CtrlK
BlogDocsLog inGet started
Tessl Logo

finishing-a-development-branch

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

63

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/finishing-a-development-branch/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%Scale 1-5

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

This is a well-crafted skill with strong actionability and workflow clarity. The step-by-step process is clearly sequenced with appropriate validation gates, destructive operations require confirmation, and all four options have concrete executable commands. Minor weaknesses include slight redundancy between the workflow steps and the Common Mistakes/Red Flags sections, and a throwaway 'When to Use' line.

DimensionReasoningScore

Conciseness

The skill is mostly efficient and well-structured. Minor verbosity in the 'Common Mistakes' and 'Red Flags' sections which partially repeat information already conveyed in the workflow steps (e.g., test verification is mentioned in Step 1 and again in both sections). The 'When to Use' section is a generic filler sentence. Otherwise, content is lean and assumes Claude's competence.

4 / 5

Actionability

Fully executable guidance throughout: concrete bash commands for each option, specific git commands, gh pr create with template body, exact option text to present to users. The skill covers all four paths with copy-paste ready commands and clear conditional logic.

5 / 5

Workflow Clarity

Clear 5-step sequence with explicit validation checkpoints: tests must pass before proceeding (Step 1 gates Step 2), tests are re-verified after merge (Option 1), typed confirmation required before destructive discard (Option 4). Feedback loops are present—if tests fail, stop and fix. The quick reference table provides an excellent summary of which actions apply to which option.

5 / 5

Progressive Disclosure

Good structure with clear sections (Overview, Process steps, Quick Reference, Common Mistakes, Red Flags, Integration). The Integration section provides clear cross-references to related skills. Minor gap: no bundle files exist, but the skill is self-contained enough (~120 lines) that this is acceptable. The content is well-organized for a single-file skill, though the Common Mistakes and Red Flags sections could potentially be consolidated.

4 / 5

Total

18

/

20

Passed

Description

62%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 has a clear 'when' clause that specifies the trigger conditions well, but the 'what' portion is somewhat vague—'presenting structured options' doesn't convey much about the actual guidance provided. It would benefit from more natural user-facing trigger terms and more specificity about what the structured options entail.

Suggestions

Add natural trigger terms users might say, such as 'done coding', 'ready to push', 'pull request', 'finish up', 'wrap up work'

Expand the 'what' to be more specific about the structured options—e.g., 'presents options including direct merge to main, creating a pull request with description, or branch cleanup with squashed commits'

DimensionReasoningScore

Specificity

Names the domain (development workflow completion) and mentions a few concrete actions (merge, PR, cleanup), but doesn't elaborate on what each option entails or what the skill actually does beyond 'presenting structured options'.

3 / 5

Completeness

Has both 'what' (guides completion by presenting structured options for merge, PR, or cleanup) and 'when' (implementation is complete, all tests pass, need to decide how to integrate). The 'when' is explicit and clear, though the 'what' could be more detailed.

4 / 5

Trigger Term Quality

Includes some relevant terms like 'merge', 'PR', 'tests pass', and 'cleanup', but misses natural user phrases like 'done coding', 'ready to commit', 'pull request', 'finish up', 'wrap up', or 'push changes'.

3 / 5

Distinctiveness Conflict Risk

Fairly distinct niche focused on the post-implementation decision point, but could potentially overlap with git workflow skills or PR creation skills. The specific trigger of 'all tests pass and deciding integration method' helps differentiate it.

4 / 5

Total

14

/

20

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

frontmatter_unknown_keys

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

Warning

Total

10

/

11

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.