risk-and-issues-manager-scott-margetts
RAID log methodology with decision extraction from emails and meeting notes. Use when asked to identify risks, log assumptions, track issues, extract decisions from correspondence, create or update a RAID log, escalate a risk to an issue, assess project risks, validate or challenge assumptions, or capture scope-relevant decisions. Also triggers when the user pastes email chains and asks what decisions were made, or needs to find buried decisions and untested assumptions in correspondence. Trigger on: 'risk report', 'RAID log', 'what are the risks', 'what decisions were made', 'update the risk
npx skills add lawve-ai/awesome-legal-skills --skill risk-and-issues-manager-scott-margetts --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill maintains a RAID log (Risks, Assumptions, Issues, Decisions) for legal matters and extracts structured data from emails and notes. It operates in two modes: RAID log maintenance and decision extraction from correspondence. It prioritizes the decision extraction function to surface buried decisions, risks, assumptions, issues, and scope signals from email chains and meeting notes, outputting structured entries ready to add to the RAID log.
Mode 1: RAID log maintenance
Create, update, and manage the four components of the RAID log for a matter. If an existing RAID log is provided (e.g., an uploaded Excel log), read and update it using its structure and numbering.
Mode 2: Decision extraction from correspondence
Read pasted email chains, meeting notes, or call notes to identify:
- Decisions (explicit or implicit),
- Risks, Assumptions, Issues, and Scope signals. Output: structured entries with flags for follow-up or escalation.
Mode 3: Risk identification from context
When given matter setup details, identify key operational risks based on matter type, jurisdictions, team, timeline, and commercial arrangements.
How it works
- Determine the mode based on the user’s prompt (Decision extraction favored if input is a chain without a mode provided).
- For Mode 1, confirm matter name and whether an existing RAID log is available; if a file is uploaded, read and follow its structure.
- For Mode 2, scan the entire input for explicit and implicit decisions, risks, assumptions, issues, and scope signals; log with notes on status (e.g., Implied, Conditions).
- For Mode 3, collect matter context and apply the risk identification framework.
- Produce output starting with an Items requiring immediate action section, followed by IRAD counters, then full log entries (Issues, Risks, Assumptions, Decisions).
When to use it
Trigger phrases include: 'risk report', 'RAID log', 'what are the risks', 'what decisions were made', 'update the risk register', 'what assumptions are we making', 'what could go wrong', 'flag any issues', 'extract decisions from these emails'. If a user pastes an email chain without specifying, default to Mode 2.
What it can touch
The skill interfaces with a RAID log (Excel structure) and sources from pasted correspondence to extract IRAD data. It requires reading and writing to the RAID log structure as defined in the output fields for Issues, Risks, Assumptions, and Decisions.
Caveats
License is Apache-2.0 per metadata. States that decisions may be explicit or implicit; implicit decisions require validation. It distinguishes between Confirmed and Implied decisions and flags scope changes for a separate scope-change controller.
# Risk and Issues Manager ## Purpose Maintain a structured RAID log (Risks, Assumptions, Issues, Decisions) for legal matters and extract structured data from unstructured correspondence. This skill operates in two modes: RAID log maintenance (creating, updating, and managing the log) and decision extraction (identifying decisions, risks, assumptions, and scope-relevant information buried in email chains and meeting notes). The decision extraction mode is the highest-value function. Decisions get made in email constantly — "let's leave Germany out for now," "we'll use the existing holdco," "client says they don't need a valuation" — and they're never formally recorded. Six months later when scope is disputed, budget is blown, or a workstream is stuck, nobody can find the email where the decision was made. This skill catches those decisions at the point they're made and logs them with the metadata needed to make them useful later. ## Operating modes ### Mode 1: RAID log maintenance Create, update, and manage the four components of the RAID log. This is the ongoing discipline — the log is a living document that's reviewed regularly and updated as the matter progresses. ### Mode 2: De
- Purpose
- Operating modes
- Mode 1: RAID log maintenance
- Mode 2: Decision extraction from correspondence
- Mode 3: Risk identification from context
- Step-by-step process
- Step 1: Determine the mode
- Step 2: Process the input
- Step 3: Produce the output
- IRAD counters
- Step 4: Write the immediate action summary (this goes FIRST in the output)
- RAID methodology — the operational knowledge
- Why most RAID logs fail
- Risk identification — what to look for
What does the risk-and-issues-manager-scott-margetts skill do?
RAID log methodology with decision extraction from emails and meeting notes. Use when asked to identify risks, log assumptions, track issues, extract decisions from correspondence, create or update a RAID log, escalate a risk to an issue, assess project risks, validate or challenge assumptions, or capture scope-relevant decisions. Also triggers when the user pastes email chains and asks what decisions were made, or needs to find buried decisions and untested assumptions in correspondence. Trigger on: 'risk report', 'RAID log', 'what are the risks', 'what decisions were made', 'update the risk
How do I install it?
Run `npx skills add lawve-ai/awesome-legal-skills --skill risk-and-issues-manager-scott-margetts --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From lawve-ai/awesome-legal-skills, a repository with 618 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.