Run a PDCA cycle, Plan Do Check Act improvement cycle, or structured improvement project.

MITAuto-check passedDevelopment

Install Pdca Improvement

skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill pdca-improvement -a claude-code

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

GitHub CLI
$ gh skill install hashgraph-online/awesome-codex-plugins pdca-improvement --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/problem-solving/pdca-improvement .claude/skills/pdca-improvement && 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
pdca-improvement
GitHub stars
1.3k
Token cost
~2.1k tokens
SKILL.md length
1,008 words
Files
2 (incl. references)
Skills in repo
714
Repo updated
First seen
Licence
MIT

At a glance

Run a PDCA cycle, Plan Do Check Act improvement cycle, or structured improvement project.

  • Works in 4 steps: Define the current situation → Analyse root cause → Develop the improvement plan → …
  • Process optimisation
  • SKILL.md covers When to use, Prerequisites, Workflow and Gate summary, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Pdca Improvement is an agent skill from hashgraph-online/awesome-codex-plugins. Run a PDCA cycle, Plan Do Check Act improvement cycle, or structured improvement project. Guides through problem analysis, piloting, verification, and standardisation. Distinguished from 8D: PDCA is for proactive improvement initiatives, 8D is for reactive defect response. Use for process optimisation, lessons learned implementation, and quality objectives.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/pdca-examples.md`).

It sits in Development. 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

  • Process optimisation
  • Lessons learned implementation
  • Quality objectives

Example prompts

  • “/pdca-improvement”

Workflow steps

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

  1. Define the current situation
  2. Analyse root cause
  3. Develop the improvement plan
  4. Define the pilot scope

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

Pdca Improvement loads about 2.1k tokens when it runs, and up to ~7.5k if it reads all its reference files. Until then it costs about 94 tokens; SKILL.md has 1,008 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~94
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.5k

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). 1,008 words, ~2,053 tokens.

Download SKILL.mdSave it as .claude/skills/pdca-improvement/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
pdca-improvement
description
Run a PDCA cycle, Plan Do Check Act improvement cycle, or structured improvement project. Guides through problem analysis, piloting, verification, and standardisation. Distinguished from 8D: PDCA is for proactive improvement initiatives, 8D is for reactive defect response. Use for process optimisation, lessons learned implementation, and quality objectives.
license
MIT
metadata.author
RBraga01
metadata.version
1.1
metadata.iso-9001
10.3
metadata.iatf-16949
10.3.1
metadata.domain
quality-engineering
metadata.subdomain
problem-solving
metadata.industries
automotive,electronics,aerospace,medical,general
metadata.status
approved
metadata.created
2026-06-01

PDCA Improvement Cycle

When to use

Use PDCA for:

  • Continuous improvement initiatives (not problem reactions — use 8D for that)
  • Implementing a process optimisation with uncertain outcome
  • Piloting a change before full deployment
  • Structured improvement from lessons learned or audit findings
  • Meeting a quality objective that requires a new approach

Key distinction from 8D: PDCA is proactive or slow-burn improvement. 8D is reactive to a specific defect or failure. Both use root cause analysis, but PDCA has a broader scope and a pilot step before full deployment.

When PDCA is used for corrective action (e.g., responding to an audit finding or recurring NC): a Corrective Action Request (CAR) must also be opened to document root cause, actions, and VOE per ISO 9001 §10.2. PDCA is the improvement methodology; the CAR is the governance record.

Prerequisites

  • Improvement goal defined (with target metric)
  • Baseline data available (current performance)
  • Owner and resources assigned

Workflow

PLAN — Analyse and define the approach
  1. Define the current situation

    • What is the problem or improvement opportunity?
    • What is the current measured performance? (baseline)
    • What is the target? (SMART: Specific, Measurable, Achievable, Relevant, Time-bound)
  2. Analyse root cause

    • Use Fishbone and 5-Why to understand why current performance is below target
    • Use data: Pareto charts, run charts, capability studies
  3. Develop the improvement plan

    • What specific actions will close the gap?
    • Who is responsible for each action?
    • What is the timeline?
    • What resources are needed?
    • What risks does the change introduce? Review the applicable PFMEA — does this change add or remove a failure mode? Does it affect any existing prevention or detection control?
  4. Define the pilot scope

    • Which process, line, or area will pilot the change?
    • What volume or duration is needed to validate effectiveness? Define this before starting the pilot — do not decide after seeing results.
    • What will you measure, and how?

Pilot volume guidance: as a minimum, the pilot should produce enough output to statistically distinguish signal from noise. Typical references:

  • Process capability change: minimum 30 consecutive cycles or units under the new conditions
  • Defect rate reduction: minimum volume to yield at least 5 expected events at the old rate (e.g., if baseline defect rate = 2%, minimum pilot = 250 units)
  • Time-dependent improvement: minimum 4 weeks of sustained performance data

Plan gate: Is the root cause understood? Is the pilot scope defined with explicit volume/duration minimum? Is success measurable against a specific target?


