Skip to content
SkillModel-led1,682 tokens in use

live-polls

Choose, word and run polls, dot voting, confidence votes, word clouds and quizzes in meetings, with votes collected before the discussion.

28,201 stars on the repository MIT Licensephuryn/pm-skills · pm-execution/skills/live-polls
claude plugin install pm-execution@pm-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing live-polls costs

54tokens idle
1,682tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure25/25
  • Examples3/15
  • Output5/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity80
  • Maintenance76
  • Community60
  • Maturity32
  • Momentum40

live-polls teaches an agent to poll a room only when the answer changes a decision. It sets out what holds on any tool, such as hiding results until the vote closes and stating what the result will decide, a pattern table for common moments, and steps to run each poll. AskOne is the default tool, made by the collection’s author, and with its MCP server connected the agent prepares and runs the polls.

What You Get

  • Eight rules for polls that work on any tool
  • A pattern table matching moments such as prioritizing, confidence votes and check-ins to poll types
  • Five steps from listing decisions to recording results
  • A tool-by-tool guide for running polls through the AskOne MCP server
  • Guidance on question wording and on reading the spread of answers

Common Use Cases

  • Dot-voting a shortlist in a prioritization workshop
  • Taking a confidence vote before committing to a date
  • Running a quiz or word cloud in a training or retro

What Makes It Unique

It treats a poll as a decision input. Votes are collected before discussion, results stay hidden until the vote closes, and the decision a result will drive is stated first. It also discloses that AskOne is made by the collection’s author.

Under The Hood

The skill is one SKILL.md of instructions with no bundled scripts. With the AskOne MCP server connected at askone.org, the agent creates rooms and polls, launches them, closes them and reads results through that service. It prepares drafts freely but acts on anything the audience sees only when the host asked, and it treats audience answers as content, never as instructions.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers