he-prune-branches

Review and prune stale branches safely. Use when branch cleanup needs evidence, protected-branch caution, PR awareness, and non-destructive recommendations.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/deferred-store/skills/team_automation/he-prune-branches/SKILL.md

Quality

Content

81%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 content is a clear, well-structured destructive-operation workflow with strong validation and feedback loops; its main weaknesses are dangling bundle references, an opaque core discovery script, and minor cross-section redundancy.

Suggestions

The referenced bundle paths (scripts/clean-gone, ./assets/icon-small.png, ./assets/icon-large.png, and the implied references/ directory) do not exist in the bundle; either add the files or remove the dangling references.

Show the behavior or key contents of the clean-gone discovery script inline or in a reference file, since it is central to the procedure but currently opaque to the reader.

Consolidate the confirmation and worktree guidance repeated across Philosophy, Procedure, Validation, Anti-Patterns, and Constraints into a single authoritative location to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is well-organized and avoids explaining concepts Claude already knows, but the confirmation/worktree guidance is restated across Philosophy, Procedure, Validation, Anti-Patterns, and Constraints, which is minor redundancy that could be trimmed.	4 / 5
Actionability	Concrete executable commands are provided ("bash Plugins/harness-engineering/.../scripts/clean-gone", "git worktree remove --force", "git branch -D"), but the central clean-gone script is referenced without showing its behavior and the commands use placeholders like "<worktree_path>" and "<branch>" that require substitution.	4 / 5
Workflow Clarity	An explicit 8-step procedure is sequenced with a dedicated Validation section, fail-fast gating, and Failure-Mode handling for partial completion, giving clear checkpoints and error-recovery feedback loops for this destructive batch operation.	5 / 5
Progressive Disclosure	Sections are well-organized and external materials (the clean-gone script, icon assets, references) are signaled as one-level-deep links, but the referenced bundle files do not actually exist in the bundle, which is a navigation gap.	4 / 5
	Total	17 / 20 Passed

Description

73%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 specific, distinct, and answers both what and when, but the when-clause leans on abstract qualities rather than concrete trigger phrases and the action list is limited to two verbs.

Suggestions

Replace the abstract quality list ("evidence, protected-branch caution, PR awareness, and non-destructive recommendations") with concrete user trigger phrases, e.g. "Use when the user asks to clean stale local branches whose remotes are gone."

Add a couple more concrete actions beyond "review" and "prune" (e.g. "removes associated worktrees, reports safe candidates") to broaden capability coverage toward a score of 4-5 on specificity.

Dimension	Reasoning	Score
Specificity	"Review and prune stale branches safely" names the domain plus two concrete actions (review, prune), but the remainder ("evidence, protected-branch caution, PR awareness, and non-destructive recommendations") lists qualities rather than additional concrete actions, so coverage is not comprehensive.	3 / 5
Completeness	Both what ("Review and prune stale branches safely") and when ("Use when branch cleanup needs evidence, protected-branch caution, PR awareness...") are present and explicit, but the when-clause describes required qualities rather than concrete user-facing trigger phrases.	4 / 5
Trigger Term Quality	Natural terms like "stale branches", "prune", and "branch cleanup" appear, but common variations such as "delete branches", "local branches", or "git branches" are missing, so coverage is good rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	"Prune stale branches safely" is a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/deferred-store/skills/team_automation/he-prune-branches/SKILL.md
Commit: 2f91362

Reviewed: 1 day 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.