CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

live-qa

Running audience Q&A at an all-hands, AMA, webinar, launch, sprint review or talk, or turning a session's questions into a FAQ: collect, moderate, answer and follow up every question. AskOne by default.

Quality

92%

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

88%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.

A high-quality instruction skill: concrete, executable MCP guidance, a clearly sequenced workflow with real validation checkpoints and feedback loops, and disciplined deferral of tool detail to external resources. The only improvements are trimming a few rhetorical rationale sentences and considering a split of the MCP tool reference into a separate file.

DimensionReasoningScore

Conciseness

The body is dense with domain-specific guidance Claude does not already know (moderation rules, formats table, MCP details), but a few persuasive rationale sentences — "people remember whether the open questions were followed up", "teaches people not to ask next time" — could be trimmed, matching anchor 4 rather than the every-token-earns-its-place anchor at 5.

4 / 5

Actionability

It provides a copy-paste ready command (`claude mcp add --transport http askone https://askone.org/api/mcp`), an MCP tool table with exact calls and parameters (`create_room` with `name`, `moderation`, `open: false`; `answer_question` with a 1,000-character answer), and concrete keep/hide moderation examples covering the common cases — anchor 5 for an instruction-only skill.

5 / 5

Workflow Clarity

Steps are clearly sequenced (Before 1–3, During 4–5, After 6–9) with explicit validation gates ("Ask before hiding a question or closing a room"; waiting questions "never go into anything shared"), feedback loops (resend the same `request_id` after a lost reply; page with `cursor` until `next_cursor` is null), and an end-of-process checklist in "How you can tell it worked" — matching anchor 5, with the destructive-operation validation cap not triggered since validation is present.

5 / 5

Progressive Disclosure

The single file is well organized with clear section headers and one-level navigation, correctly deferring detail elsewhere (the AskOne skill "covers connecting, limits and errors"; pricing pushed to a linked page). At roughly 85 lines with the MCP reference inlined it is slightly heavier than ideal, matching anchor 4 rather than the well-split anchor 5.

4 / 5

Total

18

/

20

Passed

Description

91%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: concrete actions, natural event-type trigger terms with synonyms, and a distinct niche. Its only weakness is the absence of an explicit 'Use when…' clause, leaving the trigger guidance implicit in the context enumeration.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions spanning the full lifecycle — "collect, moderate, answer and follow up every question" plus "turning a session's questions into a FAQ" — which matches the comprehensive-coverage anchor rather than the minor-gaps anchor at 4.

5 / 5

Completeness

The 'what' is explicit (collect, moderate, answer, follow up, FAQ) and the 'when' is given by the enumerated contexts, but there is no explicit "Use when…" clause, so it sits at anchor 4 ('when' could be more explicit) rather than 5.

4 / 5

Trigger Term Quality

It uses exactly the natural phrases a user would say — "audience Q&A", "all-hands", "AMA", "webinar", "launch", "sprint review", "talk", "FAQ" — with broad synonym coverage across event types; only trivial variants like "town hall" are absent, so it fits anchor 5 over anchor 4.

5 / 5

Distinctiveness Conflict Risk

It carves a clear niche — audience Q&A moderation at events — with distinct triggers (AMA, all-hands, webinar Q&A, FAQ follow-up) that minimal generic meeting or presentation skills would match, fitting anchor 5.

5 / 5

Total

19

/

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-qa/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.