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

65

Quality

78%

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/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

73%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 a tight, executable workflow with strong validation gates appropriate to its destructive operations. Its main weakness is redundancy between the 'Common Mistakes' and 'Red Flags' sections plus a filler 'When to Use' line that add tokens without adding guidance.

Suggestions

Merge 'Common Mistakes' and 'Red Flags' into a single 'Rules' section (or drop one) — they restate the same verify-tests / confirm-discard / cleanup-for-1-and-4 guidance.

Replace the filler 'When to Use' line with concrete trigger conditions (e.g. 'Use after implementation is complete and all tests pass, when deciding between merge, PR, keep, or discard') or remove it.

Trim the 'Announce at start' line unless announcement behavior is a required part of the skill contract; it adds tokens for marginal guidance value.

DimensionReasoningScore

Conciseness

The body is mostly lean and command-driven, but 'Common Mistakes' and 'Red Flags' restate the same rules (verify tests, confirm discard, cleanup for options 1 & 4), and the 'When to Use' section is filler ('applicable to execute the workflow or actions described in the overview'). Not a 4 because the redundancy and filler are noticeable rather than minor.

3 / 5

Actionability

Provides concrete, executable git/gh commands for every option (checkout, pull, merge, push, gh pr create, branch -d/-D, worktree remove) with a real PR heredoc template; minor gaps are the unsubstituted placeholders (<base-branch>, <test command>) which are appropriate for a template.

4 / 5

Workflow Clarity

Clear 5-step sequence (verify tests → base branch → present options → execute → cleanup) with explicit validation checkpoints: a test-pass gate that halts before options, re-verification on the merged result, and a typed 'discard' confirmation for the destructive option. The destructive-operation validation cap does not apply because validation is present.

5 / 5

Progressive Disclosure

A self-contained single SKILL.md with no bundle files, organized into clear headed sections (Process, Quick Reference, Common Mistakes, Red Flags, Integration); good structure with a minor organization gap from the duplicated Common Mistakes/Red Flags sections. Not a 5 because the redundancy keeps navigation from being fully clean.

4 / 5

Total

16

/

20

Passed

Description

83%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 well-constructed: third person, explicit 'Use when' trigger with concrete conditions, and a clear statement of capability. It cleanly answers both what and when, with only minor room for broader trigger synonyms.

DimensionReasoningScore

Specificity

Names the domain ('completion of development work') and several concrete actions ('structured options for merge, PR, or cleanup'), matching the 'lists several specific actions; minor gaps' anchor; not a 5 because coverage of possible integration outcomes is not exhaustive.

4 / 5

Completeness

Explicitly answers both 'what' ('guides completion of development work by presenting structured options for merge, PR, or cleanup') and 'when' ('Use when implementation is complete, all tests pass, and you need to decide how to integrate the work') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ('implementation is complete', 'all tests pass', 'merge', 'PR', 'cleanup'), giving good keyword coverage; not a 5 because common synonyms/extensions (e.g. 'pull request', 'rebase', 'finish branch') are absent.

4 / 5

Distinctiveness Conflict Risk

The 'finishing a branch / decide how to integrate' trigger carves a clear niche distinct from generic git skills, but there is minor overlap risk with PR-creation or worktree skills; not a 5 because 'merge/PR/cleanup' could partially collide with related workflow skills.

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.

Validation15 / 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.