Agent skill

Meeting Coach Leader

by shareAI-lab in shareAI-lab/lab-skills

Coach leaders and managers to prepare, run, and review high-bandwidth meetings that advance real work and decisions.

Apache-2.0Auto-check passedProduct & Project Management

Install Meeting Coach Leader

skills CLI
$ npx skills add shareAI-lab/lab-skills --skill meeting-coach-leader -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install shareAI-lab/lab-skills meeting-coach-leader --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/shareAI-lab/lab-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/team-collaboration/meeting-coach-leader .claude/skills/meeting-coach-leader && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
meeting-coach-leader
GitHub stars
315
Token cost
~2.2k tokens
SKILL.md length
1,207 words
Files
4 (incl. references)
Skills in repo
10
Repo updated
First seen
Licence
Apache-2.0

At a glance

Coach leaders and managers to prepare, run, and review high-bandwidth meetings that advance real work and decisions.

  • Works in 5 steps: the decision or outcome needed; → the employee artifact or pre-read; → the two to five questions that could… → …
  • Meeting retrospectives
  • SKILL.md covers Choose the immediate need, Read the evidence in both…, Define the value of the meeting and Prepare the smallest useful…, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Meeting Coach Leader is an agent skill from shareAI-lab/lab-skills. Coach leaders and managers to prepare, run, and review high-bandwidth meetings that advance real work and decisions. Use for meeting retrospectives, employee work reviews, decision meetings, agenda and question design, direct feedback, meeting-quality diagnosis, or repeated low-value discussions. Preserve direct standards without taking over the worker's work or degrading the truth signal.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/manager-playbook.md` and `references/templates.md`).

It sits in Product & Project Management, covering Retrospectives. The repository describes itself as: Skills distilled from the Lab's real work and collaboration practices. The licence is Apache-2.0.

When your agent uses it

  • Meeting retrospectives
  • Employee work reviews
  • Decision meetings
  • Agenda and question design

Example prompts

  • “/meeting-coach-leader”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. the decision or outcome needed;
  2. the employee artifact or pre-read;
  3. the two to five questions that could change the decision;
  4. known gaps that may block the meeting;
  5. the desired close: decision, correction, owner, or next output.

What it can do on your machine

Read from SKILL.md and the folder at commit becee99. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Meeting Coach Leader loads about 2.2k tokens when it runs, and up to ~3.6k if it reads all its reference files. Until then it costs about 103 tokens; SKILL.md has 1,207 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~103
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from shareAI-lab/lab-skills at commit becee99, republished under its Apache-2.0 licence (© shareAI-lab). 1,207 words, ~2,236 tokens.

Download SKILL.mdSave it as .claude/skills/meeting-coach-leader/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
meeting-coach-leader
description
Coach leaders and managers to prepare, run, and review high-bandwidth meetings that advance real work and decisions. Use for meeting retrospectives, employee work reviews, decision meetings, agenda and question design, direct feedback, meeting-quality diagnosis, or repeated low-value discussions. Preserve direct standards without taking over the worker's work or degrading the truth signal.

Meeting Coach: Leader

Optimize meetings for truth, decisions, learning, and executable work. Do not confuse intensity, duration, or manager airtime with progress.

Choose the immediate need

  • Prepare: decide what the meeting must accomplish, what should be pre-read, and which questions deserve synchronous time.
  • Run: maintain a clear sequence, expose the real gap, make the required decision, and close with ownership.
  • Review employee work: distinguish incomplete work, weak evidence, poor explanation, wrong scope, and unclear original expectations.
  • Debrief recent meetings: find repeated low-bandwidth patterns and change the work or meeting system.
  • Give feedback: be direct and specific without humiliation, vague reassurance, or absorbing the employee's responsibility.

Keep the default answer practical. Read manager-playbook.md for deeper feedback language and anti-patterns. Read templates.md only when a reusable agenda, review, or follow-up note would help.

Read the evidence in both directions

When recent meetings or transcripts are supplied, read the complete relevant corpus and trace:

  • what previous work was being reviewed;
  • what was accepted, rejected, or reconstructed live;
  • what the manager expected explicitly and repeatedly;
  • what the employee actually understood and delivered;
  • which decisions were made;
  • which issues merely consumed time;
  • what changed for the next work cycle.

