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

65

Quality

77%

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 ./skills/skill-rollback/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A well-structured, highly actionable rollback workflow with strong safety engineering — validation checkpoints, explicit confirmation, a pre-rollback safety tag, and preservation of LESSONS.md. The only meaningful improvements are consolidating the redundant summary sections and explicitly binding the checkpoint tag variable.

DimensionReasoningScore

Conciseness

The body is lean and operational — executable git commands, table templates, and short guarded instructions with no explanation of concepts Claude already knows. Minor trimming is possible: the "Safety Measures", "Quick Reference", and "The Bottom Line" sections largely restate the inline steps and core principle, keeping it at anchor 4 rather than 5.

4 / 5

Actionability

Guidance is almost entirely copy-paste ready: exact git commands, the literal confirmation token "ROLLBACK", a deterministic tag-naming format, and concrete output templates. The small gap is that $CHECKPOINT_TAG is used in commands without an explicit step binding it to the tag parsed from the user's request, matching anchor 4 rather than 5.

4 / 5

Workflow Clarity

The destructive rollback flow is clearly sequenced across eight numbered steps with explicit validation gates: tag-existence check with a hard STOP ("Do not proceed"), a diff preview shown before confirmation, a mandatory exact-word confirmation, and a safety checkpoint created before any file change. Error recovery (tag not found → show available checkpoints) is handled, matching anchor 5; since validation is present, the destructive-operation cap of 3 does not apply.

5 / 5

Progressive Disclosure

The skill is self-contained with well-labeled sections (two modes, numbered steps, reference tables) and no nested-reference chains; the single external pointer ("see skills/blocks/codex-host-adapter.md") is clearly signaled. At ~265 lines, supporting material like the checkpoint tag-format reference could be split into a reference file, which keeps this at anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

73%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 tight, explicit description that clearly states both what the skill does and when to use it, with natural trigger language. Its main weaknesses are the second-person phrasing in the trigger clause (penalized under the voice guideline) and single-action coverage that undersells the skill's full capability set.

Suggestions

Rewrite the trigger clause in third person to remove the second-person voice, e.g. "use when a change went wrong and work needs to be reverted to a prior checkpoint".

Enumerate the concrete capabilities (list available checkpoints, preview affected files, create a safety checkpoint before restoring) instead of the single rollback action.

Add natural synonyms such as "undo", "restore", or "go back to" alongside "rollback" and "revert" to broaden trigger coverage.

DimensionReasoningScore

Specificity

The description names one concrete action — "Roll back to a previous checkpoint via git" — which sits at anchor 3 (domain plus 1-2 concrete actions), but the trigger clause uses second person ("when... you need to revert"), which the guidelines penalize by reducing specificity by 1. It also omits the skill's other concrete capabilities (listing checkpoints, previewing affected files, creating safety checkpoints), so it is not comprehensive.

2 / 5

Completeness

It explicitly answers both questions: the what is "Roll back to a previous checkpoint via git" and the when is "use when a change went wrong and you need to revert" — a concrete, natural trigger phrase. This matches anchor 5; anchor 4 would require the 'when' to be vague or only implicit, which it is not.

5 / 5

Trigger Term Quality

Natural trigger terms are present — "roll back", "checkpoint", "revert", "a change went wrong" — phrases a user would plausibly say when they need this skill. A few common synonyms ("undo", "restore", "go back to") and the concrete tag pattern are missing, matching anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

The checkpoint-rollback niche with git-specific framing is mostly distinct from other skills, but "revert" and "rollback" are broad git terms that could overlap with generic git-undo or version-control skills, matching anchor 4. It is clearly above anchor 3 because the checkpoint framing is not generically applicable.

4 / 5

Total

15

/

20

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.

Validation — 16 / 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.