Capa Officer

What it does

When your agent uses it

• Running CAPA investigations
• Fishbone diagrams
• Root cause determination
• Corrective action tracking

Example prompts

• “/capa-officer”

Requirements

• Python 3

Workflow steps

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

1. 1Document trigger event with objective evidence
2. 2Assess significance and determine CAPA necessity
3. 3Form investigation team with relevant expertise
4. 4Collect data and evidence systematically
5. 5Select and apply appropriate RCA methodology
6. 6Identify root cause(s) with supporting evidence
7. 7Develop corrective and preventive actions
8. 8Validation: 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 19392f7. 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 2 files 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 4k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 87 tokens; SKILL.md has 1,256 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~87

When it runs · the whole SKILL.md, loaded when a task matches

~4k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~11k

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

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 alirezarezvani/claude-skills at commit 19392f7, republished under its MIT licence (© alirezarezvani). 1,256 words, ~3,994 tokens.

name

capa-officer

description

CAPA system management for medical device QMS. Covers root cause analysis, corrective action planning, effectiveness verification, and CAPA metrics. Use when running CAPA investigations, 5-Why analysis, fishbone diagrams, root cause determination, corrective action tracking, effectiveness verification, or CAPA program optimization.

triggers

CAPA investigation, root cause analysis, 5 Why analysis, fishbone diagram, corrective action, preventive action, effectiveness verification, CAPA metrics…

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

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]

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.

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: _______

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)

# 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

{
  "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"
    }
  ]
}

© alirezarezvani, 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 4 other files (scripts, references) in ra-qm-team/skills/capa-officer of alirezarezvani/claude-skills.

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

Open the folder on GitHubat commit 19392f7

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in alirezarezvani/claude-skills, which our catalogue first saw on October 7, 2026.

• LeoYeAI/openclaw-master-skillsskills/capa-officer