Agent skill

Refactor Execute

Automatically processes TizenFX ai-task issues (dispatching between refactoring/feature modes) and creates a PR.

Apache-2.0Auto-check passedDevelopment

Install Refactor Execute

skills CLI

$ npx skills add Samsung/TizenFX --skill refactor-execute -a claude-code

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

GitHub CLI

$ gh skill install Samsung/TizenFX refactor-execute --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/Samsung/TizenFX.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/refactor-execute .claude/skills/refactor-execute && 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/

Paste into Claude Code

Install the "refactor-execute" agent skill from https://github.com/Samsung/TizenFX/tree/main/.agents/skills/refactor-execute into .claude/skills/refactor-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "refactor-execute", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/Samsung/TizenFX/tree/main/.agents/skills/refactor-execute

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add Samsung/TizenFX --skill refactor-execute -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install Samsung/TizenFX refactor-execute --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Samsung/TizenFX.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/refactor-execute .agents/skills/refactor-execute && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "refactor-execute" agent skill from https://github.com/Samsung/TizenFX/tree/main/.agents/skills/refactor-execute into .agents/skills/refactor-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "refactor-execute", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Samsung/TizenFX --skill refactor-execute -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install Samsung/TizenFX refactor-execute --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Samsung/TizenFX.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/refactor-execute .cursor/skills/refactor-execute && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "refactor-execute" agent skill from https://github.com/Samsung/TizenFX/tree/main/.agents/skills/refactor-execute into .cursor/skills/refactor-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "refactor-execute", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/Samsung/TizenFX.git --path .agents/skills/refactor-execute

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add Samsung/TizenFX --skill refactor-execute -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install Samsung/TizenFX refactor-execute --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Samsung/TizenFX.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/refactor-execute .gemini/skills/refactor-execute && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "refactor-execute" agent skill from https://github.com/Samsung/TizenFX/tree/main/.agents/skills/refactor-execute into .gemini/skills/refactor-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "refactor-execute", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install Samsung/TizenFX refactor-execute

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add Samsung/TizenFX --skill refactor-execute -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/Samsung/TizenFX.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/refactor-execute .github/skills/refactor-execute && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "refactor-execute" agent skill from https://github.com/Samsung/TizenFX/tree/main/.agents/skills/refactor-execute into .github/skills/refactor-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "refactor-execute", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Samsung/TizenFX --skill refactor-execute -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install Samsung/TizenFX refactor-execute --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Samsung/TizenFX.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/refactor-execute .opencode/skills/refactor-execute && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "refactor-execute" agent skill from https://github.com/Samsung/TizenFX/tree/main/.agents/skills/refactor-execute into .opencode/skills/refactor-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "refactor-execute", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: refactor-execute
GitHub stars: 214
Token cost: ~1.4k tokens
SKILL.md length: 510 words
Files: 1
Skills in repo: 5
Repo updated: Oct 6, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Automatically processes TizenFX ai-task issues (dispatching between refactoring/feature modes) and creates a PR.

Works in 2 steps: [Refactoring mode]: The issue body… → [Feature-centric mode]: Any other bug…
Tasks that involve Refactoring
Calls gh, git and dotnet

What it does

Refactor Execute is an agent skill from Samsung/TizenFX. Automatically processes TizenFX ai-task issues (dispatching between refactoring/feature modes) and creates a PR.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Refactoring. The repository describes itself as: C Device APIs for Tizen. The licence is Apache-2.0.

When your agent uses it

Tasks that involve Refactoring

Example prompts

“/refactor-execute”

Workflow steps

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

[Refactoring mode]: The issue body contains [Type: Refactoring], or comments explicitly request refactoring/optimization.
[Feature-centric mode]: Any other bug fix or feature request.

What it can do on your machine

Read from SKILL.md and the folder at commit 0352388. 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
Shell commands in SKILL.md call:
- gh
- git
- dotnet
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.
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

Refactor Execute loads about 1.4k tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 510 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~32
When it runs · the whole SKILL.md, loaded when a task matches: ~1.4k

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 Samsung/TizenFX at commit 0352388, republished under its Apache-2.0 licence (© Samsung). 510 words, ~1,392 tokens.

Download SKILL.mdSave it as .claude/skills/refactor-execute/SKILL.md (or your agent's skills folder).

name: refactor-execute
description: Automatically processes TizenFX ai-task issues (dispatching between refactoring/feature modes) and creates a PR.

TizenFX AI Bot Universal Task Pipeline (Refactoring / Feature Combined)

Overview

A universal automation pipeline that sequentially processes GitHub Issues labeled ai-task. The task mode is dynamically determined based on the [Type: Refactoring] keyword in the issue body or explicit instructions in comments.

