Agent skill

Capa Officer

by borghei in borghei/Claude-Skills

CAPA system management for medical device QMS, covering root cause analysis, corrective action planning, and effectiveness verification.

MITAuto-check passedDevelopment

Install Capa Officer

skills CLI
$ npx skills add borghei/Claude-Skills --skill capa-officer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install borghei/Claude-Skills capa-officer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ra-qm-team/capa-officer .claude/skills/capa-officer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
capa-officer
GitHub stars
886
Token cost
~5.5k tokens
SKILL.md length
1,977 words
Files
4 (incl. scripts, references)
Skills in repo
354
Repo updated
First seen
Licence
MIT

At a glance

CAPA system management for medical device QMS, covering root cause analysis, corrective action planning, and effectiveness verification.

  • Works in 8 steps: Document trigger event with objective… → Assess significance and determine CAPA… → Form investigation team with relevant… → …
  • CAPA investigations
  • SKILL.md covers Table of Contents, Clarify First, CAPA Investigation Workflow and Root Cause Analysis, plus 5 more sections
  • Runs Python scripts from its folder; calls python

What it does

Capa Officer is an agent skill from borghei/Claude-Skills. CAPA system management for medical device QMS, covering root cause analysis, corrective action planning, and effectiveness verification. Use for CAPA investigations, 5-Why and fishbone analysis, and corrective action tracking.

Its SKILL.md is about 5.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/effectiveness-verification-guide.md`, `references/rca-methodologies.md` and `scripts/capa_tracker.py`).

It sits in Development, covering Root cause analysis. The repository describes itself as: 385 AI skills, 77 expert agents, and 900 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, research, and a LinkedIn toolkit… The licence is MIT.

When your agent uses it

  • CAPA investigations
  • 5-Why and fishbone analysis
  • Corrective action tracking

Example prompts

  • “/capa-officer”

Requirements

  • Python 3

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Document trigger event with objective evidence
  2. Assess significance and determine CAPA necessity
  3. Form investigation team with relevant expertise
  4. Collect data and evidence systematically
  5. Select and apply appropriate RCA methodology
  6. Identify root cause(s) with supporting evidence
  7. Develop corrective and preventive actions
  8. Validation: Root cause explains all symptoms; if eliminated, problem would not recur

What it can do on your machine

Read from SKILL.md and the folder at commit 4a698e8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Capa Officer loads about 5.5k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 60 tokens; SKILL.md has 1,977 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~5.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~13k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from borghei/Claude-Skills at commit 4a698e8, republished under its MIT licence (© borghei). 1,977 words, ~5,512 tokens.

Download SKILL.mdSave it as .claude/skills/capa-officer/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
capa-officer
description
CAPA system management for medical device QMS, covering root cause analysis, corrective action planning, and effectiveness verification. Use for CAPA investigations, 5-Why and fishbone analysis, and corrective action tracking.
license
MIT + Commons Clause
metadata.version
1.0.0
metadata.author
borghei
metadata.category
compliance
metadata.domain
corrective-action
metadata.updated
2026-03-31
metadata.tags
capa, root-cause-analysis, fmea, corrective-action, quality

CAPA Officer

Corrective and Preventive Action (CAPA) management within Quality Management Systems, focusing on systematic root cause analysis, action implementation, and effectiveness verification.


Table of Contents


Clarify First

Before starting a CAPA investigation, confirm these inputs. If any is unknown or vague, ASK — do not assume:

  • Trigger event and objective evidence — what happened, where/when, and what records exist (drives the problem statement and RCA scope)
  • Severity classification — Critical, Major, or Minor (sets investigation team composition, action depth, and verification timeline)
  • Source — complaint, audit finding, recurring NC, or trend (determines whether a CAPA is required and the regulatory linkage)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the CAPA record.

