skills/base/bill-pr-description/SKILL.md
Use when generating a PR title, description, and QA steps from the current branch changes. Works standalone or as part of bill-feature-implement. Use when user mentions write PR description, generate PR, PR title, or create pull request.
npx skillsauth add sermilion/mobile-development-plugin bill-pr-descriptionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
If .agents/skill-overrides.md exists in the project root and contains a ## bill-pr-description section, read that section and apply it as the highest-priority instruction for this skill. The matching section may refine or replace parts of the default workflow below.
If an AGENTS.md file exists in the project root, apply it as project-wide guidance.
Precedence for this skill: matching .agents/skill-overrides.md section > AGENTS.md > built-in defaults.
Generate a PR title, description, and QA/test steps ready to paste. Present the result to the user for review.
main.HEAD, along with the commit log and branch name.CLAUDE.md, AGENTS.md, and the matching bill-pr-description section in .agents/skill-overrides.md when present.You MUST search for a repo-native PR template before generating any description. Do not skip this step. Do not assume no template exists without checking.
Search these locations in order, using glob or file-read tools:
.github/pull_request_template.md.github/PULL_REQUEST_TEMPLATE.mdpull_request_template.mdPULL_REQUEST_TEMPLATE.md.github/pull_request_template/*.md.github/PULL_REQUEST_TEMPLATE/*.mddocs/pull_request_template.mdWhen a repo-native template is found:
When multiple templates are found and there is no obvious default, ask the user which one to use.
Only when NO repo-native template is found at any of the above locations, fall back to the built-in Skill Bill template in the section below.
Short, under 70 characters, prefixed with the ticket ID if the branch name contains one (e.g., feat: [ME-4493] Show empty state for daily report AI).
This template is a fallback. Use it ONLY when no repo-native PR template was found in the search above.
# Summary
<1-3 sentences: what changed and why. Reference the ticket/spec. Include motivation.>
<optional: bullet list of key changes if more than one logical change>
## Feature Flags
<flag name and description, or "N/A">
# How Has This Been Tested?
<overview of tests performed — unit tests, manual verification, preview checks>
<reproducible test instructions:>
1. <step>
2. <step>
3. <expected result>
bill-feature-implement, check .feature-specs/<ISSUE_KEY>-<feature-name>/spec.md for additional context (this file only exists when bill-feature-implement created it)For the shared telemetry contract including the orchestrated flag semantics, follow telemetry-contract.md.
This skill emits a single skillbill_pr_description_generated event via the pr_description_generated MCP tool.
Standalone invocation: after presenting the PR description (and after the user has created the PR, if applicable), call pr_description_generated with commit_count, files_changed_count, was_edited_by_user (true if the user requested changes to the generated description), pr_created (true if the PR has actually been created), and optional pr_title.
Orchestrated invocation (when called from bill-feature-implement or similar parent that passes orchestrated=true): call pr_description_generated with orchestrated=true and the same fields. The tool returns {"mode": "orchestrated", "telemetry_payload": {...}}. Return that payload to the orchestrator — it will embed it in its own finished event.
development
Use when running a governed editorial assignment desk from Readian recommendations through candidate selection and source-backed story packs.
testing
Use when reviewing unit tests in a file, current changes, or a commit to flag low-value, tautological, or coverage-only tests that do not validate real behavior. Use when user mentions check test quality, review tests, tautological tests, weak tests, or coverage-padding.
data-ai
Use when removing an existing skill or platform skill set and cleaning up agent installs, manifests, and supporting links.
development
Use when you want a generic quality-check entry point that detects the dominant stack in scope and delegates to the matching stack-specific quality-check skill. Use when user mentions run checks, validate, lint, format, quality check, or run quality.