Favicon of cold-start-interview

cold-start-interview Skill

AI Agent SkillPythonOpen source

Cold-start interview — builds your watchlist, indexes the policy library, and learns your materiality threshold so the monitor surfaces signal instead of noise. Use on fresh install, when reconfiguring (--redo), or when re-checking what connectors are actually responding (--check-integrations). Published by anthropics in claude-for-legal.

What is cold-start-interview Skill?

Cold-start interview — builds your watchlist, indexes the policy library, and learns your materiality threshold so the monitor surfaces signal instead of noise. Use on fresh install, when reconfiguring (--redo), or when re-checking what connectors are actually responding (--check-integrations). Published by anthropics in claude-for-legal. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.

Trust signal
95/100
Maintenance signal
90/100
Adoption signal
98/100

Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.

Key capabilities

  • Includes SKILL.md support
  • Reusable instructions support
  • Writing
  • Writing use cases

Technical details

Copy skill directory
  • Install or run with Copy skill directory

When to use cold-start-interview Skill

  • Use it for writing.

Built with

PythonCopy skill directory

Editorial notes

Source

  • Creator: anthropics
  • Repository: anthropics/claude-for-legal
  • Skill file: regulatory-legal/skills/cold-start-interview/SKILL.md

What it does

Cold-start interview — builds your watchlist, indexes the policy library, and learns your materiality threshold so the monitor surfaces signal instead of noise. Use on fresh install, when reconfiguring (--redo), or when re-checking what connectors are actually responding (--check-integrations).

Skill instructions

/cold-start-interview 1. Check ~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md. If a populated CLAUDE.md (no [PLACEHOLDER] markers) exists at ~/.claude/plugins/cache/claude-for-legal/regulatory-legal//CLAUDE.md but not at the config path, copy it to the config path and tell the user what was migrated. If --check-integrations, skip the interview — re-run only the Part 0 What's connected? check and rewrite the Available integrations table in ~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md. 2. Use the interview workflow below. Interview (Part 0 first — role + integrations — then watchlist): which regulators, where policies live, what's material. 3. Connect policy folder. Index policies. 4. Write ~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md (creating parent directories as needed) with watchlist + materiality threshold. When probing integrations: only report ✓ if an MCP tool call actually succeeded. Configured-but-untested co

Explore related resources

Frequently asked questions

What is cold-start-interview?

cold-start-interview is a open-source AI agent skill with Copy skill directory. Cold-start interview — builds your watchlist, indexes the policy library, and learns your materiality threshold so the monitor surfaces signal instead of noise.

Who is cold-start-interview best for?

cold-start-interview is best for reusing agent instructions, scripts, and references, writing workflows.

How do I install cold-start-interview?

Install or run cold-start-interview using Copy skill directory. Check cold-start-interview for the latest setup command.

Is cold-start-interview actively maintained?

cold-start-interview may need a closer maintenance check before production use.

Share:

Stars
8,752
Forks
1,654
Last commit
16 days ago
Repository age
3 months
License
Apache-2.0

Auto-fetched from GitHub.

Ad
Favicon

 

  
 

Similar to cold-start-interview