CAPA Investigation Workflow

Conduct systematic CAPA investigation from initiation through closure:

  1. Document trigger event with objective evidence
  2. Assess significance and determine CAPA necessity
  3. Form investigation team with relevant expertise
  4. Collect data and evidence systematically
  5. Select and apply appropriate RCA methodology
  6. Identify root cause(s) with supporting evidence
  7. Develop corrective and preventive actions
  8. Validation: Root cause explains all symptoms; if eliminated, problem would not recur
CAPA Necessity Determination
Trigger TypeCAPA RequiredCriteria
Customer complaint (safety)YesAny complaint involving patient/user safety
Customer complaint (quality)EvaluateBased on severity and frequency
Internal audit finding (Major)YesSystematic failure or absence of element
Internal audit finding (Minor)RecommendedIsolated lapse or partial implementation
Nonconformance (recurring)YesSame NC type occurring 3+ times
Nonconformance (isolated)EvaluateBased on severity and risk
External audit findingYesAll Major and Minor findings
Trend analysisEvaluateBased on trend significance
Investigation Team Composition
CAPA SeverityRequired Team Members
CriticalCAPA Officer, Process Owner, QA Manager, Subject Matter Expert, Management Rep
MajorCAPA Officer, Process Owner, Subject Matter Expert
MinorCAPA Officer, Process Owner
Evidence Collection Checklist
  • Problem description with specific details (what, where, when, who, how much)
  • Timeline of events leading to issue
  • Relevant records and documentation
  • Interview notes from involved personnel
  • Photos or physical evidence (if applicable)
  • Related complaints, NCs, or previous CAPAs
  • Process parameters and specifications

Root Cause Analysis

Select and apply appropriate RCA methodology based on problem characteristics.

RCA Method Selection Decision Tree
Is the issue safety-critical or involves system reliability?
├── Yes → Use FAULT TREE ANALYSIS
└── No → Is human error the suspected primary cause?
    ├── Yes → Use HUMAN FACTORS ANALYSIS
    └── No → How many potential contributing factors?
        ├── 1-2 factors (linear causation) → Use 5 WHY ANALYSIS
        ├── 3-6 factors (complex, systemic) → Use FISHBONE DIAGRAM
        └── Unknown/proactive assessment → Use FMEA
5 Why Analysis

Use when: Single-cause issues with linear causation, process deviations with clear failure point.

Template:

PROBLEM: [Clear, specific statement]

WHY 1: Why did [problem] occur?
BECAUSE: [First-level cause]
EVIDENCE: [Supporting data]

WHY 2: Why did [first-level cause] occur?
BECAUSE: [Second-level cause]
EVIDENCE: [Supporting data]

WHY 3: Why did [second-level cause] occur?
BECAUSE: [Third-level cause]
EVIDENCE: [Supporting data]

WHY 4: Why did [third-level cause] occur?
BECAUSE: [Fourth-level cause]
EVIDENCE: [Supporting data]

WHY 5: Why did [fourth-level cause] occur?
BECAUSE: [Root cause]
EVIDENCE: [Supporting data]

Example - Calibration Overdue:

PROBLEM: pH meter (EQ-042) found 2 months overdue for calibration

WHY 1: Why was calibration overdue?
BECAUSE: Equipment was not on calibration schedule
EVIDENCE: Calibration schedule reviewed, EQ-042 not listed

WHY 2: Why was it not on the schedule?
BECAUSE: Schedule not updated when equipment was purchased
EVIDENCE: Purchase date 2023-06-15, schedule dated 2023-01-01

WHY 3: Why was the schedule not updated?
BECAUSE: No process requires schedule update at equipment purchase
EVIDENCE: SOP-EQ-001 reviewed, no such requirement

WHY 4: Why is there no such requirement?
BECAUSE: Procedure written before equipment tracking was centralized
EVIDENCE: SOP last revised 2019, equipment system implemented 2021

WHY 5: Why has procedure not been updated?
BECAUSE: Periodic review did not assess compatibility with new systems
EVIDENCE: No review against new equipment system documented

