills/track-outreach/SKILL.md on GitHub (opens in a new tab)

Review before you install

A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.