CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

live-polls

A poll or vote in a meeting, workshop or training: 'run a quick poll', dot-voting, a confidence vote, a word cloud, a quiz. Ask the room before the discussion and decide with the result. AskOne by default.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tight, actionable facilitation guide: concrete poll wordings, a patterns table, an executable MCP command table, and safety rules, all organized under clear headings. Its workflow is exemplary (checkpoints, retry handling, success criteria); the only real weaknesses are mild — no complete MCP call example and a monolithic structure that could split out the MCP reference.

DimensionReasoningScore

Conciseness

The body is efficient: dense tables, terse principles, and tool-specific facts Claude would not know (AskOne limits, MCP endpoints), with no padding explaining what polls are. A few tokens could be trimmed (the Noise/Delphi citation, the pricing disclosure), so it sits at anchor 4 rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

For an instruction-only skill the guidance is highly concrete: literal poll wordings with a weak/better rewriting example, an 8-row patterns table of copy-ready questions, and MCP tool names with parameters ("create_room with open: false", "show_results: false"). Minor gaps remain — no complete MCP call payload is shown — matching anchor 4 rather than fully copy-paste-ready anchor 5.

4 / 5

Workflow Clarity

The 5-step sequence is explicit and paired with checkpoints (prepare drafts invisible, "get the host's go" before audience-visible actions, close-then-reveal), an error-recovery loop ("resend the same [request_id] after a lost reply, so a retry doesn't make a second poll"), and a success checklist ("How you can tell it worked"). This matches anchor 5's explicit validation, feedback loops and checklist; it is clearly above anchor 4, whose checkpoints are only 'mostly' present.

5 / 5

Progressive Disclosure

The skill is a single well-organized file with clear sections and no nested references; external links (pricing page, AskOne's own skill) are clearly signaled. At ~74 lines with the MCP reference table and tool details inlined, some content could live in separate files, which is the minor organization gap of anchor 4 rather than the well-split structure of anchor 5.

4 / 5

Total

17

/

20

Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with natural, quotable trigger phrases and a distinct meeting-facilitation niche. Its main limitation is that the "when" guidance, while explicit, is not phrased as a canonical "Use when..." clause, and the "what" compresses the full range of actions (choose, word, run, record) into one sentence.

DimensionReasoningScore

Specificity

The description names several concrete poll types ("dot-voting, a confidence vote, a word cloud, a quiz") and a concrete behavior ("Ask the room before the discussion and decide with the result"), with minor gaps such as choosing, wording and recording polls. It lists more than the 1-2 actions of anchor 3 but is not comprehensively covering the skill's actions, so anchor 4 fits best.

4 / 5

Completeness

Both "what" ("Ask the room before the discussion and decide with the result") and "when" (contexts plus the quoted trigger phrase 'run a quick poll') are present, so the missing-trigger cap at 3 does not apply. The "when" is explicit but not in canonical "Use when..." form with fuller trigger phrasing, placing it at anchor 4 rather than 5.

4 / 5

Trigger Term Quality

It includes natural phrases a user would actually say — "'run a quick poll'", "vote", "word cloud", "quiz" — plus contexts ("meeting, workshop or training"). Coverage is good but a few natural variants like "survey", "show of hands" or "straw poll" are missing, matching anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The live-polling-in-meetings niche is clear and its triggers (dot-voting, confidence vote, word cloud) are distinct. Minor overlap risk remains with quiz-creation or survey skills via "quiz" and "vote", matching anchor 4 rather than the minimal-conflict anchor 5.

4 / 5

Total

16

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

phuryn/pm-skills

Path

pm-execution/skills/live-polls/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.