Skip to content
Agentmart
Submit a tool

social-search

Collect what people say across public communities and the web in parallel, then return one independently written, cited brief.

Skill by DanMcInerney

IndexedMIT★ 124
Write a review

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/danmcinerney-social-search

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

Collect what people say across public communities and the web in parallel, then return one independently written, cited brief.

Reviews

Write a review

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/social-search

What's inside

Skill name
social-search
Description
Collect what people say across public communities and the web in parallel, then return one independently written, cited brief.
License
MIT
Instructions
13 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

Establish [library context](../../references/library-context.md).

Split the caller's sources into a few collection assignments that can run at once. Keep sources that share discussions together, and give each original that several sources discuss one owner. Reuse supplied evidence that already covers part of the scope. Divide the caller's bounds, keeping time for the final review.

Launch every assignment through `orchflows:orch-work` before gathering any. Give each collector the question, window, sources, bounds, its own directory for `results.md`, and the paths of the [evidence contract](../../references/evidence.md), [public access](../../references/access.md) and its collection guidance.

At the handoff deadline, stop unfinished collectors. Record missing or failed assignments as gaps, and keep useful partial evidence.

Use `orchflows:orch-review` once. The assessor collected nothing. Give it the question, the caller's output requirements, every handoff and gap, the evidence contract and the assessment guidance. It checks claims against the saved support and writes the cited brief from that evidence alone, to the caller's requirements. The brief is about the topic: its gaps name what it could not cover, not how the research ran.

Return the assessor's brief unchanged, with its coverage and gaps.

From DanMcInerney/orchflows, MIT.

More from DanMcInerney/orchflows

Signals

Stars
124
Forks
10
Open issues
0
Last commit (this folder)
Sep 23, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/DanMcInerney/orchflows
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from DanMcInerney

Cite this page

social-search skill. Agent Mart. https://agentmart.dev/skills/danmcinerney-social-search (last updated 2026-10-24)