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

68

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

88%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.

An excellent procedural skill body: fully executable commands, a well-sequenced workflow with explicit validation and confirmation gates for a destructive operation, and clean section structure. The only real weakness is mild repetition of the safety messaging across four separate closing sections.

DimensionReasoningScore

Conciseness

The body is dominated by executable commands, tables, and short directives with almost no explanation of concepts Claude already knows, matching 'Efficient; minor instances of over-explanation that could be trimmed'. It is not 5 because the safety message is repeated across the Safety Measures table, Red Flags table, 'The Bottom Line', and inline CRITICAL notes — some of which could be consolidated.

4 / 5

Actionability

Every step carries a copy-paste-ready bash command (git tag listing, tag validation, diff preview, safety tagging, LESSONS.md preservation, checkout restore), and both modes include concrete example output, matching 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases'. No gaps found.

5 / 5

Workflow Clarity

The ROLLBACK mode is a clearly numbered 8-step sequence with explicit validation checkpoints: tag existence check with a hard STOP on failure, a mandatory confirmation gate, a preview of affected files before any change, and a safety-checkpoint recovery path for undoing the rollback. This matches the top anchor 'Clear sequence with explicit validation steps; feedback loops for error recovery' — notable because it is a destructive operation with strong validation.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), and the body is well-organized with clear section headers, tables, and a quick reference, matching 'Good structure; most content is appropriately placed; minor organization gaps'. It is not 5 because the skill exceeds the simple-skill size threshold, and the tag-format catalog, Quick Reference, and safety-summary tables are mildly redundant sections that could be consolidated or split out.

4 / 5

Total

18

/

20

Passed

Description

78%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.

A concise, well-targeted description that clearly states what the skill does and when to use it in natural language. Its main gaps are thin capability coverage (one action listed) and trigger synonyms that live only in the frontmatter trigger block rather than the description itself.

Suggestions

Enumerate 2-3 concrete capabilities in the description (e.g., 'list checkpoints, preview affected files, and create a safety backup before restoring') to lift specificity beyond a single action.

Fold the natural trigger synonyms from the frontmatter trigger block into the description (e.g., 'undo', 'go back to', 'restore checkpoint') so the description alone carries full keyword coverage.

DimensionReasoningScore

Specificity

The description names the domain ("previous checkpoint via git") and one concrete action ("Roll back"), which matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'. It stays below 4 because capabilities like listing checkpoints, previewing affected files, or creating a safety backup are not mentioned, and above 2 because 'roll back to a previous checkpoint via git' is a specific, non-generic action.

3 / 5

Completeness

It explicitly answers both questions: what ("Roll back to a previous checkpoint via git") and when ("use when a change went wrong and you need to revert"), with a concrete, naturally phrased trigger clause. It is not 4 because the 'when' clause is already explicit and specific rather than merely present-but-imprecise, and not below 5 since no anchor better fits.

5 / 5

Trigger Term Quality

Natural trigger terms are present: "roll back", "revert", and the phrase "when a change went wrong", which matches 'Good keyword coverage; a few natural terms missing'. It is not 5 because common synonyms a user would naturally say — "undo", "go back to", "restore checkpoint" — appear only in the separate frontmatter trigger block, not in the description itself, and there are no checkpoint-tag-style keywords.

4 / 5

Distinctiveness Conflict Risk

The checkpoint framing carves a clear niche, matching 'Mostly distinct; minor overlap risk with closely related skills'. It is not 5 because generic trigger words like "revert" and "a change went wrong" could also fire for a plain git-revert or generic undo/edit-recovery skill.

4 / 5

Total

16

/

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.

Validation — 15 / 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
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.