Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill meeting-minutes-generatorgit clone --depth 1 https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_ConstructionWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/meeting-minutes-generator)<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/meeting-minutes-generator"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/meeting-minutes-generator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/meeting-minutes-generator"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/meeting-minutes-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00020 | $0.02365 |
| Opus 5.5 | $0.00008 | $0.00946 |
| Sonnet 5.5 | $0.00004 | $0.00473 |
| Haiku 4.5 | $0.00002 | $0.00236 |
Grade A, and why
meeting-minutes-generator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- meeting-minutes-generator — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Minutes Generator
Business Case
Problem Statement
Meeting documentation is inconsistent:
- Minutes not standardized
- Action items lost
- Decisions not tracked
- Poor distribution
Solution
Standardized meeting minutes generation with action item tracking, decision logging, and automatic distribution.
Technical Implementation
import pandas as pd
from datetime import datetime, date, timedelta
from typing import Dict, Any, List, Optional
from dataclasses import dataclass, field
from enum import Enum
class MeetingType(Enum):
OAC = "oac" # Owner-Architect-Contractor
PROGRESS = "progress"
COORDINATION = "coordination"
SAFETY = "safety"
PRECONSTRUCTION = "preconstruction"
CLOSEOUT = "closeout"
OTHER = "other"
class ActionStatus(Enum):
OPEN = "open"
IN_PROGRESS = "in_progress"
COMPLETE = "complete"
OVERDUE = "overdue"
class Priority(Enum):
HIGH = "high"
MEDIUM = "medium"
LOW = "low"
@dataclass
class Attendee:
name: str
company: str
role: str
email: str
present: bool = True
@dataclass
class ActionItem:
action_id: str
description: str
assigned_to: str
due_date: date
priority: Priority
status: ActionStatus
created_meeting: str
completed_date: Optional[date] = None
notes: str = ""
@dataclass
class Decision:
decision_id: str
description: str
made_by: str
decision_date: date
impact: str = ""
@dataclass
class DiscussionTopic:
topic_id: str
title: str
presenter: str
discussion: str
decisions: List[Decision] = field(default_factory=list)
actions: List[str] = field(default_factory=list) # Action IDs
@dataclass
class MeetingMinutes:
meeting_id: str
meeting_type: MeetingType
title: str
date: date
time_start: str
time_end: str
location: str
attendees: List[Attendee]
topics: List[DiscussionTopic]
action_items: List[ActionItem]
next_meeting: Optional[date] = None
prepared_by: str = ""
approved_by: str = ""
class MeetingMinutesGenerator:
"""Generate and track meeting minutes."""
def __init__(self, project_name: str):
self.project_name = project_name
self.meetings: Dict[str, MeetingMinutes] = {}
self.all_actions: Dict[str, ActionItem] = {}
self._meeting_counter = 0
self._action_counter = 0
self._decision_counter = 0
def create_meeting(self, meeting_type: MeetingType, title: str,
meeting_date: date, time_start: str, time_end: str,
location: str) -> MeetingMinutes:
self._meeting_counter += 1
meeting_id = f"MTG-{self._meeting_counter:04d}"
meeting = MeetingMinutes(
meeting_id=meeting_id,
meeting_type=meeting_type,
title=title,
date=meeting_date,
time_start=time_start,
time_end=time_end,
location=location,
attendees=[],
topics=[],
action_items=[]
)
self.meetings[meeting_id] = meeting
return meeting
def add_attendee(self, meeting_id: str, name: str, company: str,
role: str, email: str, present: bool = True):
if meeting_id not in self.meetings:
return
attendee = Attendee(name, company, role, email, present)
self.meetings[meeting_id].attendees.append(attendee)
def add_topic(self, meeting_id: str, title: str, presenter: str,
discussion: str) -> str:
if meeting_id not in self.meetings:
return ""
topic_id = f"{meeting_id}-T{len(self.meetings[meeting_id].topics) + 1:02d}"
topic = DiscussionTopic(topic_id, title, presenter, discussion)
self.meetings[meeting_id].topics.append(topic)
return topic_id
def add_decision(self, meeting_id: str, topic_id: str, description: str,
made_by: str, impact: str = "") -> Decision:
if meeting_id not in self.meetings:
return None
self._decision_counter += 1
decision_id = f"DEC-{self._decision_counter:04d}"
decision = Decision(
decision_id=decision_id,
description=description,
made_by=made_by,
decision_date=self.meetings[meeting_id].date,
impact=impact
)
# Find topic and add decision
for topic in self.meetings[meeting_id].topics:
if topic.topic_id == topic_id:
topic.decisions.append(decision)
break
return decision
def create_action(self, meeting_id: str, description: str, assigned_to: str,
due_date: date, priority: Priority = Priority.MEDIUM) -> ActionItem:
if meeting_id not in self.meetings:
return None
self._action_counter += 1
action_id = f"ACT-{self._action_counter:04d}"
action = ActionItem(
action_id=action_id,
description=description,
assigned_to=assigned_to,
due_date=due_date,
priority=priority,
status=ActionStatus.OPEN,
created_meeting=meeting_id
)
self.meetings[meeting_id].action_items.append(action)
self.all_actions[action_id] = action
return action
def update_action_status(self, action_id: str, status: ActionStatus):
if action_id in self.all_actions:
self.all_actions[action_id].status = status
if status == ActionStatus.COMPLETE:
self.all_actions[action_id].completed_date = date.today()
def get_open_actions(self, assigned_to: str = None) -> List[ActionItem]:
actions = [a for a in self.all_actions.values()
if a.status in [ActionStatus.OPEN, ActionStatus.IN_PROGRESS]]
if assigned_to:
actions = [a for a in actions if assigned_to.lower() in a.assigned_to.lower()]
return sorted(actions, key=lambda x: x.due_date)
def get_overdue_actions(self) -> List[ActionItem]:
today = date.today()
overdue = []
for action in self.all_actions.values():
if action.status in [ActionStatus.OPEN, ActionStatus.IN_PROGRESS]:
if action.due_date < today:
action.status = ActionStatus.OVERDUE
overdue.append(action)
return overdue
def generate_minutes_document(self, meeting_id: str) -> str:
"""Generate formatted meeting minutes."""
if meeting_id not in self.meetings:
return ""
mtg = self.meetings[meeting_id]
lines = [
f"# {mtg.title}",
f"**Date:** {mtg.date.strftime('%B %d, %Y')}",
f"**Time:** {mtg.time_start} - {mtg.time_end}",
f"**Location:** {mtg.location}",
f"**Project:** {self.project_name}",
"",
"## Attendees",
]
for att in mtg.attendees:
status = "Present" if att.present else "Absent"
lines.append(f"- {att.name} ({att.company}) - {att.role} [{status}]")
lines.extend(["", "## Discussion Topics"])
for topic in mtg.topics:
lines.extend([
f"### {topic.title}",
f"*Presented by: {topic.presenter}*",
"",
topic.discussion,
""
])
if topic.decisions:
lines.append("**Decisions:**")
for dec in topic.decisions:
lines.append(f"- [{dec.decision_id}] {dec.description}")
lines.append("")
if mtg.action_items:
lines.extend(["## Action Items", ""])
lines.append("| ID | Action | Assigned | Due | Priority |")
lines.append("|---|---|---|---|---|")
for action in mtg.action_items:
lines.append(f"| {action.action_id} | {action.description} | "
f"{action.assigned_to} | {action.due_date} | {action.priority.value} |")
if mtg.next_meeting:
lines.extend(["", f"## Next Meeting: {mtg.next_meeting.strftime('%B %d, %Y')}"])
return "\n".join(lines)
def export_all_actions(self, output_path: str):
"""Export action items to Excel."""
data = [{
'ID': a.action_id,
'Description': a.description,
'Assigned To': a.assigned_to,
'Due Date': a.due_date,
'Priority': a.priority.value,
'Status': a.status.value,
'Meeting': a.created_meeting
} for a in self.all_actions.values()]
df = pd.DataFrame(data)
df.to_excel(output_path, index=False)
return output_path
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 337 lines · 20 tokens per session scan A f51970f41771
meeting-minutes-generator is a skill published in the GitHub repository datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction (373 stars, last pushed 8d ago), licensed MIT. It adds 20 tokens to every session and 2,365 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
process-mapper
Use when a BizOps lead, COO, or process-improvement owner needs to document an end-to-end business process (procurement, employee onboarding, incident handoff, customer-onboarding, claims adjudication) in BPMN-style notation, measure cycle times by stage, surface where work spends most of its time waiting vs. being…
design-handoff-brief
Transform feature briefs into structured design briefs that give designers the context they need before opening Figma. Use when asked to write a design brief, create a design handoff, brief a designer on a new feature, or translate a PRD into design requirements. Produces a brief with user goal, emotional context…
estimating-and-contingency
Produces a cost or effort estimate someone can defend — decomposing the work, choosing between analogous, parametric and bottom-up methods, documenting the basis and its assumptions, expressing confidence as a range, and sizing contingency and management reserve separately. Use this to build an estimate, challenge one…
scenario-team-admin
Use when administering a Scenario team from an agent through MCP: restricting which models a team or project can run (model access control, allowlist, blocklist), inviting or removing team and project members, changing roles, capping a member's Creative Unit spend, creating or deleting projects, auditing API keys and…
rice-impact-matrix
Califica iniciativas usando tanto RICE como alineación estratégica para una priorización matizada. Úsalo cuando te pidan priorizar características, construir una matriz de prioridades, combinar puntuación cuantitativa con ajuste estratégico, o decidir qué construir después con múltiples iniciativas en competencia.…
multi-agent-client-onboarding
Uses Agent SDK to deploy 3 parallel agents for client onboarding -- workflow auditor, tech stack mapper, and strategy drafter. Real consulting workflow that produces a complete client assessment.