AugmentClaude

Research Process Builder

Build and validate web research workflows through iterative testing and refinement.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.

    This copies the whole skill folder into ~/.claude/skills/research-process-builder-leadgrowgtm/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Build validated web research processes through self-annealing loops. Takes a research goal, generates search steps, tests against sample companies, scores accuracy, and iterates until 90%+. Use when creating new research workflows, building claygent/agent prompts, or systematizing any web research task.

What this skill does

Research Process Builder

Factory that produces validated, step-by-step web research processes through iterative testing. Takes any research goal, generates search patterns, tests against real companies, scores accuracy, and loops until 90%+ reliability.

Output: portable .md process files any agent (Claude Code, Clay, custom GPT, browser agent) can follow.

When To Use

  • Building a new research workflow for any topic (company intel, market sizing, hiring signals, tech stack detection)
  • Creating claygent or web research agent prompts that need to work reliably
  • Systematizing any manual web research you do repeatedly

When NOT To Use

  • Running an existing research process (load the process .md directly)
  • One-off research where you just need the answer
  • Data enrichment at scale (use a dedicated enrichment tool)

Interactive Flow

@references/interactive-flow.md

Example Processes

ProcessFileStepsAccuracy
Find competitorsprocesses/find-competitors.md793%
Find reviewsprocesses/find-reviews.md695%
Find recent newsprocesses/find-news.md790%
Find PR/releasesprocesses/find-pr-releases.md590%
Find third-party profilesprocesses/find-profiles.md6100%
Find hiring activityprocesses/find-hiring.md593%
Find job role insightsprocesses/find-job-role-insights.md590%
Find growth signalsprocesses/find-growth-signals.md793%
Find customer negativityprocesses/find-negativity.md690%

Build Methodology

@references/build-loop.md

Accumulated Learnings

@references/learnings.md

Related skills