CtrlK
BlogDocsLog inGet started
Tessl Logo

gh-stack

Manages stacked PRs and splits multi-part work into reviewable branches with gh-stack. Use for stack creation, viewing, edits, push, submit, sync, rebase, merge, or checkout; when asked to split or isolate work for review; whenever a user mentions a stack, branch layers, dependent PRs, or gh stack; or when a stack is checked out.

80

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 an efficient, executable reference with sequenced workflows, validation/recovery for risky operations, and well-signaled one-level-deep references that match real bundle files.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: it skips generic git/PR concepts and reserves its tokens for skill-specific facts (TTY detection, --remote requirements, exit codes), with tables instead of prose. Not a 4 because there is no over-explanation to trim.

5 / 5

Actionability

Copy-paste-ready bash commands with required flags throughout — e.g. 'gh stack submit --auto', 'gh stack merge 42 --yes', 'gh stack rebase --upstack' — covering the common creation, edit, sync, and merge cases.

5 / 5

Workflow Clarity

The core loop and branch-placement flow are explicitly sequenced with checkpoints (view --json, inspect git log, checkout owner, rebase upstack, return to top), and destructive/batch ops (merge, sync, rebase) have a feedback loop via the Exit 3 recovery section.

5 / 5

Progressive Disclosure

A concise overview points to three one-level-deep references, each with a clear task trigger ('read before creating a stack', 'read when a command fails', 'read on a rebase conflict') and the explicit instruction not to preload all three; all referenced files exist.

5 / 5

Total

20

/

20

Passed

Description

100%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 is third-person, lean, and answers both what the skill does and exactly when to invoke it, with concrete actions and natural trigger terms including the tool name.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'stack creation, viewing, edits, push, submit, sync, rebase, merge, or checkout' plus 'splits multi-part work into reviewable branches' — giving comprehensive coverage rather than a vague domain label.

5 / 5

Completeness

Explicitly answers both 'what' (manages stacked PRs and splits multi-part work) and 'when' via an explicit 'Use for ...; when asked ...; whenever a user mentions ...; or when a stack is checked out' trigger clause.

5 / 5

Trigger Term Quality

Natural user phrasing is well covered: 'stack', 'stacked PRs', 'split or isolate work for review', 'branch layers', 'dependent PRs', and the literal tool name 'gh stack', matching the synonyms-and-tool-name anchor.

5 / 5

Distinctiveness Conflict Risk

A clear niche (stacked PRs with gh-stack) with distinct, tool-specific triggers that would not fire for unrelated git/PR skills; minimal conflict risk.

5 / 5

Total

20

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
vercel/next.js
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.