DO — Implement (pilot)
  1. Implement the planned changes in the pilot scope only
  2. Train affected personnel
  3. Execute and collect data during the pilot
  4. Document what actually happened vs. what was planned (deviations are data)

Do not deploy broadly at this stage. The pilot is to learn, not to commit.


CHECK — Verify results

Compare pilot results against the Plan targets:

MetricBaselineTargetPilot resultGap closed?
[KPI 1]
[KPI 2]

Ask:

  • Did the change produce the expected improvement?
  • Were there any unexpected negative effects?
  • Is the improvement sustainable (stable over time) or a one-time effect?
  • Was the pilot conducted under representative conditions (same operators, same materials, same environment as production)?

Check gate:

  • If target met → proceed to Act (standardise)
  • If partially met → revise Plan, run another Do-Check cycle
  • If not met → return to Plan, re-analyse root cause

ACT — Standardise or revise

If the pilot succeeded:

  1. Update process documents: work instructions, control plan, PFMEA — each must be revised to reflect the new process
  2. If the PFMEA includes failure modes related to the improved process step, update affected S/O/D ratings and AP
  3. Deploy to all applicable areas (horizontal deployment) — list each area and confirm deployment is complete
  4. Train all affected personnel — training records required
  5. Set up ongoing monitoring to confirm the improvement holds
  6. Share lessons learned — enter in lessons learned register

If the pilot failed or was inconclusive:

  1. Document what was learned
  2. Revise the Plan (new root cause hypothesis or new approach)
  3. Repeat the cycle

Do not standardise an unverified change. Standardising a failed pilot permanently embeds the problem.


Show full SKILL.md (344 more words)Show less
Required PDCA documentation (ISO 9001 §10.3)

For the cycle to be auditable, the following records must exist at closure:

  • Baseline measurement with data source and date
  • Root cause analysis (fishbone or 5-Why output)
  • Pilot plan with explicit volume/duration minimum and success criteria
  • Pilot execution data (before/after comparison)
  • Check gate decision (proceed / revise / restart) with supporting data
  • Updated PFMEA, Control Plan, and Work Instructions (if applicable) with new revision numbers and approval dates
  • Training records for all affected personnel
  • Horizontal deployment log (areas assessed, actions taken)
  • Lessons learned register entry

Gate summary

GateKey questionPass criterion
PlanIs root cause understood and pilot scoped?Root cause confirmed, target measurable, pilot volume/duration defined
DoWas the pilot conducted as planned?Actions implemented, data collected per plan
CheckDid the change achieve the target?Target metric met or exceeded; minimum pilot volume reached
ActAre documents updated and deployment complete?PFMEA/CP/WI revised, training done, horizontal deployment documented

Common mistakes

  • Skipping Plan — jumping straight to Do without understanding root cause
  • Undefined pilot volume — deciding after the pilot how much data is "enough"; set the minimum before starting
  • Skipping Check — deploying broadly after pilot without verifying data
  • Treating Act as permanent before Check — standardising before the pilot result is confirmed
  • One cycle only — PDCA is a cycle; if the first cycle doesn't solve it, run another
  • Using PDCA for urgent defects — for customer complaints or safety issues, use 8D instead
  • Not updating PFMEA — a process change without PFMEA update leaves the risk register inaccurate

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@migmccPolished PDCA cycle workflow and D6 verification integration

© 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/problem-solving/pdca-improvement of hashgraph-online/awesome-codex-plugins.

  • SKILL.md
  • references/pdca-examples.md

Open the folder on GitHubat commit 9e7b281

Compare with similar skills

Pdca Improvement 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.

Pdca Improvement compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pdca Improvement this skillhashgraph-online/awesome-codex-plugins1.3k—~2.1kAutomated safety check: PassMIT
Vercel Composition Patternssupabase/supabase111k58 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 58 repos~726 tokens
    DevelopmentAuto-check passed
  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    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 Pdca Improvement

What does Pdca Improvement do?

Run a PDCA cycle, Plan Do Check Act improvement cycle, or structured improvement project. Pdca Improvement is an agent skill from hashgraph-online/awesome-codex-plugins. Run a PDCA cycle, Plan Do Check Act improvement cycle, or structured improvement project.

When should I use Pdca Improvement?

Pdca Improvement fits situations like: process optimisation; lessons learned implementation; quality objectives.

How do I install Pdca Improvement in Claude Code?

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

How do I install Pdca Improvement in Codex?

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

Can I use Pdca Improvement 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 pdca-improvement -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pdca-improvement, .gemini/skills/pdca-improvement, .github/skills/pdca-improvement and .opencode/skills/pdca-improvement in your project.

What does Pdca Improvement need to run?

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

Does Pdca Improvement 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 Pdca Improvement 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 Pdca Improvement use?

Pdca Improvement 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 Pdca Improvement use?

About 2.1k tokens (SKILL.md is roughly 8.2k 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 5.4k tokens, read only when the agent opens those files.

What are the alternatives to Pdca Improvement?

Skills that share tags, products or a category with Pdca Improvement: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pdca Improvement?

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.