create-pr

Full PR creation pipeline — self-review, code review checks, and PR creation with a structured template.

Quality

55%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./devflow-plugin/skills/create-pr/SKILL.md

Quality

Discovery

32%

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 conveys the general purpose of the skill — a PR creation pipeline — but lacks explicit trigger guidance ('Use when...') and misses common user-facing terms like 'pull request'. The actions listed are somewhat high-level and could benefit from more concrete specifics about what each step entails.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to create a pull request, open a PR, or submit code for review.'

Include common trigger term variations such as 'pull request', 'open a PR', 'submit PR', 'merge request', and 'GitHub/GitLab PR'.

Make the actions more concrete — e.g., specify what 'code review checks' include (linting, test coverage, style checks) and what the 'structured template' covers (summary, testing notes, reviewer checklist).

Dimension	Reasoning	Score
Specificity	Names the domain (PR creation) and some actions (self-review, code review checks, PR creation with structured template), but these are somewhat high-level and not deeply concrete — e.g., it doesn't specify what 'code review checks' entail or what the structured template includes.	2 / 3
Completeness	Describes what the skill does (PR creation pipeline with self-review and code review checks) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'when' is entirely absent, warranting a 1.	1 / 3
Trigger Term Quality	Includes 'PR creation', 'code review', and 'self-review' which are relevant keywords, but misses common variations users might say like 'pull request', 'open a PR', 'submit PR', 'merge request', or 'GitHub PR'.	2 / 3
Distinctiveness Conflict Risk	The combination of self-review, code review checks, and PR creation with a structured template is somewhat distinctive, but 'code review' could overlap with standalone code review skills, and 'PR creation' could overlap with general git workflow skills.	2 / 3
	Total	7 / 12 Passed

Implementation

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a solid, actionable PR creation skill with a clear multi-step workflow, explicit validation gates, and executable commands throughout. Its main weaknesses are minor verbosity in places where Claude's existing knowledge is assumed (self-review checklist items) and the unexplained $ARGUMENTS placeholder. The PR template could benefit from being extracted to a separate file for maintainability.

Suggestions

Remove or explain the dangling `$ARGUMENTS` placeholder at the end, which is unclear and potentially confusing.

Consider extracting the PR body template into a separate file (e.g., PR_TEMPLATE.md) and referencing it, improving both conciseness and progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but includes some unnecessary explanation. Phrases like 'You are creating a pull request. This command runs the full PR pipeline.' are slightly redundant, and some steps could be tightened (e.g., the self-review checklist items are things Claude already knows to check). However, it's not egregiously verbose.	2 / 3
Actionability	Provides fully executable bash commands throughout (git log, git diff, gh pr create), a complete PR template with heredoc syntax, and specific fallback commands when devflow is unavailable. The guidance is copy-paste ready and concrete.	3 / 3
Workflow Clarity	Clear 8-step sequence with explicit validation checkpoints: step 3 runs checks, step 4 is a decision gate that requires user approval before proceeding with failing checks, step 6 presents draft for user review before creation. The feedback loop (find issues → ask user → fix or proceed) is well-defined, and the 'Important' section reinforces key constraints.	3 / 3
Progressive Disclosure	The content is well-structured with clear sections and numbered steps, but the PR template is inlined as a large heredoc block that could potentially be a separate template file. For a skill of this size (~80 lines) with no bundle files, the inline approach is acceptable but not optimal. The $ARGUMENTS placeholder at the end is unexplained.	2 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

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: AndreJorgeLopes/devflow
Commit: b0b1bb6

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.