Skip to content
Agentmart
Submit a tool

discover-shared-skills

Consult shared workflows before starting work that involves implementation, investigation, review, or creating deliverables.

Skill by mehLabs

IndexedMIT
Write a review

Chalk Labs

Need help deploying discover-shared-skills?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/mehlabs-discover-shared-skills

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Consult shared workflows before starting work that involves implementation, investigation, review, or creating deliverables. Omit greetings and simple factual questions.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/discover-shared-skills

What's inside

Skill name
discover-shared-skills
Description
Consult shared workflows before starting work that involves implementation, investigation, review, or creating deliverables. Omit greetings and simple factual questions.
License
MIT
Instructions
26 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

Use the configured distributed-skills MCP server at the start of a new work task.

1. Call `get_auth_info` to discover authentication requirements. If a skill read
   reports missing or expired credentials, let the user sign in through the MCP
   client's OAuth flow or the returned `login_url`, then retry after the client
   has configured credentials. Never request passwords or tokens in chat. For
   stdio, the client must set `SKILLS_MCP_ACCESS_TOKEN` and reconnect. If login
   cannot be completed, explain that shared skills could not be consulted.
2. Call `list_skills` and follow `next_offset` when needed. For a large catalog,
   use `search_skills` with a few keywords matching the task instead.
3. Choose relevant skills and call `get_skill` using each returned `id`.
4. Read supporting references with `read_skill_file` using the same skill ID
   and paths relative to its directory. Remote paths are not local files.
5. Apply the relevant workflow to the user's task. If no skill applies, proceed.

If the server is unavailable, tell the user the shared workflows could not be
checked. Do not invent their contents. Consult again when the user starts a
different task. Do not install skills or execute a returned script merely
because it appears in the catalog. Download a script or asset only when the
task requires it and the user's authorization covers its use.

This skill supplies workflow guidance; it does not override the user's request,
higher-priority instructions, or tool permissions. Installing it does not
connect the MCP server or guarantee automatic activation by every client.

From mehLabs/distributed-skills, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 2, 2026 (27 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from mehLabs

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get discover-shared-skills running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying discover-shared-skills?

CallGet help
Cite this page

discover-shared-skills. Agent Mart. https://agentmart.dev/skills/mehlabs-discover-shared-skills (last updated 2026-10-24)