ROOT CAUSE: Procedure review process does not assess compatibility
with organizational systems implemented after original procedure creation.
Fishbone Diagram Categories (6M)
CategoryFocus AreasTypical Causes
Man (People)Training, competency, workloadSkill gaps, fatigue, communication
Machine (Equipment)Calibration, maintenance, ageWear, malfunction, inadequate capacity
Method (Process)Procedures, work instructionsUnclear steps, missing controls
MaterialSpecifications, suppliers, storageOut-of-spec, degradation, contamination
MeasurementCalibration, methods, interpretationInstrument error, wrong method
Mother NatureTemperature, humidity, cleanlinessEnvironmental excursions

See references/rca-methodologies.md for complete method details and templates.

Root Cause Validation

Before proceeding to action planning, validate root cause:

  • Root cause can be verified with objective evidence
  • If root cause is eliminated, problem would not recur
  • Root cause is within organizational control
  • Root cause explains all observed symptoms
  • No other significant causes remain unaddressed

Corrective Action Planning

Develop effective actions addressing identified root causes:

  1. Define immediate containment actions
  2. Develop corrective actions targeting root cause
  3. Identify preventive actions for similar processes
  4. Assign responsibilities and resources
  5. Establish timeline with milestones
  6. Define success criteria and verification method
  7. Document in CAPA action plan
  8. Validation: Actions directly address root cause; success criteria are measurable
Action Types
TypePurposeTimelineExample
ContainmentStop immediate impact24-72 hoursQuarantine affected product
CorrectionFix the specific occurrence1-2 weeksRework or replace affected items
CorrectiveEliminate root cause30-90 daysRevise procedure, add controls
PreventivePrevent in other areas60-120 daysExtend solution to similar processes
Action Plan Components
ACTION PLAN TEMPLATE

CAPA Number: [CAPA-XXXX]
Root Cause: [Identified root cause]

ACTION 1: [Specific action description]
- Type: [ ] Containment [ ] Correction [ ] Corrective [ ] Preventive
- Responsible: [Name, Title]
- Due Date: [YYYY-MM-DD]
- Resources: [Required resources]
- Success Criteria: [Measurable outcome]
- Verification Method: [How success will be verified]

ACTION 2: [Specific action description]
...

IMPLEMENTATION TIMELINE:
Week 1: [Milestone]
Week 2: [Milestone]
Week 4: [Milestone]
Week 8: [Milestone]

APPROVAL:
CAPA Owner: _____________ Date: _______
Process Owner: _____________ Date: _______
QA Manager: _____________ Date: _______
Action Effectiveness Indicators
IndicatorTargetRed Flag
Action scopeAddresses root cause completelyTreats only symptoms
SpecificityMeasurable deliverablesVague commitments
TimelineAggressive but achievableNo due dates or unrealistic
ResourcesIdentified and allocatedNot specified
SustainabilityPermanent solutionTemporary fix

Effectiveness Verification

Verify corrective actions achieved intended results:

  1. Allow adequate implementation period (minimum 30-90 days)
  2. Collect post-implementation data
  3. Compare to pre-implementation baseline
  4. Evaluate against success criteria
  5. Verify no recurrence during verification period
  6. Document verification evidence
  7. Determine CAPA effectiveness
  8. Validation: All criteria met with objective evidence; no recurrence observed
Verification Timeline Guidelines
CAPA SeverityWait PeriodVerification Window
Critical30 days30-90 days post-implementation
Major60 days60-180 days post-implementation
Minor90 days90-365 days post-implementation
Verification Methods
MethodUse WhenEvidence Required
Data trend analysisQuantifiable issuesPre/post comparison, trend charts
Process auditProcedure compliance issuesAudit checklist, interview notes
Record reviewDocumentation issuesSample records, compliance rate
Testing/inspectionProduct quality issuesTest results, pass/fail data
Interview/observationTraining issuesInterview notes, observation records
Effectiveness Determination
Did recurrence occur during verification period?
├── Yes → CAPA INEFFECTIVE (re-investigate root cause)
└── No → Were all effectiveness criteria met?
    ├── Yes → CAPA EFFECTIVE (proceed to closure)
    └── No → Extent of gap?
        ├── Minor gap → Extend verification or accept with justification
        └── Significant gap → CAPA INEFFECTIVE (revise actions)

See references/effectiveness-verification-guide.md for detailed procedures.


