CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/backup-verification-author

Author backup-verification harness - per-backup-type integrity (SHA-256 / encrypted-payload signature), restore-to-test-env spot-check cadence, partial-restore (single-table / single-object) verification, cross-region replication validation, retention-policy assertions. "An untested backup is not a backup." Use when a service's backups have never been restore-tested, when the backup tool is being swapped, or when an audit needs proof that backups are integrity-checked and restorable.

75

Quality

94%

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

Overview
Quality
Evals
Security
Files

Quality

Content

87%

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

The body is dense, executable, and well-structured as a verification-harness authoring guide, scoring high on conciseness, actionability, and progressive disclosure. The main gap is workflow clarity: it defines validation at each step but lacks validate->fix->retry feedback loops for the destructive/batch operations it covers.

Suggestions

Add explicit error-recovery feedback loops for the database/batch operations - e.g., 'if the SHA check fails, re-run the backup with verbose logging and re-verify; if the restore spot-check fails, alert the on-call and open a ticket' - to move from validation-only to a validate->fix->retry cycle.

In Step 6, wrap the retention test's head_object call in try/except inside the code block itself rather than only noting it afterward, so the example is correct and executable as written.

Add a short 'Definition of done / audit checklist' consolidating the assertions across all eight steps, so an auditor can verify the harness is complete in one pass.

DimensionReasoningScore

Conciseness

The body is lean and code-heavy - concrete tables and executable bash/yaml/python blocks with only brief, load-bearing framing (e.g., "Backups silently fail in many ways...") rather than explanations of concepts Claude already knows.

3 / 3

Actionability

Provides fully executable code and commands throughout - pg_dump/sha256sum/gpg pipelines, a CI cron job, pg_restore and S3 version-id commands, and pytest functions - that are copy-paste ready, matching the score-3 anchor.

3 / 3

Workflow Clarity

Steps 1-8 are clearly sequenced with explicit verification checkpoints (SHA match, signature verify, count>0), but error-recovery feedback loops (validate -> fix -> retry) are absent for database/batch operations, which the rubric caps at 2.

2 / 3

Progressive Disclosure

A single well-organized file with clearly labeled sections and a References block pointing one level deep to sibling skills (dr-drill-runner, restore-time-tests, secrets-rotation-runner) and an external DR guide, with no nested references.

3 / 3

Total

11

/

12

Passed

Description

100%

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, specific enumerated capabilities, and an explicit multi-trigger "Use when" clause covering what and when. It is distinguishable from sibling skills like restore-time-tests and dr-drill-runner. No changes needed.

DimensionReasoningScore

Specificity

Lists multiple concrete actions - "per-backup-type integrity (SHA-256 / encrypted-payload signature), restore-to-test-env spot-check cadence, partial-restore (single-table / single-object) verification, cross-region replication validation, retention-policy assertions" - matching the score-3 anchor for multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both what (authors a backup-verification harness with enumerated capabilities) and when (an explicit "Use when..." clause with three concrete triggers), matching the score-3 anchor.

3 / 3

Trigger Term Quality

Natural triggers a user would say appear in the "Use when" clauses - "backups have never been restore-tested", "backup tool is being swapped", "audit needs proof that backups are integrity-checked and restorable" - with good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

It carves a clear niche (verification/restorability of backups, not restore-time SLA or drill execution) with distinct triggers, making conflict with adjacent skills unlikely.

3 / 3

Total

12

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Reviewed

Table of Contents