CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dbops-changeset

Generates Liquibase database changesets via a structured workflow: resolve schema+instance (from context or via API discovery), confirm DB engine type, generate Liquibase YAML, and present for HITL review with Accept / Deny / Accept & Commit actions. Use when asked to create, modify, or drop database tables, columns, indexes, or constraints as a Liquibase changeset, generate a database migration, or fix a failed migration. Supports update mode (refine existing changeset) and error-recovery mode (fix a failed migration).

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/claude/skills/dbops-changeset/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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 dense, highly actionable operational workflow with genuine validation checkpoints and a well-designed error-recovery feedback loop, undermined by a broken progressive-disclosure design — all Liquibase generation rules live in a reference.md that is not shipped — and by notable repetition across the Important Rules, gate-protocol, and error-recovery sections. Tightening the duplication and shipping the missing reference file would lift it substantially.

Suggestions

Ship reference.md in the skill bundle (or inline the essential Liquibase YAML rules): the body defers all generation rules, FK column resolution, and error-recovery root causes to a file that does not exist, breaking Step 4, 3-B-4, and Error Recovery step 2.

Deduplicate repeated instructions — the verbatim-error/openInHarness rules appear in Steps D, E, F, and Important Rules, and failure classification appears in both Step F triage and Error Recovery step 1a; state each once and reference it.

Standardize step numbering and heading levels ("### Step 4" vs "## Step 5", the "Steps A–E" reference, nested 3-B) and document the source of unresolved placeholders like <org_id>, <project_id>, and <account>.

DimensionReasoningScore

Conciseness

The body is mostly operational, domain-specific instruction (MCP resource calls, gate protocol, engine-prefix table) that Claude could not know, but it is noticeably repetitive: "surface the exact error message verbatim and stop / Do NOT fabricate navigation paths / never construct the URL manually" appears in Steps D, E, F, and Important Rules; the accept/deny/accept-commit rules and conversation_id resolution are stated twice; and the infrastructure-vs-changeset failure classification is duplicated between Step F triage and Error Recovery step 1a. Anchor 3 ("could be tightened") fits better than 4, where the duplication is more than minor.

3 / 5

Actionability

Concrete, near-copy-paste tool calls with exact args (harness_list/harness_get/harness_execute blocks), deterministic reply strings, decision tables, and worked author-normalization examples make this largely executable. Not 5, because some placeholders are never resolved (where do `<org_id>`, `<project_id>`, `<account>` come from?), and Step C's elicitation loop is currently superseded by the server-side "stop and tell the user" note, leaving the documented loop unexecutable as written.

4 / 5

Workflow Clarity

Sequencing is clear (Step 0 context check → discovery → engine resolution → snapshot checks → generation → HITL review gate → accept/deny/commit branches) with explicit validation checkpoints (conflict check in 3-B-2, the mandatory Accept/Deny review, error-recovery feedback loop with failure classification). Not 5, because of labeling drift ("### Step 4" vs "## Step 5", a gate-protocol reference to "Steps A–E" vs the actual A–F, nested 3-B) and because Step 4's execution path depends entirely on a reference.md that is absent from the bundle, leaving a gap in the otherwise well-validated workflow.

4 / 5

Progressive Disclosure

The body repeatedly defers bulk detail to a single one-level-deep reference ("Before generating Liquibase YAML, Read `reference.md`... It contains all Liquibase YAML rules"), but no reference.md exists in the bundle — references/, scripts/, and assets/ are all absent, so every reference to it (Step 4, 3-B-4, Error Recovery step 2) is dangling and the disclosed content is simply missing. Per the bundle-structure guideline this is worse than the anchor-3 case of merely unclear references; the claimed disclosure layer does not exist, matching anchor 2's "minimal structure" failure.

2 / 5

Total

13

/

20

Passed

Description

92%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, concrete, enumerates the workflow stages and both special modes, and pairs them with an explicit "Use when" clause of natural trigger phrases. The only weakness is slightly incomplete synonym coverage of trigger terms (missing "alter table", "add column", "schema change", "DDL").

DimensionReasoningScore

Specificity

Quotes like "resolve schema+instance (from context or via API discovery), confirm DB engine type, generate Liquibase YAML, and present for HITL review with Accept / Deny / Accept & Commit actions" enumerate the full pipeline as concrete actions, and "update mode (refine existing changeset)" and "error-recovery mode (fix a failed migration)" cover the special modes — comprehensive with no gaps. Not 4, because there are no minor coverage gaps; every operational capability of the skill is explicitly named in third person.

5 / 5

Completeness

It explicitly answers "what" ("Generates Liquibase database changesets via a structured workflow: resolve schema+instance... generate Liquibase YAML, and present for HITL review") and "when" with a concrete "Use when asked to..." clause listing specific intents including the update and error-recovery modes. Not 4, because the "when" clause is already explicit and trigger-phrase-level, matching the anchor-5 example pattern exactly.

5 / 5

Trigger Term Quality

"Use when asked to create, modify, or drop database tables, columns, indexes, or constraints as a Liquibase changeset, generate a database migration, or fix a failed migration" covers the natural phrasings users would say for this task. Not 5, because common synonyms are missing — e.g. "add a column", "alter table", "schema change/migration", "DDL" — so a few natural trigger phrases would not match. Not 3, because the coverage goes well beyond a couple of generic keywords.

4 / 5

Distinctiveness Conflict Risk

"Liquibase changeset", "database migration", and "fix a failed migration" carve out a clear niche that would not collide with generic SQL, ORM, or document skills; the Harness DBOPS framing further narrows it. Not 4, because there is no meaningful overlap risk with closely related skills — the trigger vocabulary is unambiguous.

5 / 5

Total

19

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (617 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

harness/harness-ai

Path

plugins/claude/skills/dbops-changeset/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.