CAPA Metrics and Reporting

Monitor CAPA program performance through key indicators.

Key Performance Indicators
MetricTargetCalculation
CAPA cycle time<60 days average(Close Date - Open Date) / Number of CAPAs
Overdue rate<10%Overdue CAPAs / Total Open CAPAs
First-time effectiveness>90%Effective on first verification / Total verified
Recurrence rate<5%Recurred issues / Total closed CAPAs
Investigation quality100% root cause validatedRoot causes validated / Total CAPAs
Aging Analysis Categories
Age BucketStatusAction Required
0-30 daysOn trackMonitor progress
31-60 daysMonitorReview for delays
61-90 daysWarningEscalate to management
>90 daysCriticalManagement intervention required
Management Review Inputs

Monthly CAPA status report includes:

  • Open CAPA count by severity and status
  • Overdue CAPA list with owners
  • Cycle time trends
  • Effectiveness rate trends
  • Source analysis (complaints, audits, NCs)
  • Recommendations for improvement

Reference Documentation

Root Cause Analysis Methodologies

references/rca-methodologies.md contains:

  • Method selection decision tree
  • 5 Why analysis template and example
  • Fishbone diagram categories and template
  • Fault Tree Analysis for safety-critical issues
  • Human Factors Analysis for people-related causes
  • FMEA for proactive risk assessment
  • Hybrid approach guidance
Effectiveness Verification Guide

references/effectiveness-verification-guide.md contains:

  • Verification planning requirements
  • Verification method selection
  • Effectiveness criteria definition (SMART)
  • Closure requirements by severity
  • Ineffective CAPA process
  • Documentation templates

Tools

CAPA Tracker
bash
# Generate CAPA status report
python scripts/capa_tracker.py --capas capas.json

# Interactive mode for manual entry
python scripts/capa_tracker.py --interactive

# JSON output for integration
python scripts/capa_tracker.py --capas capas.json --output json

# Generate sample data file
python scripts/capa_tracker.py --sample > sample_capas.json

Calculates and reports:

  • Summary metrics (open, closed, overdue, cycle time, effectiveness)
  • Status distribution
  • Severity and source analysis
  • Aging report by time bucket
  • Overdue CAPA list
  • Actionable recommendations
Sample CAPA Input
json
{
  "capas": [
    {
      "capa_number": "CAPA-2024-001",
      "title": "Calibration overdue for pH meter",
      "description": "pH meter EQ-042 found 2 months overdue",
      "source": "AUDIT",
      "severity": "MAJOR",
      "status": "VERIFICATION",
      "open_date": "2024-06-15",
      "target_date": "2024-08-15",
      "owner": "J. Smith",
      "root_cause": "Procedure review gap",
      "corrective_action": "Updated SOP-EQ-001"
    }
  ]
}

Regulatory Requirements

ISO 13485:2016 Clause 8.5
Sub-clauseRequirementKey Activities
8.5.2 Corrective ActionEliminate cause of nonconformityNC review, cause determination, action evaluation, implementation, effectiveness review
8.5.3 Preventive ActionEliminate potential nonconformityTrend analysis, cause determination, action evaluation, implementation, effectiveness review
FDA 21 CFR 820.100

Required CAPA elements:

  • Procedures for implementing corrective and preventive action
  • Analyzing quality data sources (complaints, NCs, audits, service records)
  • Investigating cause of nonconformities
  • Identifying actions needed to correct and prevent recurrence
  • Verifying actions are effective and do not adversely affect device
  • Submitting relevant information for management review
Common FDA 483 Observations
ObservationRoot Cause Pattern
CAPA not initiated for recurring issueTrend analysis not performed
Root cause analysis superficialInadequate investigation training
Effectiveness not verifiedNo verification procedure
Actions do not address root causeSymptom treatment vs. cause elimination

