diff --git a/.github/copilot-instructions.md b/.github/copilot-instructions.md
index 98bdff031..c73a518ab 100644
--- a/.github/copilot-instructions.md
+++ b/.github/copilot-instructions.md
@@ -61,6 +61,7 @@ General app structure is:
 
 ## Repo-Local Skills
 
+All skills are defined in `.github/skills/` and indexed in `.github/skills/README.md`.
 Use these repo-local skills for recurring SD.Next model integration work:
 
 - `port-model`  
@@ -103,4 +104,8 @@ Use these repo-local skills for recurring SD.Next model integration work:
   File: `.github/skills/analyze-model/SKILL.md`  
   Use when analyzing an external model URL to identify implementation style and estimate how difficult it is to port into SD.Next.
 
+- `fix-lint`  
+  File: `.github/skills/fix-lint/SKILL.md`  
+  Use when running the full lint workflow in required order (`pre-commit`, `eslint`, `ruff`, `pylint`) and fixing findings as needed, while ignoring lint issues explicitly marked with `TODO`.
+
 When creating and updating skills, update this file and the index in `.github/skills/README.md` accordingly.
diff --git a/.github/skills/README.md b/.github/skills/README.md
index 04ee2d386..120b417d0 100644
--- a/.github/skills/README.md
+++ b/.github/skills/README.md
@@ -44,6 +44,10 @@ This folder contains repo-local Copilot skills for recurring SD.Next tasks.
   File: `analyze-model/SKILL.md`
   Use when analyzing an external model URL to classify implementation style and estimate SD.Next porting difficulty before coding.
 
+- `fix-lint`
+  File: `fix-lint/SKILL.md`
+  Use when running the full lint workflow in strict order and fixing issues as needed (`pre-commit`, `eslint`, `ruff`, `pylint`), while ignoring findings explicitly marked with `TODO`.
+
 ## Notes
 
 - Keep skills narrowly task-oriented and reusable.
diff --git a/.github/skills/fix-lint/SKILL.md b/.github/skills/fix-lint/SKILL.md
new file mode 100644
index 000000000..222dfe501
--- /dev/null
+++ b/.github/skills/fix-lint/SKILL.md
@@ -0,0 +1,89 @@
+---
+name: fix-lint
+description: "Run SD.Next lint workflow tools in order and fix issues as needed, while ignoring lint findings explicitly marked with TODO."
+argument-hint: "Optionally focus on a subset of tools or files, otherwise run full workflow"
+---
+
+# Fix Lint Workflow
+
+Run the project lint workflow in the required order, fix findings, and re-run affected tools until clean.
+
+## When To Use
+
+- The user asks to run lint and fix issues
+- A PR requires lint-clean status before review
+- Multiple files changed and style/static checks may have drifted
+- You need a repeatable full-lint remediation pass
+
+## Required Environment Step
+
+Always start from repository root and activate virtual environment first:
+
+- Linux: `. venv/bin/activate`
+- Windows: `venv\\scripts\\activate`
+
+If activation fails, report the blocker and stop before running Python-based tools.
+
+## Required Tool Execution Order
+
+Run tools in this exact sequence:
+
+1. `pre-commit run --all-files`
+2. `eslint . javascript/`
+3. `cd extensions-builtin/sdnext-modernui && eslint . javascript/`
+4. `ruff check`
+5. `pylint *.py`
+6. `pylint modules/`
+7. `pylint pipelines/`
+8. `pylint scripts/`
+9. `pylint extensions-builtin/`
+
+## Fix Policy
+
+- Fix issues reported by each tool before moving on.
+- Ignore lint issues explicitly marked with `TODO`.
+- Do not suppress errors globally just to pass checks.
+- Keep fixes minimal and targeted to reported findings.
+- Preserve existing project conventions and avoid unrelated refactors.
+
+## Procedure
+
+### 1. Initialize Environment
+
+- Confirm current directory is repository root.
+- Activate venv using OS-appropriate command.
+
+### 2. Execute And Repair Per Tool
+
+For each tool in the required order:
+
+- Run the command.
+- Parse failures and group by file.
+- Apply minimal code fixes.
+- Re-run the same command until it passes or only `TODO`-marked findings remain.
+- If a fix introduces new failures in earlier tools, re-run impacted earlier tools.
+
+### 3. Cross-Check Regression
+
+After all tools pass individually:
+
+- Re-run the full ordered sequence once to ensure no cross-tool regressions.
+
+### 4. Report
+
+Return:
+
+- Commands executed (in order)
+- Files changed
+- Which issues were fixed
+- Any findings intentionally ignored due to `TODO` markers
+- Any remaining blockers that could not be auto-fixed
+
+## Pass Criteria
+
+A successful run means:
+
+- All listed tools executed in order
+- No remaining fixable lint errors from those tools
+- Remaining issues are only those explicitly marked with `TODO` (if any)
+- Final verification pass completed
diff --git a/CHANGELOG.md b/CHANGELOG.md
index aa0870cd1..f7dfbf158 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -34,6 +34,7 @@
   - additional instructions in `instructions/`:  
     `core.instructions.md`, `ui.instructions.md`  
   - skills in in `skills/README.md`:  
+    *coding skills*: `fix-lint` (must before commit)  
     *validation skills*: `check-models`, `check-api`, `check-schedulers`, `check-processing`, `check-scripts`  
     *model skills*: `port-model`, `debug-model`, `analyze-model`  
     *github skills*: `github-issues`, `github-features`