Repository

Repo: samsung/TizenFX (GitHub)
CLI: gh CLI (authenticated)

Pipeline Flow

⓪ Discover target Issues (ai-task)
  → ① Determine task mode (Refactoring vs Feature/Bug)
    → [Refactoring] Refactor + guarantee API preservation → Build → Benchmark → PR
    → [Feature/Bug] Implement feature + tests → Build → PR

Stage ⓪: Universal Issue Discovery

bash

gh issue list --repo samsung/TizenFX --label "ai-task" --state open --json number,title,createdAt --jq 'sort_by(.createdAt) | .[]'

Process the oldest issue first
Process at most 2 issues per run (to maintain quality)
Always terminate after 2 issues even if more are pending

Stage ①: Mode Determination and Feedback Absorption

Fetch the selected issue details and comments:

bash

gh issue view {NUMBER} --repo samsung/TizenFX --comments

Mode dispatch criteria:

[Refactoring mode]: The issue body contains [Type: Refactoring], or comments explicitly request refactoring/optimization. → Apply benchmark and rollback stages.
[Feature-centric mode]: Any other bug fix or feature request. → Skip benchmark, focus on unit test validation.

Stage ②: Branch Creation and Pre-Validation

Clone or update the repository:

bash

gh repo clone samsung/TizenFX || (cd TizenFX && git checkout main && git pull)

Create a working branch:
bash
```
git checkout -b ai-task/issue-{ID}
```
[Refactoring mode] Self-reflection on potential API compatibility breaks:
- Enumerate public API surface of the target area
- Verify by design that the API signature remains unchanged after the refactor

Stage ③: Code Modification

Modify source per the analysis/plan in the issue
Refactoring mode: Strictly preserve state/behavior, keep public API signatures intact
Feature-centric mode: Implement per spec, account for edge cases

Stage ④: Build Verification and Testing

Build verification (required):
bash
```
dotnet build
```
→ Must have 0 errors. Fix errors and rebuild if any occur.
[Feature-centric mode] Unit tests:
bash
```
dotnet test
```
→ Existing tests must pass. Add missing test cases when necessary.

Stage ⑤: [Refactoring Mode Only] Benchmark and Rollback Validation

Add a comparative benchmark to test/Tizen.Benchmark.Gallery/
Attempt to deploy and run on an sdb device

When sdb-related errors/issues occur (device not connected, deploy failure, execution error, etc.):

Pass (skip) the benchmark stage

Post a comment on the PR explaining why the benchmark was skipped:

bash

gh pr comment {PR_NUMBER} --repo samsung/TizenFX --body "⚠️ **Benchmark skipped**: Encountered an issue with sdb device connection/deployment/execution, so the benchmark could not be run. Manual benchmark verification is required. Error: {error summary}"

Also note "Benchmark: skipped (sdb error)" in the PR Verification section

On successful execution:

If the execution log shows a performance regression of 5% or more (median), automatically roll back the code:
bash
```
git checkout -- .
```
→ After rollback, retry from Stage ③ with a different approach (max 1 retry) → If a regression persists on retry, leave a comment on the issue and move to the next issue

Show full SKILL.md (210 more words)Show less

Stage ⑥: PR Creation and Issue Linking

Perform a final .NET expert review over the full set of changes.

Commit and push changes:

bash

git add -A
git commit -m "Refactor: {change summary} (Fixes #{ID})"
git push origin HEAD

Write the PR description (pr_description.md):

markdown

## Summary
{Summary of the changes}

## Changes
{List of changed files and what changed in each}

## Mode
{Refactoring / Feature}

## Verification
- [ ] Build: passed
- [ ] Tests: {passed / N/A}
- [ ] Benchmark: {result summary / skipped (sdb error: reason) / N/A}

Fixes #{ID}

Create the PR:

bash

gh pr create --repo samsung/TizenFX --title "[AI Task] {task summary}" --body-file pr_description.md --label "ai-task"

3-1. Verify and ensure the label is applied:

bash

   gh pr view --repo samsung/TizenFX --json labels --jq '.labels[].name' | grep -q "ai-task" || \
   gh pr edit --repo samsung/TizenFX --add-label "ai-task"

After processing the current issue, if fewer than 2 issues have been handled and more are queued, return to Stage ⓪. Always terminate once 2 issues have been processed.

Constraints

At most 2 issues per run (this limit is absolute)
When performing refactoring-only changes, behavior preservation is mandatory
If build errors cannot be resolved in 2 consecutive attempts, comment on the issue and skip it
Prefer small, reviewable PRs over large sweeping changes

Reporting

Processed issue numbers and links
Created PR links
Task mode per issue (Refactoring / Feature)
Benchmark result (where applicable) or skip reason
Reason for any skipped issues

Files

Just SKILL.md in .agents/skills/refactor-execute of Samsung/TizenFX.

Open the folder on GitHubat commit 0352388

Compare with similar skills

Refactor Execute 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.

