CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

database-admin

Database administration tasks including schema changes, backups, monitoring, and user access management.

Quality

82%

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

96%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 operational skill: lean, fully executable commands and SQL with explicit validation and feedback loops around destructive operations (rollback on migration failure, verify-before-delete for backups, post-restore sanity checks). The only structural gap is that all content lives inline in one ~143-line file with no one-level-deep reference files to split out the larger SQL playbooks.

DimensionReasoningScore

Conciseness

The body is command-first and lean: steps are executable commands or terse conventions (e.g. 'Filename: `<YYYYMMDDHHMMSS>_<short_description>.sql`') with no explanations of concepts Claude already knows. It matches the anchor 'Lean and efficient; assumes Claude's competence; every token earns its place' — the single intro sentence is the only near-redundant line.

5 / 5

Actionability

Fully executable, copy-paste-ready guidance throughout: `pg_dump $DATABASE_URL > backup_$(date +%Y%m%d_%H%M%S).sql`, complete CREATE ROLE/GRANT/DROP ROLE SQL blocks, and ready-to-run pg_stat_activity/pg_stat_user_indexes queries. Placeholders (<username>, <env>, <pid>) appear only where values are genuinely variable, matching 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases'.

5 / 5

Workflow Clarity

Multi-step workflows are clearly sequenced with explicit validation and feedback loops: 'Confirm the migration applied', 'If the migration fails, roll back', backup step 6 'Delete the local copy after confirming upload' (verification before destructive deletion), a post-restore sanity check ('SELECT COUNT(*) FROM users; should match pre-backup count'), and an access audit query. This matches 'Clear sequence with explicit validation steps; feedback loops for error recovery' and is not capped since destructive/batch operations do have validation.

5 / 5

Progressive Disclosure

A single well-sectioned file (~143 lines) with clearly headed domains (migrations, backups, monitoring, access) and consolidated 'Shared Reference' sections that avoid duplication. It sits between anchor 4 ('Good structure; most content is appropriately placed') and anchor 5: the content is well organized but nothing is split into reference files (e.g. the role-creation and monitoring SQL playbooks), so it falls short of 'well-signaled one-level-deep references; content appropriately split'. Not 3, since structure is clearly better than 'some structure; references not clearly signaled'.

4 / 5

Total

19

/

20

Passed

Description

58%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 clearly communicates what the skill covers via four concrete task areas, but it entirely lacks 'when to use' trigger guidance and omits natural trigger synonyms (migrations, restore, Postgres, roles/permissions, slow queries), leaving completeness and trigger-term quality at the middle of the scale. Distinctiveness is decent but would be sharper if the PostgreSQL scope were stated.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when the user asks to run or review schema migrations, back up or restore the database, investigate slow queries or connection issues, or create/revoke database users.'

Include natural synonyms and keywords users actually say: PostgreSQL/Postgres, migrations, restore, roles, permissions, slow queries, connection pooling.

State the PostgreSQL-specific scope explicitly (e.g. 'PostgreSQL database administration...') to reduce overlap with generic SQL, DevOps, or other-database admin skills.

DimensionReasoningScore

Specificity

The description lists several specific task areas — 'schema changes, backups, monitoring, and user access management' — matching anchor 4 ('Lists several specific actions; minor gaps in coverage'). It is above anchor 3 (only 1-2 concrete actions) but below anchor 5 because coverage is not comprehensive (no restore, performance tuning, or replication).

4 / 5

Completeness

The 'what' is clear (four concrete task areas under 'Database administration tasks including...'), but there is no 'Use when...' clause or any equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3. It fits anchor 3 ('Has a clear what but when is missing or only weakly implied').

3 / 5

Trigger Term Quality

Some relevant keywords are present ('schema changes', 'backups', 'monitoring', 'user access management'), but common variations users would naturally say are missing: 'migrations', 'restore', 'Postgres/PostgreSQL', 'roles', 'permissions', 'slow queries'. This matches anchor 3 ('Some relevant keywords but missing common variations or synonyms') rather than 4, where only a few natural terms would be missing.

3 / 5

Distinctiveness Conflict Risk

'Database administration' with its four named task areas is a mostly distinct niche with minor overlap risk against closely related skills (generic SQL assistants, DevOps/infra skills, IAM tooling), matching anchor 4. It is below anchor 5 because the description names no explicit triggers and omits 'PostgreSQL', which would sharpen the niche.

4 / 5

Total

14

/

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

tesslio/product-plugins

Path

plugin-creator/evals/scenario-1/inputs/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.