Agent skill

Car Corrective Action

by hashgraph-online in hashgraph-online/awesome-codex-plugins

Write a corrective action report, CAPA, respond to an NCR or audit finding, or document an 8D D5 root cause action.

MITAuto-check passedDevelopment

Install Car Corrective Action

skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill car-corrective-action -a claude-code

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

GitHub CLI
$ gh skill install hashgraph-online/awesome-codex-plugins car-corrective-action --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/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/RBraga01/Quality-Engineering-Skills/skills/documentation/car-corrective-action .claude/skills/car-corrective-action && 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
car-corrective-action
GitHub stars
1.3k
Token cost
~2.6k tokens
SKILL.md length
1,287 words
Files
2 (incl. references)
Skills in repo
714
Repo updated
First seen
Licence
MIT

At a glance

Write a corrective action report, CAPA, respond to an NCR or audit finding, or document an 8D D5 root cause action.

  • Works in 10 steps: Header → Problem summary → Immediate containment (if not already in… → …
  • Any quality escape requiring documented systemic corrective action
  • SKILL.md covers When to use, Key distinction from NCR, CAR structure and Closure criteria, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Car Corrective Action is an agent skill from hashgraph-online/awesome-codex-plugins. Write a corrective action report, CAPA, respond to an NCR or audit finding, or document an 8D D5 root cause action. Covers the full CAR structure: root cause analysis, corrective actions, implementation evidence, and verification of effectiveness (VOE) per ISO 9001 §10.2. Use for any quality escape requiring documented systemic corrective action.

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/car-template.md`).

It sits in Development, covering Root cause analysis and Audit readiness. The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is MIT.

When your agent uses it

  • Any quality escape requiring documented systemic corrective action
  • Tasks that involve Root cause analysis
  • Tasks that involve Audit readiness

Example prompts

  • “/car-corrective-action”

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. Header
  2. Problem summary
  3. Immediate containment (if not already in NCR)
  4. Root cause analysis
  5. Corrective actions
  6. Implementation evidence
  7. Verification of effectiveness (VOE)
  8. AP revision (AIAG-VDA, if applicable)
  9. Systemic prevention and horizontal deployment
  10. Lessons learned

What it can do on your machine

Read from SKILL.md and the folder at commit 9e7b281. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Car Corrective Action loads about 2.6k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 93 tokens; SKILL.md has 1,287 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~93
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~10k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from hashgraph-online/awesome-codex-plugins at commit 9e7b281, republished under its MIT licence (© hashgraph-online). 1,287 words, ~2,648 tokens.

Download SKILL.mdSave it as .claude/skills/car-corrective-action/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
car-corrective-action
description
Write a corrective action report, CAPA, respond to an NCR or audit finding, or document an 8D D5 root cause action. Covers the full CAR structure: root cause analysis, corrective actions, implementation evidence, and verification of effectiveness (VOE) per ISO 9001 §10.2. Use for any quality escape requiring documented systemic corrective action.
license
MIT
metadata.author
RBraga01
metadata.version
1.1
metadata.iso-9001
10.2
metadata.iatf-16949
10.2.3
metadata.domain
quality-engineering
metadata.subdomain
documentation
metadata.industries
automotive,electronics,aerospace,medical,general
metadata.status
approved
metadata.created
2026-06-01

Corrective Action Request (CAR) Writing

When to use

A CAR is written in response to:

  • An NCR requiring permanent corrective action
  • A customer complaint
  • An internal or external audit finding (Major or Minor non-conformance)
  • A recurring non-conformance requiring systemic correction

The CAR is the documented evidence that the problem was analysed, corrected, and prevented from recurring. ISO 9001 §10.2.1 requires documented information of the actions taken and their results. For IATF 16949 audit Major NCs, CARs must typically be closed within 90 days; check the applicable CSR for customer-specific closure deadlines.

Key distinction from NCR

NCRCAR
What is wrong (objective facts)Why it is wrong + what is being done about it
Detection point and evidenceRoot cause analysis + actions
Severity and dispositionVerification of effectiveness
Written immediatelyWritten after investigation

A CAR references the NCR but extends it into corrective action territory.


CAR structure

1. Header
FieldContent
CAR numberTraceable to NCR or audit finding
NCR / finding referenceLinks this CAR to the trigger event
Date opened
OwnerResponsible person (name, not function)
Target closure date
Closure authorityNamed person with authority to close this CAR (quality manager or equivalent)
Actual closure date(filled on closure)
2. Problem summary

One or two sentences summarising the NCR or finding. Objective, factual. Must match the NCR description exactly — no new interpretation.

Example:

"47 of 200 connector units in lot 2026-05-12-A had pin insertion depth 0.6–1.5 mm below lower specification limit (5.0 ± 0.3 mm). Detected at incoming inspection (NCR-2026-0047)."

3. Immediate containment (if not already in NCR)

Confirm containment is in place. If documented in the NCR, reference it. If not yet done, define it here.

4. Root cause analysis

This is the core of the CAR. Use structured methodology:

Recommended tools:

  • 5-Why for linear cause chains
  • Fishbone for complex or multi-factor problems

Identify two root causes:

  1. Root cause of occurrence — why did the non-conformance happen?
  2. Root cause of escape — why was it not detected before it reached the next customer?