Refactor Execute compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Refactor Execute this skillSamsung/TizenFX	214	—	~1.4k	Automated safety check: Pass	Apache-2.0	today
Guidelinesakash-network/node	1.1k	22 repos	~577	Automated safety check: Pass	MIT	yesterday
Component Refactoringlangflow-ai/langflow	156k	—	~3.5k	Automated safety check: Pass	MIT	today
Migrate Core Code to Submodulestinyhumansai/openhuman	41k	—	~2.6k	Automated safety check: Pass	GPL-3.0	today
ast-grep Structural Searchcode-yeongyu/oh-my-openagent	70k	—	~3.3k	Automated safety check: Pass	MIT	today
Systematic Code Refactoringluongnv89/claude-howto	42k	—	~3k	Automated safety check: Pass	MIT	7 days ago

Similar skills

Guidelines
akash-network/node
Behavioral guidelines to reduce common LLM coding mistakes. An agent skill from akash-network/node.
1.1k GitHub starsUsed in 22 repos~577 tokens
DevelopmentAuto-check passed
Component Refactoring
langflow-ai/langflow
Refactor high-complexity React components in Langflow frontend.
156k GitHub stars~3.5k tokensUpdated today
DevelopmentAuto-check passed
Migrate Core Code to Submodules
tinyhumansai/openhuman
Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.
41k GitHub stars~2.6k tokensUpdated today
DevelopmentAuto-check passed
ast-grep Structural Search
code-yeongyu/oh-my-openagent
Searches and rewrites code by syntax-tree shape across 25 languages with ast-grep, for codemods, structural queries and YAML lint rules, using a Python wrapper script.
70k GitHub stars~3.3k tokensUpdated today
DevelopmentAuto-check passed
Systematic Code Refactoring
luongnv89/claude-howto
Guides refactoring in phases based on Martin Fowler's method: research, test coverage check, planning and small tested steps, with your approval at each phase.
42k GitHub stars~3k tokensUpdated 7 days ago
DevelopmentAuto-check passed
Codex
skills-directory/skill-codex
A skill your agent uses when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing
1.5k GitHub starsUsed in 3 repos~1.8k tokens
DevelopmentAuto-check passed

Questions about Refactor Execute

What does Refactor Execute do?

Automatically processes TizenFX ai-task issues (dispatching between refactoring/feature modes) and creates a PR. Refactor Execute is an agent skill from Samsung/TizenFX. Automatically processes TizenFX ai-task issues (dispatching between refactoring/feature modes) and creates a PR.

When should I use Refactor Execute?

Refactor Execute fits situations like: tasks that involve Refactoring.

How do I install Refactor Execute in Claude Code?

Run `npx skills add Samsung/TizenFX --skill refactor-execute -a claude-code`. Or copy the skill folder (.agents/skills/refactor-execute in Samsung/TizenFX) into .claude/skills/refactor-execute in your project. Claude Code loads it when a task matches its description.

How do I install Refactor Execute in Codex?

Run `npx skills add Samsung/TizenFX --skill refactor-execute -a codex`. Or copy the skill folder (.agents/skills/refactor-execute in Samsung/TizenFX) into .agents/skills/refactor-execute in your project. Codex loads it when a task matches its description.

Can I use Refactor Execute 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 Samsung/TizenFX --skill refactor-execute -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/refactor-execute, .gemini/skills/refactor-execute, .github/skills/refactor-execute and .opencode/skills/refactor-execute in your project.

What does Refactor Execute need to run?

Going by SKILL.md and its folder, Refactor Execute needs the command-line tools its instructions call (gh, git and dotnet).

Does Refactor Execute access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Refactor Execute 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 Refactor Execute use?

Refactor Execute is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Refactor Execute use?

About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Refactor Execute?

Skills that share tags, products or a category with Refactor Execute: Guidelines (akash-network/node, 1.1k stars), Component Refactoring (langflow-ai/langflow, 156k stars), Migrate Core Code to Submodules (tinyhumansai/openhuman, 41k stars) and ast-grep Structural Search (code-yeongyu/oh-my-openagent, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Refactor Execute?

Samsung (a GitHub organization) maintains it in Samsung/TizenFX, which has 214 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 6, 2026.

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

Install Refactor Execute

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

TizenFX AI Bot Universal Task Pipeline (Refactoring / Feature Combined)

Overview

Repository

Pipeline Flow

Stage ⓪: Universal Issue Discovery

Stage ①: Mode Determination and Feedback Absorption

Stage ②: Branch Creation and Pre-Validation

Stage ③: Code Modification

Stage ④: Build Verification and Testing

Stage ⑤: [Refactoring Mode Only] Benchmark and Rollback Validation

Stage ⑥: PR Creation and Issue Linking

Constraints

Reporting

Files

Compare with similar skills

Similar skills

More from Samsung/TizenFX

Related

Questions about Refactor Execute