but-agentlog

Use for prompts like "get context for branch", "catch up on this branch", "recover branch context", or "what prior agent work happened here". Skim prior agent work from `but agentlog` captures for a GitButler branch, review / pull request / merge request, or change. Prefer this over generic git branch/diff inspection when the user asks for context, history, prior work, or branch catch-up.

Quality

82%

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

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 highly actionable with concrete commands and well-sequenced decision logic, and is cleanly sectioned for a self-contained single-purpose skill. Its main weakness is redundancy: the skim/show workflow and rules are restated multiple times across sections and could be consolidated to respect token budget.

Suggestions

Consolidate the duplicated skim/show guidance: state the "prefer skim, drill down with show only when thin/ambiguous" rule once and reference it from Core Workflow, Rules, and the Reading sections instead of restating it.

Reduce repeated command listings (e.g. `but agentlog skim` appears four times); show each command form once in its primary section and refer back rather than reprinting.

Add brief handling for empty or no-match skim/show results (what to do when discovery returns nothing beyond the `but status` fallback) to push workflow_clarity toward a full feedback loop.

Dimension	Reasoning	Score
Conciseness	The body avoids basic-concept padding and uses concrete commands, but the same guidance recurs across Core Workflow, Rules, and the Reading sections (e.g. "Prefer `skim`", "Treat `skim` as complete but abbreviated", the `but agentlog skim` command shown four+ times), so it could be tightened noticeably.	3 / 5
Actionability	Provides copy-paste-ready executable commands ("but agentlog skim", "but agentlog show <session-key> --limit 20", "but --json agentlog skim", "but status") plus specific output field lists, covering the common cases fully.	5 / 5
Workflow Clarity	A clear numbered sequence (skim -> summarize-and-stop or drill down via --json -> show -> --turn) with explicit decision checkpoints and a target-discovery fallback ("but status"); not a 5 because error/empty-result recovery is implicit rather than spelled out.	4 / 5
Progressive Disclosure	No bundle files exist and the skill is self-contained, organized into clear headers (Core Workflow, Target Discovery, Rules, Reading skim/show, Skim Summary) with easy navigation; over the 50-line simple-skill threshold and without one-level-deep external references, so it lands at good-structure rather than the top anchor.	4 / 5
	Total	16 / 20 Passed

Description

90%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 strong: it pairs concrete trigger phrases with a clear statement of what the skill does and when to prefer it over alternatives. The only soft spot is specificity, since it names essentially one action (skim) rather than a set of distinct capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ("Skim prior agent work from `but agentlog` captures") plus its target types, but does not list several distinct actions, so it sits at the 1-2 concrete actions anchor rather than comprehensive.	3 / 5
Completeness	Explicitly answers both what ("Skim prior agent work from `but agentlog` captures...") and when ("Use for prompts like..." and "Prefer this over generic git branch/diff inspection when the user asks for context, history, prior work, or branch catch-up") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Quotes natural user phrases ("get context for branch", "catch up on this branch", "recover branch context", "what prior agent work happened here") plus synonyms (context, history, prior work, branch catch-up), giving comprehensive coverage of terms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (agentlog capture skimming) and explicitly disambiguates from generic git branch/diff inspection and the general GitButler CLI, minimizing conflict risk.	5 / 5
	Total	18 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: gitbutlerapp/gitbutler
Path: crates/but-agentlog/skill/SKILL.md
Commit: 5546418

Reviewed: about 4 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.