CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

qa-deploy-migration-rollback

Verify deployments, database migrations, rollback, environment config, and drift between the repo and the live system. Use before and after any release, schema change, or infrastructure change.

66

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 concise, well-sequenced QA procedure with genuine validation checkpoints and explicit exit criteria, appropriate to its small size. Its main gaps are actionability — no commands or concrete examples for fingerprinting, config inspection, or the smoke journey — and the unexplained "(pattern E3)" reference to material that is not in the skill.

Suggestions

Add one concrete example per risky step — e.g., a sample fingerprint record (build ID, commit SHA, migration version) and a command or technique for reading the effective config inside the running service — to lift actionability.

Replace or inline the "(pattern E3)" reference: either explain the pattern inline in one sentence or drop it, since no pattern catalog exists in the bundle.

Specify the "critical journey" to smoke (e.g., 'the one user-facing path that exercises the changed schema') and add a next step for drift findings, closing the workflow's remaining validation gaps.

DimensionReasoningScore

Conciseness

The ~20-line body is lean and dense ("Fingerprint before and after deploy: build ID, commit, asset hashes, workflow versions, migration version"; "Live state wins; record each difference"): no concept explanations Claude already knows and no padding — every token earns its place.

5 / 5

Actionability

Concrete artifacts are named ("row counts and checksums before and after; constraints valid; down-migration or restore tested") but no executable commands or examples show how to fingerprint, read "the effective config inside the running service", or smoke "the critical journey". The unexplained "(pattern E3)" points to a pattern catalog that exists neither in the skill nor the bundle, leaving key details missing — above the vague-hints level but below 'mostly executable'.

3 / 5

Workflow Clarity

A clear numbered 1–6 sequence with validation checkpoints (checksums/constraints around migrations, "confirm the app works and data written by N is still readable", smoke after deploy and rollback), a BLOCKED escape hatch, and an explicit "Exit criteria" section — so the destructive-operation cap at 3 does not apply. Below 5 because there is no fix/retry loop (failure paths only say "mark BLOCKED") and drift findings have no specified next step.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files, organized into clean "Procedure" and "Exit criteria" sections, which the simple-skill exception would allow to score 5. The dangling "(pattern E3)" reference to a nonexistent external catalog is a minor organization gap that keeps it at 4.

4 / 5

Total

16

/

20

Passed

Description

83%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 strong description: third-person, concise, specific about capability areas, and with an explicit, concrete "Use before and after..." trigger clause. Its only weakness is trigger-term coverage that stops short of common synonyms and a generic umbrella verb "verify" spread across several domains.

DimensionReasoningScore

Specificity

"Verify deployments, database migrations, rollback, environment config, and drift between the repo and the live system" lists several distinct, concrete capability areas in third person. Minor gaps remain (the single verb 'verify' is generic across all listed areas), so it sits just below the comprehensive level 5 anchor.

4 / 5

Completeness

It explicitly answers both what ("Verify deployments, database migrations, rollback, environment config, and drift") and when with concrete trigger phrases ("Use before and after any release, schema change, or infrastructure change"), matching the top anchor exactly. The missing-'Use when' cap does not apply because the trigger clause is explicit.

5 / 5

Trigger Term Quality

Natural terms users would say are present: "deployments", "migrations", "rollback", "release", "schema change", "infrastructure change". A few common variations are missing (e.g., "deploy", "CI/CD", "migrate a database"), matching the 'good coverage, a few natural terms missing' anchor rather than the comprehensive synonym-level anchor.

4 / 5

Distinctiveness Conflict Risk

A clear niche — release/migration verification with rollback rehearsal and repo-vs-live drift checks — with mostly distinct triggers. Minor overlap risk with general deployment or config-management skills due to broad terms like "environment config".

4 / 5

Total

17

/

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

itsablabla/qa-bug-agent-skills

Path

skills/qa-deploy-migration-rollback/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.