Prefer raw transcripts over AI-generated minutes when they conflict. Separate meeting claims, verified facts, inferences, and proposals. Do not diagnose personality or intent from one artifact.

Define the value of the meeting

Before planning an agenda, state one primary outcome:

  • make a decision;
  • review whether work is ready;
  • resolve a specific disagreement;
  • generate options;
  • coach a work method;
  • give performance feedback;
  • coordinate owners and dependencies.

Avoid silently mixing all of them. If several are necessary, name the transition and allocate time deliberately.

Ask whether a meeting is needed at all. Prefer an async document when the work is mainly background reading, fact collection, or straightforward status. Use synchronous time for ambiguity, disagreement, trade-offs, feedback, and decisions.

Prepare the smallest useful meeting

Prepare:

  1. the decision or outcome needed;
  2. the employee artifact or pre-read;
  3. the two to five questions that could change the decision;
  4. known gaps that may block the meeting;
  5. the desired close: decision, correction, owner, or next output.

Do not hide acceptance criteria in the manager's head. For complex work, tell the employee beforehand what question the work must answer and what evidence matters. Ask the employee to restate the assignment when misunderstanding would be costly.

Run a high-bandwidth review

Use a simple flow:

  1. Open: state the purpose and decision needed.
  2. Hear the answer: let the employee give the top-line conclusion before detailed interruption, unless a foundational premise is immediately invalid.
  3. Locate the real gap: determine whether the issue is missing work, unreliable evidence, wrong reasoning, poor communication, scope drift, or unclear expectations.
  4. Discuss only what matters synchronously: focus on evidence, trade-offs, disagreement, risk, and decisions.
  5. Stop low-value loops: do not spend an hour recreating an artifact that should be corrected offline.
  6. Close: state what was decided, what remains open, who owns the next output, when it is due, and what acceptable completion means.

If the work is not ready, say so early. Use the remaining time to identify the smallest correction that makes the next review worthwhile.

Ask questions that increase information

Prefer questions such as:

  • What exact decision does this support?
  • What is your conclusion in one sentence?
  • Which evidence is decisive?
  • What is confirmed, inferred, assumed, and unknown?
  • Can this number be reproduced from source values and units?
  • What would falsify the recommendation?
  • Why is the alternative worse under the current constraints?
  • Which gap could still change the decision?
  • What do you need from me now?

Avoid repeating rhetorical questions after the gap is already clear. Repetition increases pressure but often produces no new information.

Be direct without making communication worse

Do not lower the standard, hide an invalid result, or pretend work is ready. Also do not use sarcasm, global ability labels, public humiliation, or prolonged interrogation as substitutes for precise feedback.

Use this pattern:

  1. name the observable work result;
  2. state the expectation it failed or met;
  3. explain the decision, trust, or rework impact;
  4. define the replacement behavior or artifact;
  5. set the next check.

Example:

This cost conclusion is not reviewable because the unit conversion and workload assumption cannot be reproduced. Rebuild it from the official price, show one formula and three workload scenarios, compare it with a dedicated-server baseline, and send the calculation before writing the recommendation.

Employee experience matters because fear, confusion, and unpredictability reduce the accuracy of the information reaching the manager. Respect does not mean comfort at all times. It means clear standards, a real chance to explain, specific correction, and no avoidable degradation.

The manager does not need to suppress legitimate frustration or absorb failed work. State the consequence plainly, pause a meeting that no longer creates value, and return responsibility to the employee with a clear correction.

Show full SKILL.md (390 more words)Show less

Do not take over the employee's work

When the manager discovers a missing analysis:

  • identify the missing question and why it matters;
  • give enough framing to prevent another misunderstanding;
  • avoid designing the entire solution live;
  • ask the employee to return with the evidence, calculation, or proposal;
  • separate coaching from doing the work for them.

If the same failure repeats after expectations and support are clear, treat it as a performance or role-fit signal rather than adding more meeting explanation.

Diagnose meeting quality

Judge whether the meeting created:

  • a clearer shared model;
  • new trustworthy information;
  • an explicit decision or narrowed choice;
  • an executable next action;
  • better future work behavior.