Show full SKILL.md (792 more words)Show less

Troubleshooting

ProblemPossible CauseResolution
Root cause analysis yields only symptomsInvestigation stopped too early or used wrong RCA methodApply the RCA Method Selection Decision Tree; ensure at least 5 levels of "why" with evidence at each level
CAPA effectiveness verification fails repeatedlyCorrective action addresses symptoms, not true root causeRe-open investigation, consider hybrid RCA approach (e.g., Fishbone + 5-Why), involve additional subject matter experts
CAPA cycle times consistently exceed 60-day targetInsufficient resources allocated or unclear ownershipEscalate during management review; assign dedicated CAPA coordinator; break complex CAPAs into phased actions
Overdue CAPA rate exceeds 10%Lack of automated tracking or reminder systemImplement automated alerts via QMS software; run python scripts/capa_tracker.py --capas capas.json weekly to identify aging items
Auditors cite "superficial root cause analysis"Inadequate training on RCA methodologiesConduct RCA methodology training for investigation teams; use templates from references/rca-methodologies.md; require evidence at each analysis step
Recurring issues despite closed CAPAsPreventive actions not extended to similar processesDuring action planning, explicitly assess all analogous processes; add preventive actions targeting systemic causes, not just the specific instance
Stakeholders disagree on CAPA severity classificationNo standardized severity criteria appliedUse the CAPA Necessity Determination table and Severity definitions consistently; document classification rationale with objective evidence

Success Criteria

  • First-time effectiveness rate exceeds 90% -- verified through post-implementation data collection showing no recurrence during the verification window
  • Average CAPA cycle time under 60 days -- measured from open date to close date across all severity levels, tracked via capa_tracker.py metrics
  • Overdue rate maintained below 10% -- monitored through aging analysis with escalation triggers at 61-day and 90-day thresholds
  • 100% of root causes validated with objective evidence -- every root cause passes the validation checklist (explains all symptoms, elimination prevents recurrence, within organizational control)
  • All critical and major CAPAs include preventive actions -- corrective actions address the specific occurrence while preventive actions extend solutions to analogous processes
  • Management review receives monthly CAPA status reports -- including open count by severity, overdue list, cycle time trends, and effectiveness rate trends
  • Recurrence rate below 5% -- tracked by monitoring closed CAPAs for reappearance of the same issue type within 12 months of closure

Scope & Limitations

In Scope:

  • CAPA investigation workflow from trigger event through closure
  • Root cause analysis using 5-Why, Fishbone (6M), Fault Tree Analysis, Human Factors Analysis, and FMEA methodologies
  • Corrective and preventive action planning, implementation tracking, and effectiveness verification
  • CAPA metrics calculation, aging analysis, and management reporting
  • Alignment with ISO 13485:2016 Clause 8.5 and FDA 21 CFR 820.100 requirements

Out of Scope:

  • This skill does not replace a validated eQMS (electronic Quality Management System) for production CAPA tracking -- it provides analysis templates and metric calculations
  • Statistical process control and advanced trend analysis requiring specialized SPC software
  • Regulatory submission preparation (use fda-consultant-specialist or mdr-745-specialist for submission-related CAPAs)
  • Supplier CAPA management beyond internal investigation (use quality-manager-qms-iso13485 for supplier qualification)
  • Clinical investigation CAPAs requiring medical/scientific expertise beyond procedural guidance

Important Notes:

  • Under the FDA QMSR (effective February 2, 2026), CAPA requirements align with ISO 13485:2016 Clause 8.5 rather than the legacy 21 CFR 820.100 structure -- this skill covers both frameworks
  • The capa_tracker.py tool works with JSON input and does not connect to live QMS databases; export data from your eQMS for analysis