Document the chain, not just the conclusion:

Root cause of occurrence:
Why: Connector pin depth OOS → Why: insertion force insufficient → 
Why: pneumatic jig set to wrong pressure → Why: pressure setpoint not in work instruction →
Root cause: Work instruction for Station 3 does not specify jig pressure setpoint.

Root cause of escape:
Why: Not detected at our outgoing inspection → Why: no depth measurement in outgoing
inspection plan → Root cause: Control Plan does not include pin depth at outgoing.

Validation: state how the root cause was confirmed. Acceptable validation methods:

  • Reproduction test (demonstrated that removing/restoring the root cause produces/prevents the defect)
  • Data correlation (statistical relationship between root cause variable and defect occurrence)
  • Physical evidence (inspection of the failed part or process reveals the causal mechanism)
  • Direct record review (confirms the absence of the required control)

A root cause supported only by team opinion (not validated by evidence) cannot be used as the basis for CAR closure.

5. Corrective actions

One corrective action for each root cause. The action must directly address the root cause — not a symptom.

#Root cause addressedCorrective actionOwnerTarget date
1WI missing jig pressureUpdate WI-Station-3 to specify jig pressure 4.5 ± 0.2 bar[Name]2026-06-05
2CP no depth check at outgoingAdd pin depth measurement to Control Plan at outgoing, 10% sample, n=5 per batch[Name]2026-06-05

Action quality check:

  • Does this action, if implemented, prevent the root cause from occurring again?
  • Is it specific (who does what, by when)?
  • Can its implementation be verified?
6. Implementation evidence

For each corrective action, document that it was actually implemented:

ActionEvidence of implementationDate verified
WI updatedWI-Station-3 rev C, approved 2026-06-04, attached2026-06-04
Training conductedTraining attendance record attached (4 operators)2026-06-04
Control Plan updatedCP rev F, approved 2026-06-04, attached2026-06-04

Documents must be revised with a new revision number and approval date. Verbal implementation is not evidence.

7. Verification of effectiveness (VOE)

This is where most CARs fail. The action is implemented, but nobody checks whether it actually prevents the defect.

VOE requirements (ISO 9001 §10.2.1.e):

  1. Method: how will you check if the corrective action worked? (data collection, monitoring period)
  2. Metric: what will you measure? (defect rate, inspection results)
  3. Volume/duration: what sample size or time period constitutes sufficient evidence?
  4. Target: what result confirms the action was effective?

VOE minimum volume guidance:

  • For a defect with known base rate: the VOE sample must be large enough to observe at least one recurrence if the action had failed. Example: if baseline defect rate was 5%, a zero-defect sample of 60 units gives 95% confidence the rate is now below 5%.
  • For process parameter changes: minimum 30 consecutive production cycles under the new conditions, or as defined by the Control Plan sampling frequency × 3 periods.
  • For detection control improvements: minimum one full inspection cycle of the affected product family with zero escapes.
  • Minimum in all cases: state the volume used and the basis for choosing it. "Zero defects in 10 units" is not a valid VOE for a high-volume process.

VOE result:

  • Record the actual results after the monitoring period
  • State: Effective / Not effective
  • If not effective: return to root cause analysis and repeat
Show full SKILL.md (493 more words)Show less
8. AP revision (AIAG-VDA, if applicable)

If the non-conformance relates to a PFMEA failure mode with an Action Priority (AP) rating:

  • After verified implementation of the corrective action, the PFMEA must be updated with a revised S, O, and/or D rating
  • The revised AP (AP-revised) must reflect the improvement — it must be lower than the original AP or documented with justification if unchanged
  • Revised AP is recorded only after VOE is complete, not at the time of action planning
9. Systemic prevention and horizontal deployment

Ask: could this same root cause exist in similar parts, processes, or product families?

If yes:

  • List the similar areas
  • Document the actions taken to extend the corrective action
  • Evidence that horizontal deployment is complete
10. Lessons learned

One or two sentences capturing the key learning for future reference:

"Work instruction templates for assembly stations must include all process parameter setpoints. Control Plans must cover outgoing inspection of all safety-relevant characteristics."

File in the lessons learned register and reference in PFMEA update.


Closure criteria

A CAR may only be closed when ALL of the following are true, and the closure authority (named in the header) has signed off:

  • Root causes of occurrence and escape are documented with validation evidence
  • Corrective actions are implemented and documented with revision numbers and approval dates
  • VOE is complete with documented sample volume and confirms effectiveness
  • PFMEA is updated (revised failure mode entry, revised AP if applicable)
  • Control Plan is updated (if detection control changed)
  • Work Instructions are updated (if process control changed)
  • Horizontal deployment is documented
  • Customer notified of closure (if CAR was triggered by customer complaint or CSR-required notification)
  • Closure authority sign-off obtained

Common mistakes

  • "Retrain operators" as a corrective action for human error — this is never sufficient alone; the system that allowed the error must be changed
  • Closing without VOE — the most common reason for recurring non-conformances
  • VOE on insufficient sample — "zero defects in 5 units" is not effectiveness verification; define the minimum volume before collecting data
  • Implementing actions without updating PFMEA and Control Plan — next audit will find the gap
  • Generic actions — "review procedures" → not specific; must state which procedure, revised to say what, by whom, by when
  • Closing without named authority sign-off — any team member closing a CAR without defined authority is a governance gap
  • Missing AP revision — when PCA addresses a PFMEA failure mode, the revised AP must be recorded after VOE

Output Format

At the start of each use, ask the user:

"How would you like to receive the output? A — Structured Markdown (formatted tables and sections, ready to copy) B — Plain tables (simplified structure for Excel or Word) C — Narrative report (flowing text for a formal document or email)

Default: A."