Look for low-bandwidth patterns:

  • basic facts discovered live;
  • long chronology before the conclusion;
  • manager repeatedly solving the problem;
  • unsupported guesses debated at length;
  • employee agreeing without understanding;
  • coaching, architecture, review, and performance feedback mixed together;
  • no stop condition after work is clearly not ready;
  • no owner, due time, or acceptance condition at close.

Recommend the smallest change that improves the next meeting. Do not respond to process problems by creating excessive ceremony.

Use semantic review

The current agent must inspect the actual meeting and work evidence. Never score meeting or employee quality from keywords, speaking time alone, tone alone, required headings, or a fixed template.

For large or disputed cases, use independent subagents when available to examine manager expectations, employee evidence, and meeting dynamics separately. Give them raw artifacts. The primary agent must reconcile their findings and own the final recommendation.

Default output

Keep the answer compact unless the user asks for a full analysis:

  1. Verdict — what is wrong or what should happen.
  2. Meeting purpose — the outcome worth synchronous time.
  3. Pre-meeting requirement — what must exist before the meeting.
  4. Agenda and questions — only the high-value discussion.
  5. Direct feedback — exact language the manager can use.
  6. Close — decision, owner, output, timing, and acceptance condition.

Quality rules

  • Lead with the decision value.
  • Preserve high standards without using avoidable emotional damage as a management tool.
  • Protect the truth signal: make it safe to say "unknown" and costly to bluff.
  • Stop meetings that have become live rework with no new decision value.
  • Distinguish an employee gap from a task-definition or management-system gap.
  • Return ownership instead of doing the employee's job.
  • Make every meeting change the work, the decision, or the shared model.

© shareAI-lab, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in team-collaboration/meeting-coach-leader of shareAI-lab/lab-skills.

  • SKILL.md
  • agents/openai.yaml
  • references/manager-playbook.md
  • references/templates.md

Open the folder on GitHubat commit becee99

Compare with similar skills

Meeting Coach Leader next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Meeting Coach Leader compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Meeting Coach Leader this skillshareAI-lab/lab-skills315—~2.2kAutomated safety check: PassApache-2.0
Weekly Engineering Retrogarrytan/gstack136k—~2.4kAutomated safety check: PassMIT
Dough Execute Planterryyin/lizard2.5k—~4.3kAutomated safety check: PassCustom licence
Oral Paper SkillAdkid-Zephyr/oral-paper-skill357—~1.9kAutomated safety check: PassNone
Deck Retroasheshgoplani/agent-deck1.1k—~1.8kAutomated safety check: PassMIT
Dough Execution Retrospectiveterryyin/lizard2.5k—~4kAutomated safety check: PassCustom licence

Similar skills

  • Builds a weekly engineering retrospective from git history: commit counts, per-person contributions, work patterns and code quality numbers over a chosen window.

    136k GitHub stars~2.4k tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Dough Execute Plan

    terryyin/lizard

    Executes one selected story or bounded retrospective correction through an executable plan, or one authorized planless slice from a selected simple story or a contextual instruction, with…

    2.5k GitHub stars~4.3k tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Oral Paper Skill

    Adkid-Zephyr/oral-paper-skill

    Help authors learn from exemplary ICLR, ICML, and NeurIPS papers through source-linked manuscript comparisons, concrete writing and experiment suggestions, and guided reflection.

    357 GitHub stars~1.9k tokensUpdated 23 days ago
    Product & Project ManagementAuto-check passed
  • Deck Retro

    asheshgoplani/agent-deck

    Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs.

    1.1k GitHub stars~1.8k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Reviews planned, completed planless quick, or quick-to-planned execution against original intent, aggregate commits, current whole-product architecture, and tests, including after cleanup.

    2.5k GitHub stars~4k tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Criticism Self Criticism

    HughYau/qiushi-skill

    批评与自我批评:在工作完成、阶段验收、收到批评或同类错误反复出现时,对成果和过程做诚实、具体、基于事实的审视,输出可执行的改进项,并处理外来批评而不辩解。触发信号包括 review、复盘、审查、"帮我看看有没有问题"、"你确定吗";任务刚开始或只是单步查询时不触发。

    3.8k GitHub stars~423 tokensUpdated 10 days ago
    Product & Project ManagementAuto-check passed

More from shareAI-lab/lab-skills

All 10 skills in this repo
  • Agent Builder

    shareAI-lab/lab-skills

    Helps design and build AI agents for any domain around a minimal loop of capabilities, knowledge and context, adding planning or subagents only when needed.

