CtrlK
BlogDocsLog inGet started
Tessl Logo

create-branch

Create a git branch following Sentry naming conventions. Use when asked to "create a branch", "new branch", "start a branch", "make a branch", "switch to a new branch", or when starting new work on the default branch.

71

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is create-branch in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

A well-crafted, concise workflow with concrete commands and thorough failure handling across all five steps. Minor improvements possible: give the exact show-ref collision-check command, tighten the stash-handling instruction, and consider externalizing the type/examples tables.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it never explains what git, branches, or kebab-case are, and every table (type prefixes, examples) and rule directly serves the task. No padded or over-explanatory sections; not anchor 4 because there are no over-explanatory instances to trim.

5 / 5

Actionability

Guidance is mostly executable with concrete commands ("gh api user --jq .login", "git symbolic-ref refs/remotes/<remote>/HEAD ... | sed ...", "git checkout -b <branch-name>") and a worked examples table. Anchor 4 rather than 5 because of minor gaps: the collision check is named but not given as a full invocation ("(`git show-ref`)" without arguments) and stash handling is delegated as "handle any uncommitted changes appropriately".

4 / 5

Workflow Clarity

The five-step sequence is clearly ordered with explicit checkpoints and error-recovery loops: auth failure fallback ("If the command fails... ask the user"), symbolic-ref fallback, detached-HEAD handling, pre-creation name-collision check, user confirmation before creating, and "On any failure, restore stashed changes if applicable and stop". This matches anchor 5's 'explicit validation steps; feedback loops for error recovery'.

5 / 5

Progressive Disclosure

Sections (Steps 1-5, Examples, References) are well-organized and the single external link is clearly signaled, so navigation is easy. Anchor 4 rather than 5 because the ~100-line body keeps everything inline — the 12-row type table and examples table are candidates for a reference file — and the no-bundle single-file layout sits just above the size where a split would clearly not help.

4 / 5

Total

18

/

20

Passed

Description

86%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.

A strong description with explicit, natural trigger phrases and a clear what/when structure. Its only limitations are single-action specificity (natural for a one-purpose skill) and slight overlap risk from the "switch to a new branch" trigger.

DimensionReasoningScore

Specificity

"Create a git branch following Sentry naming conventions" names the domain and one concrete action, but stops short of describing what the convention entails (e.g., the <username>/<type>/<description> prefix scheme or type classification). Anchor 3 ('names domain and 1-2 concrete actions, but not comprehensive') is the best fit; anchor 4 requires several specific actions listed, which a single-action description doesn't provide.

3 / 5

Completeness

It clearly answers both questions: the "what" ("Create a git branch following Sentry naming conventions") and an explicit "Use when asked to..." clause listing concrete trigger phrases. This matches anchor 5 ('clearly and explicitly answers both what AND when with concrete trigger phrases'); anchor 4 would require the 'when' to be less explicit or specific.

5 / 5

Trigger Term Quality

The description enumerates natural user phrasings with synonyms — "create a branch", "new branch", "start a branch", "make a branch", "switch to a new branch" — plus the situational trigger "when starting new work on the default branch". Coverage of natural terms is comprehensive; no meaningful phrasing a user would say is missing.

5 / 5

Distinctiveness Conflict Risk

The Sentry-convention framing and branch-creation triggers give it a clear niche with minimal conflict risk. Not anchor 5 because "switch to a new branch" could fire on a plain branch-switch request (overlapping checkout/switch intent), a minor overlap with closely related operations.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.