branch-pr
PR creation workflow for Agent Teams Lite following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
61
52%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/branch-pr/SKILL.mdQuality
Discovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies its domain (PR creation for Agent Teams Lite) and includes a trigger clause, but it lacks concrete actions describing what the skill actually does. The 'what' portion is essentially a label rather than a list of capabilities, and the trigger terms, while reasonable, miss common user phrasings. The reference to 'issue-first enforcement system' is jargon that doesn't clarify behavior.
Suggestions
Replace the vague 'PR creation workflow' with specific actions, e.g., 'Creates branches, generates PR descriptions from linked issues, enforces issue-first policy before opening PRs, and prepares changes for review.'
Expand trigger terms to include common variations like 'submit PR', 'merge request', 'push for review', 'open pull request', or 'send changes for code review'.
Briefly explain what 'issue-first enforcement system' means in practical terms, e.g., 'Requires a linked issue before allowing PR creation' so Claude understands the constraint.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain ('PR creation workflow') but does not list any concrete actions like 'creates branch', 'generates PR description', 'links issues', or 'runs checks'. 'PR creation workflow' and 'issue-first enforcement system' are abstract labels, not specific capabilities. | 1 / 3 |
Completeness | It has a 'Trigger:' clause that partially addresses 'when', and the first sentence loosely addresses 'what'. However, the 'what' is vague (just 'PR creation workflow' with no concrete actions), and the trigger clause, while present, doesn't fully compensate for the weak capability description. | 2 / 3 |
Trigger Term Quality | Includes some natural trigger terms like 'creating a pull request', 'opening a PR', and 'preparing changes for review', which users might say. However, it misses common variations like 'submit PR', 'merge request', 'push changes', 'code review', or 'git push'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Agent Teams Lite' and 'issue-first enforcement system' adds some distinctiveness, but 'PR creation' is a broad concept that could overlap with general git workflow skills, code review skills, or CI/CD skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a thorough and actionable PR creation guide with concrete commands, regex patterns, and clear formatting requirements. Its main weaknesses are redundancy across multiple lookup tables that repeat similar type mappings, and the lack of explicit error recovery steps in the workflow despite having blocking automated checks. Trimming duplicate information and adding validation feedback loops would elevate this skill significantly.
Suggestions
Consolidate the repeated type mapping tables (branch naming, commit types, PR labels) into a single reference table to reduce redundancy and token usage.
Add explicit error recovery steps to the workflow — e.g., 'If shellcheck fails: fix issues and re-run before pushing' and 'If automated checks fail: check which job failed, fix, and push again'.
Consider extracting the detailed conventional commits section and branch naming regex into a referenced file (e.g., CONVENTIONS.md) to keep the main skill focused on the PR creation workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes redundant information — the branch naming table repeats what the regex and format line already convey, and the full 11-row type tables appear multiple times (branch naming, commit types, PR labels). Some consolidation would significantly reduce token usage without losing clarity. | 2 / 3 |
Actionability | The skill provides concrete, executable commands (git, gh CLI, shellcheck), exact regex patterns for validation, specific markdown templates for PR bodies, and copy-paste ready examples for commits and branch names. Everything is specific and directly usable. | 3 / 3 |
Workflow Clarity | The numbered workflow steps are clear and sequenced, and the automated checks table is helpful. However, there are no explicit validation checkpoints or feedback loops — e.g., what to do if shellcheck fails, if the issue doesn't have status:approved, or if automated checks fail. For a process with blocking automated checks, explicit error recovery guidance is needed. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear section headers and tables, but it's a long monolithic document (~150+ lines of dense content). The PR template reference (.github/PULL_REQUEST_TEMPLATE.md) is mentioned but the full template content is essentially duplicated inline. Related skills (issue creation, conventional commits) could be referenced rather than fully detailed here. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- Gentleman-Programming/agent-teams-lite
- Commit
6901875
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.