Adapt all output sections to the chosen format. If the platform or session context already defines a format preference, skip this question.

Changelog

VersionDateAuthorChange
1.02026-06-01@RBraga01Initial release
1.12026-06-04@migmccExpanded CAR linkage to D5-D6, added effectiveness verification requirements

© hashgraph-online, 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 1 other file (references) in plugins/RBraga01/Quality-Engineering-Skills/skills/documentation/car-corrective-action of hashgraph-online/awesome-codex-plugins.

  • SKILL.md
  • references/car-template.md

Open the folder on GitHubat commit 9e7b281

Compare with similar skills

Car Corrective Action 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.

Car Corrective Action compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Car Corrective Action this skillhashgraph-online/awesome-codex-plugins1.3k—~2.6kAutomated 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
A2ui Remediate Problema2ui-project/a2ui17k—~1.5kAutomated safety check: PassApache-2.0
Root Cause Debugginggarrytan/gstack136k—~1.4kAutomated safety check: PassMIT

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
  • A2ui Remediate Problem

    a2ui-project/a2ui

    Remediates a specific recommendation from an A2UI compliance report issue, or resolves any general GitHub issue, by inspecting context, implementing minimal targeted fixes, verifying tests, creating…

    17k GitHub stars~1.5k 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

More from hashgraph-online/awesome-codex-plugins

All 714 skills in this repo
  • Anime Reaction Gif

    hashgraph-online/awesome-codex-plugins

    Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.

    1.3k GitHub stars~922 tokensUpdated today
    Auto-check passed
  • Calibredb

    hashgraph-online/awesome-codex-plugins

    Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).

    1.3k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Rust API Test Harness

    hashgraph-online/awesome-codex-plugins

    A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…

    1.3k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Art

    hashgraph-online/awesome-codex-plugins

    Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…

    1.3k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Calle

    hashgraph-online/awesome-codex-plugins

    Use CALL-E from Codex through the calle CLI. An agent skill from hashgraph-online/awesome-codex-plugins.

    1.3k GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Game Balance Economy

    hashgraph-online/awesome-codex-plugins

    Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.

    1.3k GitHub stars~618 tokensUpdated today
    Auto-check passed

Categories

Questions about Car Corrective Action

What does Car Corrective Action do?

Write a corrective action report, CAPA, respond to an NCR or audit finding, or document an 8D D5 root cause action. Car Corrective Action is an agent skill from hashgraph-online/awesome-codex-plugins. Write a corrective action report, CAPA, respond to an NCR or audit finding, or document an 8D D5 root cause action.

When should I use Car Corrective Action?

Car Corrective Action fits situations like: any quality escape requiring documented systemic corrective action; tasks that involve Root cause analysis; tasks that involve Audit readiness.

How do I install Car Corrective Action in Claude Code?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill car-corrective-action -a claude-code`. Or copy the skill folder (plugins/RBraga01/Quality-Engineering-Skills/skills/documentation/car-corrective-action in hashgraph-online/awesome-codex-plugins) into .claude/skills/car-corrective-action in your project. Claude Code loads it when a task matches its description.

How do I install Car Corrective Action in Codex?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill car-corrective-action -a codex`. Or copy the skill folder (plugins/RBraga01/Quality-Engineering-Skills/skills/documentation/car-corrective-action in hashgraph-online/awesome-codex-plugins) into .agents/skills/car-corrective-action in your project. Codex loads it when a task matches its description.

Can I use Car Corrective Action 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 hashgraph-online/awesome-codex-plugins --skill car-corrective-action -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/car-corrective-action, .gemini/skills/car-corrective-action, .github/skills/car-corrective-action and .opencode/skills/car-corrective-action in your project.

What does Car Corrective Action need to run?

SKILL.md names no scripts, command-line tools or credentials: Car Corrective Action is instructions for the agent only.

Does Car Corrective Action 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 Car Corrective Action 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. Review the folder before installing.

What licence does Car Corrective Action use?

Car Corrective Action 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 Car Corrective Action use?

About 2.6k tokens (SKILL.md is roughly 11k 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 7.6k tokens, read only when the agent opens those files.

What are the alternatives to Car Corrective Action?

Skills that share tags, products or a category with Car Corrective Action: 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 A2ui Remediate Problem (a2ui-project/a2ui, 17k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Car Corrective Action?

hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,255 GitHub stars. The repository holds 714 skills in this directory. The repository was last updated on October 9, 2026.

Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.