git-checkpoint

Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./agentscope-examples/agents/agentscope-codingagent/src/main/resources/workspace-templates/skills/git-checkpoint/SKILL.md

Quality

Content

80%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 actionable and well-structured for a simple skill, with copy-paste git commands and clean sectioning. Its one gap is the absence of explicit verification steps around the destructive rollback operations.

Suggestions

Add an explicit verification checkpoint after destructive rollback, e.g. run 'git status' / 'git log --oneline -1' to confirm the working tree is at the intended state before proceeding.

Add a brief validation step before rolling back (e.g. 'git stash list' / confirm the checkpoint hash) so the reset target is verified, creating a validate -> reset -> verify feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean with executable commands and no over-explanation of git basics, but the opening motivation ('so you can take bold steps without fear of corrupting the working tree') is minor padding that could be trimmed, landing just below anchor 5.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands for both checkpointing ('git add -A && git commit ...') and three rollback scenarios, covering the common cases with concrete syntax.	5 / 5
Workflow Clarity	The checkpoint-then-rollback sequence is clear and conditional, but the destructive operations ('git reset --hard', 'git checkout --') lack explicit validation/verification steps, capping this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	A simple under-50-line single-purpose skill with no need for external references, organized into clear sections (Checkpoint, Roll back, Rules), which qualifies for the top anchor under the simple-skill exception.	5 / 5
	Total	17 / 20 Passed

Description

65%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 clearly conveys both purpose and a concrete trigger, with good natural keywords and a distinct niche. Its main weakness is the second-person imperative voice and a slightly narrow 'when' clause.

Suggestions

Rewrite the description in third person (e.g. 'Creates a checkpoint commit before risky changes and rolls back cleanly...') to match the rubric's voice requirement.

Broaden the 'when' trigger to cover more scenarios users would name, e.g. 'Use before multi-file refactors, large deletions, or any change you are unsure about'.

Dimension	Reasoning	Score
Specificity	Names the git domain and two concrete actions ('create a checkpoint commit', 'roll back cleanly'), which is anchor-3 level, but the imperative 'Use git...' is second-person voice so the specificity score is reduced by 1 per the rubric.	2 / 5
Completeness	Explicitly states what it does (checkpoint commit + clean rollback) and gives an explicit when ('Use before multi-file refactors'), but the trigger scenario is narrow compared to the comprehensive multi-trigger anchor 5.	4 / 5
Trigger Term Quality	Includes natural user-facing terms ('git', 'checkpoint', 'roll back', 'multi-file refactors') with good coverage; a few synonyms (e.g. 'snapshot', 'undo') are absent, so it sits just below anchor 5.	4 / 5
Distinctiveness Conflict Risk	The checkpoint/rollback safety-net framing is a clear niche with distinct triggers, with only minor overlap risk against generic git skills, fitting anchor 4 rather than the fully-distinct anchor 5.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: agentscope-ai/agentscope-java
Path: agentscope-examples/agents/agentscope-codingagent/src/main/resources/workspace-templates/skills/git-checkpoint/SKILL.md
Commit: 1a81e59

Reviewed: about 23 hours 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.