Guideline Check
Checks drafted, coded time narratives against the client billing guidelines with the deterministic guideline_check engine: block billing, prohibited or vague terms, minimum detail, non-billable work, duplicates, increments and unrecorded time. Use it after code-map, or directly, when the user asks "will this narrative get rejected?", "is my time compliant?", "catch block billing", "find prohibited terms" or "find my missing time". Do NOT use for drafting or rewriting narratives (use narrative-draft), building the manager-facing exception packet (use exception-report), approving, submitting or
Install
npx skills add microsoft/cat-agent-skills --skill guideline-checkgit 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/time-expense-narrative-compliance/skills/guideline-check ~/.claude/skills/guideline-checkPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Guideline Check (Govern) ## Purpose Determine narrative compliance against billing guidelines: minimum detail, actor/subject/purpose, block billing, prohibited and vague wording, non-billable activity, increments, evidence and date consistency, duplicate meetings, code mismatch, signal privacy and missing time. ## When to use After `code-map` in every chain, and directly whenever a user asks whether an entry will be rejected, whether time is compliant, or what time is missing. Direct requests do not require prebuilt packets: collect the missing inputs and build the chain in Step 0 before determining compliance or missing time. ## Inputs Both engine inputs are mandatory: `coded.json` from code-map (drafted narratives, mapped codes, activity signals, guidelines and provenance) and the same `activity.json` from activity-pull that the chain started from. If they do not exist yet, follow Step 0; neither a pasted narrative nor raw exports can be passed directly to guideline_check.py. Missing-time requests need both packets too, even when no time entry exists for the unrecorded activity. The rules come from `references/` and the signal policy from `config/signal-sources.json`, both in this skill folder. ## Steps
Details
- Skill name
guideline-check- Repository
- microsoft/cat-agent-skills
- Path
submissions/time-expense-narrative-compliance/skills/guideline-check/SKILL.md- License
- MIT
- Repo updated
- 15 November 2026
FAQ
What does the Guideline Check skill do?
Checks drafted, coded time narratives against the client billing guidelines with the deterministic guideline_check engine: block billing, prohibited or vague terms, minimum detail, non-billable work, duplicates, increments and unrecorded time. Use it after code-map, or directly, when the user asks "will this narrative get rejected?", "is my time compliant?", "catch block billing", "find prohibited terms" or "find my missing time". Do NOT use for drafting or rewriting narratives (use narrative-draft), building the manager-facing exception packet (use exception-report), approving, submitting or
How do I install the Guideline Check skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add microsoft/cat-agent-skills --skill guideline-check. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Guideline Check popular?
It lives in microsoft/cat-agent-skills, which has 110 GitHub stars and 122 forks.
Related skills
3 Statements
110microsoft/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).
Accessibility Pass
110microsoft/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.
Accessible Learning Materials
110microsoft/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
Qr Code Builder
110microsoft/cat-agent-skills
Use this skill whenever the user asks to "make a QR code", "create a QR code", "QR code for this link/website", "QR code with my logo", "branded QR code" or "Wi-Fi QR code". Guided walkthrough that builds a scannable QR code (PNG, SVG, PDF, JPG, WEBP) with a bundled Python script. Only the web address is required; body shapes, corner-eye styles, outer frames, brand colors, a logo and a caption are optional. Also makes Wi-Fi, contact card, email, SMS, phone, map, event and bulk codes on request. Do NOT use for reading, scanning or decoding an existing QR code, or for barcodes other than QR code
Gate Check
110microsoft/cat-agent-skills
Runs the explicit Govern step: deterministic gate_check and severity_rank set gate results, release blockers and review status. Use after assertion-map or when the user asks "run the quality gate", "what blocks client issue?", "can this go to the client?", "rank the review findings", "check required reliance language" or "list the release blockers". Do NOT use for ingesting documents (use deliverable-ingest), retrieving criteria (use criteria-retrieve), mapping assertion support (use assertion-map), the packet narrative (use review-packet), time or expense narratives (use time-expense-narrativ
Reason Classify
110microsoft/cat-agent-skills
Classifies the stated return reason against the reason-code taxonomy with the deterministic reason_classify engine, recording confidence and candidate codes. Use after return-intake in every case, or on "what reason code is this", "classify the return reason", "which reason code", "code this return", "why are they returning it". Do NOT use for sentiment or complaint triage; not for eligibility or red flags - use eligibility-check instead; not for policy text - use policy-retrieve.
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.