Mitigation Recommend

Runs the local deterministic draft mitigation and unsent owner-notification engine. Use for "recommend a mitigation", "should we expedite or substitute", "who do we notify", "who do we escalate to", or "what do we do about it". Do NOT use for intake, retrieval, mapping or terminal drafts — use disruption-intake, supply-knowledge-retrieve, shortage-impact-map or disruption-writeup instead. No procurement, supplier or ERP actions.

110 stars 122 forksWriting & ContentOfficial

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add microsoft/cat-agent-skills --skill mitigation-recommend
Manual install
git clone --depth 1 https://github.com/microsoft/cat-agent-skills.git /tmp/cat-agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/cat-agent-skills/submissions/supplier-disruption/mitigation-recommend ~/.claude/skills/mitigation-recommend

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Mitigation Recommend

## Purpose
Deterministically choose the mitigation — **expedite**, **substitute** or **reschedule** — from the
impact summary and the supply position (substitutes, alternate suppliers, lead time, single-source
flag, supplier history), set the urgency, build the cumulative owner-notification list, and raise the
governance escalations — then finalize the recommended next-best action.

## When to use
- After shortage-impact-map, in every run.
- "Should we expedite or substitute, and who do we escalate to?".

## Inputs
- The contract payload with `impact_summary{}` (worst_severity, first_impact_date, total qty at risk)
  and `supply{}` (substitutes, alternates, single_source) and `history.chronic_pattern`
  (contract `mfg.supplier-disruption.v1`).

## Steps
1. Validate the payload against the contract.
2. Run `scripts/mitigation_recommend.py --impact impact-map.json --out disruption-packet.json`.
3. Do not restate or recompute the mitigation choice or the escalations in prose; quote the engine
   output verbatim.
4. Emit the `{mitigation, notifications}` contract payload and the finalized `next_best_action`.

## Output
Contract `mfg.supplier-disruption.v1` with a populated `mitigation{}` (option, urgency, actions,
substitute_part/alternate_supplier, confidence, source=engine:mitigation_recommend), a
`notifications[]` owner list, and appended `escalations[]` plus the finalized `next_best_action` —
the `{mitigation}` hop.

## Grounding requirements
Read the full skill on GitHub

Details

Skill name
mitigation-recommend
Path
submissions/supplier-disruption/mitigation-recommend/SKILL.md
License
MIT
Repo updated
15 November 2026

FAQ

What does the Mitigation Recommend skill do?

Runs the local deterministic draft mitigation and unsent owner-notification engine. Use for "recommend a mitigation", "should we expedite or substitute", "who do we notify", "who do we escalate to", or "what do we do about it". Do NOT use for intake, retrieval, mapping or terminal drafts — use disruption-intake, supply-knowledge-retrieve, shortage-impact-map or disruption-writeup instead. No procurement, supplier or ERP actions.

How do I install the Mitigation Recommend skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add microsoft/cat-agent-skills --skill mitigation-recommend. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Mitigation Recommend popular?

It lives in microsoft/cat-agent-skills, which has 110 GitHub stars and 122 forks.

Related skills

3 Statements

110

microsoft/cat-agent-skills

Completes existing income statement, balance sheet and cash flow templates while preserving layout, grounding historical inputs and linking forecast formulas with reconciliation checks. Use for "fill in a 3-statement template", "complete an IS/BS/CF framework", "populate my integrated financial model", "link statements in this template", or "finish the forecasts in my three-statement workbook". Do NOT use for blank-slate models or general workbook edits (use xlsx), DCF valuation (use dcf-valuation), or buyout modeling (use lbo-model).

AI, LLMs & Agents122

Accessibility Pass

110

microsoft/cat-agent-skills

Use this skill whenever the user asks to check, review, or fix the accessibility of a PowerPoint deck, Word document, HTML page, or Markdown file, and before handing over any deck or document this agent just generated, so it does not ship with missing alt text, untitled slides, or unreadable colour contrast.

Frontend & Design122

Accessible Learning Materials

110

microsoft/cat-agent-skills

Maintains instructionally equivalent, accessible variants of a set of learning materials — lessons, readings, slides, and handouts — with parity checks against the original learning goals and recorded approvals. Use when the user asks to "make these materials accessible", "audit this lesson set for accessibility", "create an accessible version of this reading", "check reading level and alt text", or "keep my accessible variants in sync". Do NOT use for individual student accommodation or support-plan decisions (IEP, EHCP, or local equivalent), and do NOT use for generic document formatting (us

Learning & Education122

Pack Draft

110

microsoft/cat-agent-skills

Drafts this engagement's internal mobilization pack, joiner briefing and first-week plan only from the governed access-checklist.json and mobilization-pack.md, keeping every status, hold and DRAFT banner (never invents content, sends, shares or posts it). Use when the user asks "draft the onboarding pack from the access checklist", "write the joiner briefing for this engagement", "prepare the first-week plan for the joiner", "turn the access checklist into the mobilization pack" or "tidy up the mobilization pack wording". Do NOT use for a cold start with no access checklist yet (start with eng

Writing & Content122

Med Reconcile

110

microsoft/cat-agent-skills

Deterministic engine: diffs admission, inpatient-change and draft discharge medication lists and reports every add, stop, change and unresolved discrepancy, each cited to a numbered rule. Use when the user says "reconcile the discharge meds", "check the discharge medication list", "did anything get stopped during the stay", "is it safe to carry the home med list forward" or "just pull the home med list forward". Do NOT use for writing the summary - use summary-draft instead; do NOT use for patient-facing medication wording - use patient-instructions instead; do NOT use it to correct the draft

Writing & Content122

Patient Instructions

110

microsoft/cat-agent-skills

Produces plain-language patient discharge instructions from the reconciled evidence, with a deterministic readability check driven by config/readability-rules.json. Use when the user says "write the patient instructions", "what does the patient need to know at home", "make this readable for the patient", "plain-language discharge sheet" or "give the patient the same list as the summary". Do NOT use for the clinician-facing record - use summary-draft instead; do NOT use for the medication diff - use med-reconcile instead; do NOT use for the admission narrative - use admission-synthesise instead

Writing & Content122

Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.