CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

checkpoint-manager

State snapshots and rollback for safe experimentation. Use when creating checkpoints, rolling back changes, managing recovery points, or implementing safe experimentation.

Quality

71%

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/checkpoint-manager/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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 well-structured with executable quick-start code that matches the bundled scripts, but two referenced detail files are missing from the bundle, the destructive rollback workflow lacks validation steps, and the ASCII diagram and full JSON example spend tokens a leaner presentation would not.

Suggestions

Add the missing references/CHECKPOINT-STRATEGY.md and references/ROLLBACK-PROCEDURES.md files (or remove the References section) so the cited detail material actually exists.

Add explicit validation steps to the workflow, e.g. verify a checkpoint loads successfully before attempting a risky operation, and confirm git state matches the checkpoint commit after rollback.

Replace the 25-line ASCII box diagram with a short numbered list and trim the JSON example to the fields needed to use the API, freeing tokens for a rollback-by-id-after-restart example.

DimensionReasoningScore

Conciseness

Mostly efficient — no explanations of concepts Claude already knows — but the ~25-line ASCII box diagram and the full JSON dump could be tightened into a short numbered list and a compact schema sketch. Not 4: the box-art borders and complete example JSON are noticeable token padding, not just minor trimming.

3 / 5

Actionability

The Quick Start gives real, executable async Python that matches the actual script API (create_checkpoint with name/description, rollback, rollback_to_latest), all verified to exist. Not 5: common cases like listing, loading, or resuming a checkpoint after a restart are not shown, and no usage is demonstrated for three of the four listed scripts.

4 / 5

Workflow Clarity

The CHECKPOINT WORKFLOW diagram lays out a clear create → attempt → rollback sequence with sub-steps, but rollback is a destructive operation (git reset) and there are no explicit validation/verification steps (e.g., verify checkpoint integrity before reset, confirm state after rollback). Per the rubric, missing validation in destructive operations caps this at 3.

3 / 5

Progressive Disclosure

Section structure is good and the References section is clearly labeled with per-file descriptions, but both referenced files (references/CHECKPOINT-STRATEGY.md, references/ROLLBACK-PROCEDURES.md) do not exist — the references/ directory is absent from the bundle. Not 3: with dangling references, navigation to the detail material fails outright rather than being merely imperfectly organized.

2 / 5

Total

12

/

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-formed description with an explicit 'Use when...' clause covering multiple natural triggers. Its only weaknesses are a thin enumeration of what is actually snapshotted and a few missing synonyms (revert, undo, restore).

DimensionReasoningScore

Specificity

"State snapshots and rollback for safe experimentation" names the domain and two concrete actions (snapshots, rollback), but stops there — what state is captured or how is not enumerated. Not 4: an anchor-4 description would list several specific actions with only minor gaps in coverage.

3 / 5

Completeness

Explicitly answers both: what ("State snapshots and rollback for safe experimentation") and when ("Use when creating checkpoints, rolling back changes, managing recovery points, or implementing safe experimentation") with concrete trigger phrases. Not 4: the 'when' clause is already explicit and specific, so the anchor-4 caveat ('when' could be more explicit) does not apply.

5 / 5

Trigger Term Quality

"creating checkpoints, rolling back changes, managing recovery points" gives good natural keyword coverage a user would plausibly say. Not 5: common synonyms like "snapshot", "revert", "undo", or "restore" are missing.

4 / 5

Distinctiveness Conflict Risk

The checkpoint/recovery-point niche is distinct with dedicated triggers. Not 5: "rolling back changes" is broad enough to risk minor overlap with generic version-control or undo-type skills.

4 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

14

/

16

Passed

Repository

fernandezbaptiste/Skrillz

Path

skills/checkpoint-manager/SKILL.md

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.