open-pr

Opens a pull request from the current branch using the PR template. Use when the user asks to open a PR, create a pull request, or invokes /open-pr.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/open-pr/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

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

The body is a well-structured, lean, actionable workflow with concrete commands at every step and a real delegated script for the complex base-detection logic. The main gaps are deferred title/body formatting, the absence of an explicit error-recovery loop, and inline rather than consolidated cross-skill references.

Suggestions

Add an explicit error-recovery step after `gh pr create` (e.g. if the command fails, surface the gh error and offer to retry without --draft) to strengthen the workflow's feedback loop.

Consolidate the cross-skill references into a short 'Related skills' section (e.g. `pr` for title/body format, `canary` for post-publish releases) instead of mentioning them inline, improving navigation.

Inline the PR title format example or a one-line body template sketch so the create step is fully self-contained rather than deferring to the `pr` skill.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no padding about what a PR or git is — with concrete commands and a compact label table. Not a 5 because minor trims exist (the opening line restates the description, and "Always draft; always assign @me" repeats flags already shown in the gh command); not a 3 because it is efficient throughout with no real unnecessary explanation.	4 / 5
Actionability	Provides a copy-paste-ready `gh pr create` block with all flags and a concrete label-options table, plus specific git commands for each phase. Not a 5 because the title format and exact PR body are deferred ("see the `pr` skill", "<FILLED_TEMPLATE>" placeholder); not a 3 because the guidance is concrete and executable, not pseudocode.	4 / 5
Workflow Clarity	A clear six-step sequence (gather context, detect base, ask labels, draft, create, report) with checkpoints such as "Verify the available labels with the PR template" and "Tell the user the result". Not a 5 because there is no explicit error-recovery feedback loop (e.g. what to do if `gh pr create` fails); not a 3 because steps and several checkpoints are clearly present. The destructive/batch cap does not apply since creating a draft PR is reversible.	4 / 5
Progressive Disclosure	Well-organized into overview, numbered workflow, and notes; the complex base-detection algorithm is delegated to a real one-level-deep script (`scripts/detect-base-branch.sh`, verified present) with a clear inline summary. Not a 5 because the cross-skill references ("see the `pr` skill", "see the `canary` skill") are mentioned inline rather than gathered into a clearly signaled references/navigation section; not a 3 because structure is good and the script reference is appropriately split out and clearly signaled.	4 / 5
	Total	16 / 20 Passed

Description

82%Weight 40%Scale 1-5

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 clearly and explicitly states both what the skill does and when to use it, with concrete natural-language triggers and a slash-command invocation. It is slightly thin on breadth of named actions but strong on trigger quality and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete, specified action ("Opens a pull request from the current branch using the PR template"), but does not list several distinct actions to reach comprehensive coverage. Not a 2 because it gives a concrete, detailed action rather than a minimal generic one; not a 4 because only one action is named, not several.	3 / 5
Completeness	Explicitly answers both what ("Opens a pull request from the current branch using the PR template") and when ("Use when the user asks to open a PR, create a pull request, or invokes /open-pr") with concrete trigger phrases. Matches the anchor that clearly and explicitly answers both what AND when.	5 / 5
Trigger Term Quality	Includes natural terms users would say — "open a PR", "create a pull request", and the "/open-pr" invocation — covering the key synonyms (PR / pull request) plus the slash command. Not a 5 because it lacks additional natural variations a user might phrase (e.g. "submit a PR", "make a pull request"); not a 3 because coverage is clearly better than a single generic keyword.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (opening PRs from the current branch) with distinct, specific triggers including the "/open-pr" command, giving minimal conflict risk with unrelated skills. Not a 4 because the niche and triggers are sharply distinguished rather than only 'mostly distinct'.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: storybookjs/storybook
Path: .agents/skills/open-pr/SKILL.md
Commit: 8403f24

Reviewed: about 18 hours 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.