CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-rollback

Roll back to a previous checkpoint via git — use when a change went wrong and you need to revert

69

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

A well-sequenced, highly actionable rollback workflow with strong validation and safety gates for a destructive operation. Its main weaknesses are repetition that pads the token budget and a monolithic single-file structure with no progressive disclosure.

Suggestions

Collapse the Safety Measures and Red Flags tables (and the "The Bottom Line" block) into the step prose to remove content that restates the workflow, improving conciseness.

Trim the explanatory bullets under `git checkout <tag> -- .` to the one non-obvious fact (does not move HEAD); Claude already knows basic checkout semantics.

If the skill grows further, move the Checkpoint Tag Format and Quick Reference sections into a bundled reference file referenced one level deep to introduce progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete commands, but the Safety Measures table, Red Flags table, and "The Bottom Line" restate the steps, and the `git checkout <tag> -- .` behavior is re-explained; not 3 because of this padding, not 1 because it avoids teaching general git concepts.

2 / 3

Actionability

It provides fully executable bash commands throughout (e.g. `git tag -l "octo-checkpoint-*"`, `git diff --name-status HEAD $CHECKPOINT_TAG`, `git checkout $CHECKPOINT_TAG -- .`) with clear placeholders; not 2 because these are copy-paste ready, not pseudocode.

3 / 3

Workflow Clarity

Eight clearly sequenced steps include tag-existence validation with an explicit STOP, a mandatory "ROLLBACK" confirmation gate, and a pre-rollback safety checkpoint forming a feedback loop for a destructive operation; not 2 because validation checkpoints are explicit, not implicit.

3 / 3

Progressive Disclosure

No bundle files exist and the skill is a single ~260-line file; it is well-sectioned but monolithic with no one-level-deep references; not 3 because no content is split across files, not 1 because sectioning is clear and not deeply nested.

2 / 3

Total

10

/

12

Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise, well-structured description that clearly pairs a concrete action with an explicit use-trigger and uses correct third-person voice. It could enumerate a couple more concrete sub-actions to fully reach the top specificity anchor.

DimensionReasoningScore

Specificity

"Roll back to a previous checkpoint via git" names the git domain and one concrete action, but does not list multiple specific actions as the top anchor requires; not 1 because it is concrete rather than vague.

2 / 3

Completeness

It states both what it does ("Roll back to a previous checkpoint via git") and an explicit when ("use when a change went wrong and you need to revert"); not 2 because the trigger is explicit, not merely implied.

3 / 3

Trigger Term Quality

"rollback", "revert", "checkpoint", and "change went wrong" are natural phrases a user would say when needing this skill, giving good coverage; not 2 because it offers more than a single keyword.

3 / 3

Distinctiveness Conflict Risk

"Checkpoint rollback via git" is a clear niche with distinct triggers unlikely to fire for unrelated skills; not 2 because the checkpoint/rollback framing is specific rather than broadly overlapping.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
nyldn/claude-octopus
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.