secure-raw-data-backup

Archive irreplaceable raw data (sequencing runs, imaging, field data) to write-once cloud cold storage — generate checksums, verify before upload, stream a tarball to S3 Deep Archive under Object Lock, and prove the pipeline with a restore test before trusting it at scale. Use when the user asks to back up or archive raw data, set up an immutable/WORM backup, generate md5 checksums for a data folder, or verify/restore an existing archive.

Quality

97%

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

Quality

Content

92%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 strong, highly actionable operational skill with a well-sequenced, validation-rich workflow and clean progressive disclosure. The only friction is minor verbosity from narrative rationales that could be tightened without losing value.

Suggestions

Trim the mid-analysis war story in Step 2 to its lesson (freeze before hashing) to save tokens without losing the correction.

The measured compression example (0.004% on fastq.gz) could move to cost_model.md, leaving the rule and the probe command inline.

Condense the "Why it is built the way it is" bullet rationale in Step 2 into a single line per bullet.

Dimension	Reasoning	Score
Conciseness	The body is dense and operationally efficient — it does not re-explain S3, tar, or md5 — but the embedded war-story anecdotes and measured-number rationales, while useful, add length that could be trimmed in places; it sits just below fully lean.	4 / 5
Actionability	Copy-paste executable commands appear throughout (the inventory loop, `chmod -R a-w`, the compression probe, `scripts/backup_to_cloud.sh --dry-run`, the `nohup` invocation, `aws s3api head-object`, `list-multipart-uploads`) covering the common cases.	5 / 5
Workflow Clarity	Steps 0–7 are explicitly sequenced with validation checkpoints (freeze before hash, refuse-on-mismatch, Step 5 verify, Step 6 restore test) and feedback loops (dry-run first, orphaned-multipart check before retry, manifest-as-completion-marker); the golden rules act as a checklist. The destructive/batch cap at 3 does not apply because validation is extensive.	5 / 5
Progressive Disclosure	SKILL.md is an overview with one-level-deep references (bucket_setup.md, verification.md, cost_model.md, config.example.sh, generate_checksums.sh, backup_to_cloud.sh), all real files, each summarized in the "Available resources" section with clear navigation; detail is appropriately deferred.	5 / 5
	Total	19 / 20 Passed

Description

100%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.

An exemplar description: concrete actions, explicit trigger guidance with natural phrasing and synonyms, and a clearly bounded niche. No vague fluff or over-claims; third person throughout.

Dimension	Reasoning	Score
Specificity	"generate checksums, verify before upload, stream a tarball to S3 Deep Archive under Object Lock, and prove the pipeline with a restore test" lists multiple concrete, distinct actions covering the full archive pipeline with no significant gaps.	5 / 5
Completeness	It explicitly answers what ("Archive irreplaceable raw data... generate checksums, verify before upload, stream a tarball...") and when ("Use when the user asks to back up or archive raw data...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	The "Use when" clause surfaces natural phrases users would say ("back up or archive raw data", "immutable/WORM backup", "generate md5 checksums", "verify/restore") including synonyms like back up/archive and immutable/WORM.	5 / 5
Distinctiveness Conflict Risk	The write-once cloud cold storage / Object Lock / S3 Deep Archive niche with raw-data framing is highly specific and unlikely to trigger for unrelated skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: brunoasm/my_claude_skills
Path: secure_raw_data_backup/SKILL.md
Commit: 5bdff99

Reviewed: 6 days 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.