Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Create Pull Request Workflow · platformplatform | DecimalAI

code reviewby platformplatform

Create Pull Request Workflow

platformplatform/create-pull-request

Source platformplatform/platformplatform ↗License MIT

Create a GitHub pull request.

SkillScore73Maintained

Automatic

Coding pack

Last verified 8/19/2026

What it changes

Passed 13 of 18 test cases with the skill, and 10 of 18 without it.

Without skill55%

With skill73%

Checks it passed that the model alone missed

Selects build without flags.
Passes the --cli flag to build.
Passes the --frontend flag to build.

and 2 more in the full report

5 fixed11 passed either way5 still failing1 broke

Pass-rate lift: +18 pp
Tokens: +144%
Agent turns: 0%
Response time: -51%

Model gemini-3.6-flashMeasured 8/19/2026v116 of 22 cases passed with skill · 18 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/platformplatform-create-pull-request/SKILL.md https://app.decimal.ai/s/platformplatform-create-pull-request/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add platformplatform-create-pull-request, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/platformplatform-create-pull-request/ and pins it in .decimal/skills.lock

decimalai skills add platformplatform-create-pull-request

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/platformplatform-create-pull-request/SKILL.md https://app.decimal.ai/s/platformplatform-create-pull-request/SKILL.md

Raw file: /s/platformplatform-create-pull-request/SKILL.md ↗ · machine-readable summary at /s/platformplatform-create-pull-request.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 5

Prompt

I modified a C# controller in src/PlatformPlatform.Api/Endpoints/Users.cs. I want to build before running tests. Should I run build --backend to save time, or just build?

What was checked, without and with the skill
Checked	Without skill	With skill
Selects build without flags.	Missed	Passed

case-07 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md241 linessingle file

Create Pull Request Workflow

STEP 1: Gather Context

Run in parallel (quick reads, not background):

git status - working tree state
git branch --show-current - local branch
git --no-pager log --format=%s --reverse $(git merge-base HEAD main)..HEAD - commits on the branch
git --no-pager diff main - full diff
git rev-parse @{u} 2>/dev/null - upstream presence (already pushed?)
gh pr view --json number,url,state 2>/dev/null (only if upstream exists) - check if the branch already has an open pull request

STEP 2: Kick Off Background Work

Everything in this step starts in the background (run_in_background: true) so the workflow proceeds without waiting. Results are reconciled in STEP 10.

Validation

Skip anything already green this session. Only run what's genuinely uncertain.

When validation IS needed:

Run build first:

Backend change: build (no flags - covers backend AND frontend; backend changes can break the frontend build via API contracts)
Frontend-only: build --frontend
CLI-only: build --cli

After build, in parallel (with --no-build where applicable):

aspire-restart - service / Aspire wiring changed
format --<target>, lint --<target> - for each target whose code changed
test --no-build - backend change
e2e - frontend or shared E2E-covered code changed; use --smoke for low-impact changes (judgment)

Use judgment to decide which target a file belongs to (e.g. project / manifest / lock files affect their owning build, even when the extension isn't obvious). Each item runs only if needed and not already green.

STEP 3: Verify Branch Name

Three checks - all read-only at this stage; renames happen in STEP 8.

Track record

Benchmark

13 / 18

test cases passed, vs 10 / 18 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

platformplatform / platformplatform

.claude/skills/create-pull-request/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Create Pull Request Workflow

STEP 1: Gather Context

STEP 2: Kick Off Background Work

Validation

STEP 3: Verify Branch Name

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills