gh-stack

Manage stacked branches and pull requests with the gh-stack GitHub CLI extension. Use when the user wants to create, push, rebase, sync, navigate, or view stacks of dependent PRs. Triggers on tasks involving stacked diffs, dependent pull requests, branch chains, or incremental code review workflows.

Quality

88%

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

77%

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

The content is highly actionable with clear, validated workflows and executable examples, but it is a long monolithic file with some repeated warnings across sections. Splitting command reference and workflows into referenced files would improve progressive disclosure and reduce redundancy.

Suggestions

Move the per-command reference (init, add, push, submit, link, sync, rebase, view, checkout, unstack) and the exit-code/known-limitations tables into a referenced file (e.g., COMMANDS.md), keeping SKILL.md as a concise overview with one-level-deep links to improve progressive_disclosure.

Consolidate the repeated non-interactive-prompt warnings (always pass --json/--auto/branch arguments) into a single authoritative "Agent rules" section and reference it from the command sections instead of restating them in the forbidden-command list and each command's notes, to tighten conciseness.

Remove the duplicated deliberate-staging example (it appears in "Staging changes deliberately" and again in the "Add a branch" recommended workflow) by cross-referencing one occurrence.

Dimension	Reasoning	Score
Conciseness	The body is dense and avoids explaining generic git concepts Claude already knows, but the interactive-prompt warnings (always pass --json/--auto/branch arguments) are repeated across the "Agent rules", per-command, and forbidden-command-list sections, and the deliberate-staging example appears twice — tightening would remove redundant tokens without losing clarity.	2 / 3
Actionability	Provides copy-paste-ready bash, complete flag tables, executable JSON-parsing examples with jq, and an exit-code table — fully concrete and executable guidance rather than abstract description.	3 / 3
Workflow Clarity	Sequenced workflows (create, mid-stack changes, sync, squash-merge recovery, rebase conflicts) include explicit validation checkpoints (verify with `gh stack view --json`, exit-code-3 -> resolve -> `--continue` -> `--abort`) and clear feedback loops for the risky rebase operations.	3 / 3
Progressive Disclosure	The skill is a single ~870-line monolithic SKILL.md with no bundle files and no one-level-deep references; content that could live in separate files (per-command reference, exit codes, workflows) is inline, matching the level-2 anchor where content that should be separate stays inline rather than the level-3 split-overview pattern.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 is concise, third-person, and clearly answers both what the skill does and when to use it with concrete actions and natural trigger terms. It occupies a distinct niche unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "create, push, rebase, sync, navigate, or view stacks of dependent PRs" — and names the specific tool, matching the anchor for listing several specific concrete actions rather than naming only a domain and a few actions.	3 / 3
Completeness	Explicitly answers both what ("Manage stacked branches and pull requests with the gh-stack GitHub CLI extension") and when ("Use when the user wants to..." / "Triggers on tasks involving..."), matching the level-3 anchor for clearly answering both with explicit triggers.	3 / 3
Trigger Term Quality	Provides broad natural-term coverage ("stacked diffs, dependent pull requests, branch chains, or incremental code review workflows") that a user would plausibly say, exceeding the 'some relevant keywords' bar at level 2.	3 / 3
Distinctiveness Conflict Risk	Targets a distinct niche (stacked branches/PRs via a specific gh extension) with triggers unlikely to fire for other skills, matching the level-3 anchor rather than the overlap-prone level-2 example.	3 / 3
	Total	12 / 12 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
skill_md_line_count	SKILL.md is long (873 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: remotion-dev/remotion
Path: .agents/skills/gh-stack/SKILL.md
Commit: 1b58387

Reviewed: 2 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.