Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Corrective Action Plan Deficiencies

ASecurity

Drafts a regulator-ready Corrective Action Plan (CAP) for U.S. healthcare facilities responding to inspection, survey, or audit deficiencies. Covers root-cause analysis, remediation steps, accountability, milestones, monitoring, and validation. Trigger when the user mentions CAP, plan of correction, deficiency citation, scope/severity remediation, correction timeline, or sustainability monitoring for CMS, state, or Joint Commission findings.

16 stars
0 votes
0 copies
2 views
Added 6/7/2026
ai-agentsgorailsgitapi

Works with

cliapi

Security Analysis

A100/100

Scanned 6/7/2026

$npx -y skills add ThomasMoreAI/legal-skills-open --skill corrective-action-plan-deficiencies --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Corrective Action Plan Deficiencies?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Corrective Action Plan Deficiencies
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/thomasmoreai-corrective-action-plan-deficiencies/badge)](https://www.skillsdirectory.com/skills/thomasmoreai-corrective-action-plan-deficiencies)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: corrective-action-plan-deficiencies
title: Corrective Action Plan for Healthcare Deficiencies
description: Drafts a regulator-ready Corrective Action Plan (CAP) for U.S. healthcare facilities responding to inspection, survey, or audit deficiencies. Covers root-cause analysis, remediation steps, accountability, milestones, monitoring, and validation. Trigger when the user mentions CAP, plan of correction, deficiency citation, scope/severity remediation, correction timeline, or sustainability monitoring for CMS, state, or Joint Commission findings.
author: CaseMark
author_url: https://github.com/CaseMark/skills/tree/main/skills/legal/corrective-action-plan-deficiencies
license: Apache-2.0
version: 0.1.0
execution_mode: open
jurisdiction: us
practice: healthcare
language: en
tags: [drafting, memo, regulatory]
---

# Corrective Action Plan for Healthcare Deficiencies

Produces a regulator-ready CAP aligning documented findings with implementable remediation, measurable milestones, and post-correction validation.

## Gather Before Drafting

- Inspection documents: survey report, statement of deficiencies, exit notes, prior CAPs, correspondence
- Regulatory identifiers: CMS/state program notices, accreditation standards, certifications, response deadlines
- Root-source data: incident logs, QA metrics, training records, staffing schedules, policy versions
- Org structure: authority matrix, job descriptions, committee charters, budget constraints
- Legal posture: sanction exposure, privilege considerations, counsel alignment if liability implicated
- Submission target: regulator format requirements, filing deadlines

## Workflow

### 1. Intake and Factual Baseline

| Element | Content | Source |
|---|---|---|
| Header | Facility, program, finding IDs, dates, facility type | Survey/notice letters, CMS portal |
| Deficiency statement | Exact noncompliance language; dates, location, patient population, severity | Deficiency narrative, field notes |
| Citation mapping | Statute/regulation/standard references as written by regulator | Official citation text |
| Event timeline | Discovery → preliminary → formal findings → response date | Inspection log, correspondence |
| Prior-work continuity | Prior CAP references and outcomes; why prior actions failed if recurring | Historical CAPs, QA trend reports |

### 2. Root-Cause Analysis

1. Classify each deficiency as isolated vs. systemic.
2. Apply structured method (5-Whys / fishbone); name primary causal chain.
3. Link each driver to evidence: policy gaps, training gaps, staffing constraints, supervision blind spots, communication failures.
4. State recurrence risk and why prior controls failed.

### 3. Corrective Action Matrix

| # | Deficiency / Root Cause | Action Step | Owner | Due Date | Evidence Required | Verification Method |
|---|---|---|---|---|---|---|

Per row:
- Separate immediate correction from longer-term prevention.
- Reference the specific deficiency and root cause.
- Training entries: content, format, assessment method, proficiency threshold.
- Policy changes: section numbers, deleted/added language, distribution, acknowledgment.
- Capital/resource changes: procurement lead times, implementation dependencies.

### 4. Accountability and Escalation

- Designate CAP coordinator (single point of contact), departmental leads, executive sponsor.
- Escalation triggers: milestone missed >1 week, budget overrun above threshold, resource blockade.
- Review cadence: weekly operational, monthly executive.

### 5. Monitoring and Sustainability

| Element | Frequency | Source | Owner | Threshold |
|---|---|---|---|---|
| Process compliance | Daily/weekly initially, taper by risk | Audit tools, checklists, observation logs | QA staff | Defined target |
| Outcome data | Weekly/monthly | Quality indicators, incident reports | Clinical director/QA | Reduction to baseline |
| Competency retention | Go-live + periodic refresher | Test scores, direct observation | Education lead | Minimum met |

- Distinguish one-time completion from sustained compliance.
- Require minimum stable period before de-escalation.
- Use unannounced cross-shift audits to test durability.

### 6. Validation and Closure

- Pre-post comparison using identical metrics and sampling.
- Independent verification (internal or external) for high-risk findings.
- Closure criteria: compliance thresholds sustained across shifts and time.
- Tie to evidence logs, reports, and leadership sign-off.

### 7. Execution Template

Populate the following fields in the final output:

- Facility / Program / Agency
- Deficiency IDs / Citations / Severity
- Summary of findings (verbatim excerpts)
- Root cause(s)
- Immediate actions / Systemic actions
- Milestone schedule
- Monitoring matrix
- Validation criteria
- Escalation triggers
- Regulatory reporting cadence
- Executive approval / Signature block(s)

### 8. Pre-Output Checks

- No contradictions with prior regulator statements.
- All commitments feasible within budget, staffing, and operating constraints.
- Every obligation mapped to an evidence artifact.
- Dates are calendar-based with contingency notes.
- Legal review flagged where admissions increase enforcement risk.

## Pitfalls and Guardrails

- Use regulator-facing language; no defensive framing or noncommittal phrasing.
- Do not overpromise resources; if infeasible, request extension with substantiation and interim controls.
- Separate facts from analysis; no speculative causal assertions.
- For recurring deficiencies, state explicitly why prior remediation failed and what changed.
- IJ/condition-level findings: prioritize immediate patient-safety remediation and expedited reporting.
- Treat state-specific requirements and accreditor addenda as hard constraints.
- Verify all timelines against CMS/state/enforcement deadlines before submission.
- Include counsel review when findings imply sanction exposure, civil penalties, or contract termination risk.
- Mark uncertain legal standards with `[VERIFY]`.
- Do not include broad legal conclusions on liability; focus on compliance remediation.

Attribution

ThomasMoreAIThomasMoreAI
View sourceSee grades on GitHubMore from ThomasMoreAI →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →