checkpoint-manager

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

Quality

76%

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 ./skills/checkpoint-manager/SKILL.md

Quality

Content

65%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 and actionable with real, executable script references, but two weaknesses hold it back: the destructive rollback workflow lacks explicit validation/verification steps (capping workflow clarity at 3), and two referenced reference files are dangling because the references/ directory is absent.

Suggestions

Add explicit validation checkpoints to the workflow: verify the checkpoint was captured completely before the risky operation, and verify the rollback restored the expected git state and feature list afterward (e.g., a 'Verify' step listing a concrete command or check).

Create the missing references/ directory with CHECKPOINT-STRATEGY.md and ROLLBACK-PROCEDURES.md, or remove those References entries so no navigation link is broken.

In Quick Start, show how project_dir and the async context are obtained so the create/rollback snippets are fully copy-paste runnable end-to-end.

Dimension	Reasoning	Score
Conciseness	Lean body that assumes Claude's competence — no exposition of git/checkpoint basics, just code, a workflow diagram, a JSON shape, and a table; not a 5 because the opening line partly restates the description and the large ASCII workflow box is more verbose than a tighter flow would be.	4 / 5
Actionability	Quick Start gives concrete, executable Python calling the real scripts.checkpoint_manager module, covering create + rollback + rollback-to-latest; not a 5 because project_dir is undefined, there is no async-context setup, and error-handling usage is not shown.	4 / 5
Workflow Clarity	The CREATE -> RISKY OPERATION (success/failure) -> ROLLBACK diagram gives a clear sequence with a failure feedback branch, but this is a destructive-operation skill (git reset, state restore) with no explicit validation/verification step that a checkpoint was captured or that rollback restored correct state, so the destructive-ops cap of 3 applies.	3 / 5
Progressive Disclosure	Sections are well-organized and the Scripts list points to 4 real, existing files, but the References section points to references/CHECKPOINT-STRATEGY.md and references/ROLLBACK-PROCEDURES.md in a references/ directory that does not exist, so navigation hits dead links — a structural defect beyond the minor-gap level of a 4.	3 / 5
	Total	14 / 20 Passed

Description

87%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 is strong: third-person voice, clear what-and-when structure, concrete trigger phrases, and a distinct niche. It earns top marks on completeness and distinctiveness, with only minor specificity/trigger-coverage gaps keeping it just below full marks.

Dimension	Reasoning	Score
Specificity	Names the domain ('State snapshots and rollback') plus several concrete actions in the trigger clause ('creating checkpoints, rolling back changes, managing recovery points, implementing safe experimentation'), with only minor coverage gaps; not a 5 because the lead 'what' clause lists just two actions rather than a comprehensive set.	4 / 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, matching the score-5 anchor pattern.	5 / 5
Trigger Term Quality	Natural phrases a user would say ('creating checkpoints', 'rolling back changes', 'managing recovery points', 'safe experimentation') give good coverage; not a 5 because it omits common synonyms/variations and there are no file-extension-style triggers (none apply, but coverage is still short of comprehensive).	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (verification-recovery layer for autonomous coding) with distinct triggers ('checkpoints', 'rollback', 'recovery points') unlikely to fire for unrelated skills; conflict risk is minimal.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Commit: 93ed392

Reviewed: 1 day 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.