CtrlK
BlogDocsLog inGet started
Tessl Logo

he-prune-branches

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

59

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

62%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill has strong workflow clarity with a well-defined sequence, explicit confirmation gates, and validation checkpoints for destructive operations. Its main weaknesses are moderate verbosity from overlapping sections (Failure Modes, Validation, Anti-Patterns, Constraints) and incomplete actionability since the referenced discovery script is not bundled and command examples lack expected output context.

Suggestions

Include the `clean-gone` script in the bundle or inline its key logic so the discovery step is not opaque—document what its output format looks like (e.g., one branch per line).

Consolidate overlapping sections: merge 'Failure Modes' into 'Validation' and 'Anti-Patterns' into 'Constraints' to reduce redundancy and improve conciseness.

Add a concrete example showing expected discovery output and the resulting deletion batch presentation, so Claude knows exactly what format to use when presenting candidates to the user.

DimensionReasoningScore

Conciseness

Generally efficient but includes some sections that could be tightened—'Inputs' and 'Full Context' (icon assets) add little value, and the 'Failure Modes' and 'Anti-Patterns' sections overlap somewhat with 'Validation' and 'Constraints'. The philosophy and procedure sections are reasonably lean.

2 / 3

Actionability

The procedure references a concrete script path and provides executable bash commands for worktree/branch deletion, which is good. However, the script itself is not provided in the bundle, the discovery step is opaque (what does clean-gone output?), and the git commands are templates rather than fully contextualized examples with expected output.

2 / 3

Workflow Clarity

The procedure is clearly sequenced with explicit validation checkpoints: discovery → __NONE__ exit path → present candidates → single confirmation gate → worktree removal before branch deletion → report outcomes. The Validation section adds a fail-fast gate and covers edge cases like active branch and root worktree protection. Feedback loops for partial failures are addressed.

3 / 3

Progressive Disclosure

The content is well-structured with clear section headers, but it's somewhat monolithic—the Validation, Constraints, Anti-Patterns, and Failure Modes sections could be consolidated or moved to a reference file. The script is referenced but no bundle files are provided, so the reference path cannot be verified. No clear navigation to deeper reference materials.

2 / 3

Total

9

/

12

Passed

Description

75%Scale 1-3

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 has a clear 'Use when' clause with specific trigger conditions and occupies a distinct niche, which are its strengths. However, it could be more specific about the concrete actions performed and include more natural trigger terms that users would actually say when requesting branch cleanup.

Suggestions

Add more specific concrete actions, e.g., 'Lists branches by last commit age, checks merge status, identifies branches with open PRs, and generates safe delete commands.'

Include additional natural trigger terms users might say, such as 'git branches', 'old branches', 'delete branches', 'merged branches', 'remote branches', or 'branch management'.

DimensionReasoningScore

Specificity

It names the domain (branch cleanup) and some actions ('review and prune stale branches'), but lacks concrete specifics about what actions are performed—e.g., listing branches by age, checking merge status, generating delete commands. 'Non-destructive recommendations' is somewhat vague.

2 / 3

Completeness

It answers both 'what' (review and prune stale branches safely) and 'when' (when branch cleanup needs evidence, protected-branch caution, PR awareness, and non-destructive recommendations) with an explicit 'Use when' clause containing specific trigger conditions.

3 / 3

Trigger Term Quality

Includes relevant terms like 'branches', 'branch cleanup', 'stale branches', and 'PR', but misses common natural variations users might say such as 'git branches', 'old branches', 'delete branches', 'merged branches', or 'remote branches'.

2 / 3

Distinctiveness Conflict Risk

The description carves out a clear niche—stale branch pruning with safety considerations like protected branches and PR awareness. This is unlikely to conflict with general git skills or other code management skills due to its specific focus.

3 / 3

Total

10

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

10

/

11

Passed

Repository
jscraik/Agent-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.