Integration Points

SkillIntegrationWhen to Use
quality-manager-qms-iso13485CAPA findings feed into QMS process improvements and supplier corrective actionsWhen root cause involves QMS process gaps or supplier nonconformances
qms-audit-expertAudit findings are a primary CAPA source; CAPA closure evidence supports audit follow-upWhen CAPAs originate from internal or external audit findings
risk-management-specialistCAPA outcomes update risk assessments; FMEA results may trigger preventive CAPAsWhen root cause analysis reveals previously unassessed risks
fda-consultant-specialistFDA 483 observations and warning letters require formal CAPA responsesWhen CAPA originates from FDA inspection findings
mdr-745-specialistEU MDR vigilance reports and FSCA may trigger CAPAs; CAPA data feeds PMS/PSURWhen post-market surveillance identifies safety or performance issues
quality-documentation-managerDocument control updates resulting from CAPA actions; 21 CFR Part 11 compliance for electronic CAPA recordsWhen corrective actions require SOP revisions or new document creation

Tool Reference

capa_tracker.py

Tracks CAPA status, calculates metrics, identifies overdue items, and generates management review reports.

FlagRequiredDescription
--capas <file>Yes (unless --interactive or --sample)Path to JSON file containing CAPA records
--interactiveNoLaunch interactive mode for manual CAPA entry
--output <format>NoOutput format: json for machine-readable, default is human-readable text
--sampleNoGenerate a sample CAPA JSON file to stdout for use as a template

Calculated Metrics:

  • Total, open, closed, and overdue CAPA counts
  • Average cycle time (days from open to close)
  • First-time effectiveness rate (effective on first verification / total verified)
  • Status distribution, severity breakdown, and source analysis
  • Aging report bucketed by 0-30, 31-60, 61-90, and 90+ days
  • Overdue CAPA list with owners and days past target

Example:

bash
# Generate sample data, then analyze
python scripts/capa_tracker.py --sample > sample_capas.json
python scripts/capa_tracker.py --capas sample_capas.json
python scripts/capa_tracker.py --capas sample_capas.json --output json

© borghei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts, references) in ra-qm-team/capa-officer of borghei/Claude-Skills.

  • SKILL.md
  • references/effectiveness-verification-guide.md
  • references/rca-methodologies.md
  • scripts/capa_tracker.py

Open the folder on GitHubat commit 4a698e8

Compare with similar skills

Capa Officer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Capa Officer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Capa Officer this skillborghei/Claude-Skills886—~5.5kAutomated safety check: PassMIT
Code Design Rationale Investigatorcursor/plugins10k9 repos~2.6kAutomated safety check: PassNone
OpenLogi macOS Permissions TriageAprilNEA/OpenLogi23k—~2.5kAutomated safety check: NotesApache-2.0
Bug Finder for daisyUIsaadeghi/daisyui43k—~2.3kAutomated safety check: PassMIT
Root Cause Debugginggarrytan/gstack136k—~1.4kAutomated safety check: PassMIT
Review PRapache/shardingsphere21k—~6.4kAutomated safety check: PassApache-2.0

Similar skills

  • Official

    Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.

    10k GitHub starsUsed in 9 repos~2.6k tokens
    DevelopmentAuto-check passed
  • Decides whether an OpenLogi device problem on macOS is a privacy-permission (TCC) problem, using agent log lines, and says which identity needs which grant.

    23k GitHub stars~2.5k tokensUpdated today
    DevelopmentAuto-check: notes
  • Bug Finder for daisyUI

    saadeghi/daisyui

    Investigates suspected bugs in the daisyUI monorepo through read-only analysis, then writes a decision-ready fix plan in tmp/bugs without changing any product code.

    43k GitHub stars~2.3k tokensUpdated today
    DevelopmentAuto-check passed
  • Root Cause Debugging

    garrytan/gstack

    Investigates bugs, errors and stack traces in phases and requires a root-cause hypothesis to be confirmed before any fix is written.

    136k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Review PR

    apache/shardingsphere

    Review Apache ShardingSphere or user-authorized downstream pull requests and PR discussions from public or authorized repository evidence.

