push

Push current branch changes to origin and create or update the corresponding pull request; use when asked to push, publish updates, or create pull request.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

70%Weight 40%Scale 1-3

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

A well-structured, workflow-driven skill with strong sequencing and validation checkpoints, but it loses token efficiency to repeated guidance across Steps/Commands/Notes and leaves the PR title and body as non-executable placeholders.

Suggestions

Consolidate the force-with-lease and auth-vs-sync guidance into one location (e.g., Steps) and have Commands/Notes cross-reference it instead of restating it, to reduce redundancy.

Replace the PR-title placeholder with a concrete example title and a one-line derivation rule, or explicitly mark it as a Claude-authored value so the gap is justified rather than looking incomplete.

Turn the commented PR-body "Example workflow" into an executable sequence (e.g., a heredoc writing to the temp file followed by gh pr edit --body-file) so the body step is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept explanation, but the force-with-lease and auth-vs-sync distinction is restated across Steps, Commands comments, and Notes, which could be tightened; not score 3 because the redundancy means not every token earns its place.	2 / 3
Actionability	Provides many executable commands (git push, gh pr create/edit, mix pr_body.check) but the PR title is a placeholder ("<clear PR title written for this change>") and the PR-body drafting is a commented "Example workflow" rather than a concrete command; not score 3 because these gaps prevent full copy-paste readiness.	2 / 3
Workflow Clarity	Numbered Steps 1–8 form a clear sequence with explicit validation gates (make -C elixir all, mix pr_body.check) and an error-recovery feedback loop (pull skill, re-validate, retry); not score 2 because validation checkpoints are explicit rather than implicit.	3 / 3
Progressive Disclosure	Self-contained skill with no bundle files, organized into clearly labeled sections (Prerequisites, Goals, Related Skills, Steps, Commands, Notes) with no nested references and easy navigation; not score 2 because there is no monolithic wall or deep reference nesting to reorganize.	3 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, concise description that names concrete actions and gives explicit natural-language triggers while staying in third person. It clearly separates the push/PR niche from the related pull skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Push current branch changes to origin" and "create or update the corresponding pull request" — matching the multiple-specific-actions anchor; not score 2 because the actions are explicit and domain-specific rather than only naming a domain.	3 / 3
Completeness	Clearly answers both what (push to origin, create/update PR) and when (explicit "use when" clause); not score 2 because the trigger guidance is explicit, not merely implied.	3 / 3
Trigger Term Quality	"use when asked to push, publish updates, or create pull request" gives natural phrasings a user would actually say; not score 2 because it covers multiple common variants rather than a single keyword.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear push/PR niche with distinct triggers and is explicitly contrasted with the related `pull` skill, so it is unlikely to fire for the wrong skill; not score 2 because the scope is narrowly scoped rather than broadly overlapping.	3 / 3
	Total	12 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/symphony
Path: .codex/skills/push/SKILL.md
Commit: f8e8b8a

Reviewed: 6 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.