    315 GitHub stars~1.4k tokensUpdated 25 days ago
    Auto-check passed
  • Deep Architecture Research

    shareAI-lab/lab-skills

    Deeply research technical architecture, source code, mechanisms, SDKs, frameworks, project comparisons, and system-design options across repositories, history, official docs, issues, discussions…

    315 GitHub stars~1.3k tokensUpdated 25 days ago
    Auto-check passed
  • Neural Mechanism Research

    shareAI-lab/lab-skills

    Research why neural architectures and training methods work through forward computation, geometry, gradients, optimization dynamics, historical experiments, and competing explanations.

    315 GitHub stars~2.3k tokensUpdated 25 days ago
    Auto-check passed
  • Review AI Conversations

    shareAI-lab/lab-skills

    Recover and review local human-AI conversations from Claude Code, Codex, opencode, Grok Build, and Cursor.

    315 GitHub stars~1.1k tokensUpdated 25 days ago
    Auto-check passed
  • Skill Judge

    shareAI-lab/lab-skills

    Evaluate Agent Skill design quality with an opinionated, practice-derived rubric informed by public specifications and examples.

    315 GitHub stars~1.9k tokensUpdated 25 days ago
    Auto-check passed
  • Understanding First Report

    shareAI-lab/lab-skills

    Reconstruct and report long-running or multi-turn research, architecture questions, reviews, decisions, completion results, and status as a clear, self-contained brief.

    315 GitHub stars~4.3k tokensUpdated 25 days ago
    Auto-check passed

Questions about Meeting Coach Leader

What does Meeting Coach Leader do?

Coach leaders and managers to prepare, run, and review high-bandwidth meetings that advance real work and decisions. Meeting Coach Leader is an agent skill from shareAI-lab/lab-skills. Coach leaders and managers to prepare, run, and review high-bandwidth meetings that advance real work and decisions.

When should I use Meeting Coach Leader?

Meeting Coach Leader fits situations like: meeting retrospectives; employee work reviews; decision meetings; agenda and question design.

How do I install Meeting Coach Leader in Claude Code?

Run `npx skills add shareAI-lab/lab-skills --skill meeting-coach-leader -a claude-code`. Or copy the skill folder (team-collaboration/meeting-coach-leader in shareAI-lab/lab-skills) into .claude/skills/meeting-coach-leader in your project. Claude Code loads it when a task matches its description.

How do I install Meeting Coach Leader in Codex?

Run `npx skills add shareAI-lab/lab-skills --skill meeting-coach-leader -a codex`. Or copy the skill folder (team-collaboration/meeting-coach-leader in shareAI-lab/lab-skills) into .agents/skills/meeting-coach-leader in your project. Codex loads it when a task matches its description.

Can I use Meeting Coach Leader in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add shareAI-lab/lab-skills --skill meeting-coach-leader -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/meeting-coach-leader, .gemini/skills/meeting-coach-leader, .github/skills/meeting-coach-leader and .opencode/skills/meeting-coach-leader in your project.

What does Meeting Coach Leader need to run?

SKILL.md names no scripts, command-line tools or credentials: Meeting Coach Leader is instructions for the agent only.

Does Meeting Coach Leader access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Meeting Coach Leader safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Meeting Coach Leader use?

Meeting Coach Leader is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Meeting Coach Leader use?

About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.3k tokens, read only when the agent opens those files.

What are the alternatives to Meeting Coach Leader?

Skills that share tags, products or a category with Meeting Coach Leader: Weekly Engineering Retro (garrytan/gstack, 136k stars), Dough Execute Plan (terryyin/lizard, 2.5k stars), Oral Paper Skill (Adkid-Zephyr/oral-paper-skill, 357 stars) and Deck Retro (asheshgoplani/agent-deck, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Meeting Coach Leader?

shareAI-lab (a GitHub organization) maintains it in shareAI-lab/lab-skills, which has 315 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 16, 2026.

Source: shareAI-lab/lab-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.