    21k GitHub stars~6.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Graph-Based Bug Tracing

    tirth8205/code-review-graph

    Traces a bug through a code knowledge graph, following callers, callees and execution flow before opening source files, within a small token budget.

    32k GitHub starsUsed in 1 repo~287 tokens
    DevelopmentAuto-check passed

More from borghei/Claude-Skills

All 354 skills in this repo
  • Agent Harness

    borghei/Claude-Skills

    Test and evaluation harness for AI agents — scenario suites, deterministic replay, regression diffing, cost and latency budgets.

    886 GitHub stars~3.1k tokensUpdated 2 days ago
    Auto-check passed
  • Agents In The Team

    borghei/Claude-Skills

    Run delivery when AI coding and ops agents take tickets. An agent skill from borghei/Claude-Skills.

    886 GitHub stars~4.2k tokensUpdated 2 days ago
    Auto-check passed
  • AI Content Disclosure

    borghei/Claude-Skills

    Check AI-generated marketing content and reviews for required disclosures under the EU AI Act, FTC rules and platform AI-label policies.

    886 GitHub stars~3.4k tokensUpdated 2 days ago
    Auto-check passed
  • AI Prototyping

    borghei/Claude-Skills

    Idea to AI-generated prototype to customer validation to engineering handoff.

    886 GitHub stars~3.6k tokensUpdated 2 days ago
    Auto-check passed
  • Analytics Engineer

    borghei/Claude-Skills

    Analytics engineering across data modeling, dbt, transformation, and semantic layers.

    886 GitHub stars~3.4k tokensUpdated 2 days ago
    Auto-check passed
  • Ansoff Matrix

    borghei/Claude-Skills

    Ansoff Matrix — 4-quadrant framework for growth options: market penetration, market/product development, and diversification.

    886 GitHub stars~2.2k tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Capa Officer

What does Capa Officer do?

CAPA system management for medical device QMS, covering root cause analysis, corrective action planning, and effectiveness verification. Capa Officer is an agent skill from borghei/Claude-Skills. CAPA system management for medical device QMS, covering root cause analysis, corrective action planning, and effectiveness verification.

When should I use Capa Officer?

Capa Officer fits situations like: CAPA investigations; 5-Why and fishbone analysis; corrective action tracking.

How do I install Capa Officer in Claude Code?

Run `npx skills add borghei/Claude-Skills --skill capa-officer -a claude-code`. Or copy the skill folder (ra-qm-team/capa-officer in borghei/Claude-Skills) into .claude/skills/capa-officer in your project. Claude Code loads it when a task matches its description.

How do I install Capa Officer in Codex?

Run `npx skills add borghei/Claude-Skills --skill capa-officer -a codex`. Or copy the skill folder (ra-qm-team/capa-officer in borghei/Claude-Skills) into .agents/skills/capa-officer in your project. Codex loads it when a task matches its description.

Can I use Capa Officer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add borghei/Claude-Skills --skill capa-officer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/capa-officer, .gemini/skills/capa-officer, .github/skills/capa-officer and .opencode/skills/capa-officer in your project.

What does Capa Officer need to run?

Going by SKILL.md and its folder, Capa Officer needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Capa Officer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Capa Officer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Capa Officer use?

Capa Officer is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Capa Officer use?

About 5.5k tokens (SKILL.md is roughly 22k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.4k tokens, read only when the agent opens those files.

What are the alternatives to Capa Officer?

Skills that share tags, products or a category with Capa Officer: Code Design Rationale Investigator (cursor/plugins, 10k stars), OpenLogi macOS Permissions Triage (AprilNEA/OpenLogi, 23k stars), Bug Finder for daisyUI (saadeghi/daisyui, 43k stars) and Root Cause Debugging (garrytan/gstack, 136k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Capa Officer?

borghei (a GitHub user) maintains it in borghei/Claude-Skills, which has 886 GitHub stars. The repository holds 354 skills in this directory. The repository was last updated on October 7, 2026.

Source: borghei/Claude-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.