gitbutler-stacks

Hard-won GitButler mechanics for multi-lane work in this repo — committing to a specific lane in a stack, spreading a pile of edits back across an existing stack, ordering a stack and setting PR bases, and recovering from a scrambled workspace. Use when working with stacked branches, when `but rub`/`but absorb`/`but commit --only` mis-routes a change, when a stack collapses or a commit lands on the wrong lane, or when a hunk gets dropped. Not needed for ordinary single-lane work.

Quality

98%

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

Quality

Content

96%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 dense, fully-executable operational playbook with explicit verification checkpoints and feedback loops for destructive operations. Its only weakness is structural: all content is inlined in one file with no external references, which slightly limits navigation for a ~170-line skill.

Suggestions

Consider extracting the 'Hard-won gotchas (don't relearn these)' section into a references/ file (e.g. GOTCHAS.md) and linking to it, keeping the SKILL.md body as a navigable overview of the core workflows.

The 'Splitting one file across two stacked lanes' case is referenced from two places — consolidating it into one labeled subsection and linking from the spreading workflow would reduce duplicated context.

Dimension	Reasoning	Score
Conciseness	The body is lean and operational throughout, assuming Claude's competence — it never explains what GitButler or git is, and each line carries a hard-won gotcha or concrete command with no padding.	5 / 5
Actionability	Fully executable commands are given for every scenario (e.g. `but rub <cliId> <target>`, `git checkout 'stash@{0}^3' -- <paths>`, `but oplog snapshot -m "pristine"`, `git cat-file -p <oplog-sha>:worktree/<path>`), copy-paste ready and covering the common cases.	5 / 5
Workflow Clarity	The 'Spreading a pile of edits' section is a numbered 1–5 sequence with explicit validation checkpoints ('Verify with git status that ONLY that lane's files are present', confirm `git rev-parse == git ls-remote`), oplog snapshots before risky ops, and clear error-recovery feedback loops for destructive/batch operations.	5 / 5
Progressive Disclosure	Content is well organized into clear section headers and is appropriately self-contained, but with no bundle files present everything is inlined — the long 'Hard-won gotchas' list could arguably live in a separate reference file for easier navigation.	4 / 5
	Total	19 / 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, dense with concrete capabilities, and pairs an explicit 'Use when...' trigger list with a clear 'not needed for ordinary single-lane work' boundary. It is comprehensive, distinctive, and free of vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'committing to a specific lane in a stack, spreading a pile of edits back across an existing stack, ordering a stack and setting PR bases, and recovering from a scrambled workspace' — giving comprehensive coverage of the multi-lane domain.	5 / 5
Completeness	Explicitly answers both what (the four mechanics named above) and when ('Use when working with stacked branches... Not needed for ordinary single-lane work'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers the natural terms a GitButler user would actually say — 'stacked branches', 'but rub'/'but absorb'/'but commit --only', 'stack collapses', 'commit lands on the wrong lane', 'hunk gets dropped' — including the exact command names and failure scenarios.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — GitButler multi-lane stacked-branch work — with distinct triggers tied to specific `but` subcommands and stack-failure modes, so overlap with other skills is minimal.	5 / 5
	Total	20 / 20 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: Agenta-AI/agenta
Path: .agents/skills/gitbutler-stacks/SKILL.md
Commit: e4008fa

Reviewed: 5 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.