CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

write-script-postgresql

MUST use when writing PostgreSQL queries.

Quality

63%

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

Fix and improve this skill with Tessl

tessl review fix ./system_prompts/auto-generated/skills/write-script-postgresql/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

The body is a dense, highly actionable operational guide: every command and SQL snippet is executable, decision rules for preview/run/deploy are explicit, and validation checkpoints (dry-run, diff, preview-before-deploy) are woven in. Its weaknesses are repetition of the same deploy/metadata warnings three to four times, and a single-file layout that inlines general Windmill script-writing guidance into a PostgreSQL-specific skill with inconsistent heading levels.

Suggestions

Deduplicate: state the 'deploy only when explicitly asked' and 'generate-metadata is not a deploy' policies once in a single policy block instead of repeating them in the command list, the preview-vs-run section, and the after-writing section.

Move the general all-language guidance (General Principles, Return Values, Preprocessor Scripts) to a shared reference file (e.g. references/script-writing.md) referenced by each per-language skill, keeping only the CLI workflow and PostgreSQL section in SKILL.md.

Normalize heading levels (one H1, H2 sections) and add a short ordered checklist of the full flow: write → wmill generate-metadata → wmill script preview → deploy only on explicit request.

DimensionReasoningScore

Conciseness

Nearly all content is Windmill-specific operational knowledge Claude does not already know (wmill commands, lock-hash mechanics, S3 directives), so there is no concept-explanation padding — but the same policies are repeated verbatim several times: "Only suggest/run a deploy when the user explicitly asks" (lines 15, 25-27, 45), and generate-metadata-is-not-a-deploy (lines 14, 33, 45). Sentences like the resource-type bullet and the metadata paragraph are long multi-clause run-ons that could be tightened. Mostly efficient with noticeable duplication to trim, matching anchor 3.

3 / 5

Actionability

Fully executable throughout: exact commands (`wmill script preview <script_path>`, `wmill generate-metadata --dry-run`, `wmill generate-metadata rehash`, `wmill script preview <path> -d '<args>'`, `wmill resource-type list --schema`) and copy-paste-ready SQL (`SELECT * FROM users WHERE name = $1::TEXT AND age > $2::INT;`, `jsonb_to_recordset($1::jsonb) AS r(id INT, name TEXT)`, `-- s3 prefix=exports/users format=parquet`) cover the common cases, including per-language placeholder syntax.

5 / 5

Workflow Clarity

Explicit decision rules sequence the workflow ("If the user says 'run the script'... use script preview"; "Only use sync push when...") and validation checkpoints are present — preview validates before any deploy, `--dry-run` lists stale items before narrowing, and the regenerated .lock files are diffed and version changes reported before deploying. Not 5 because the end-to-end sequence (write → generate-metadata → preview → deploy) is never laid out as one ordered flow; the reader must assemble it from four separate subsections, and the ordering of metadata regeneration vs. preview is only implicit.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), so everything is inlined in one 114-line file. Structure exists (##/### sections) but heading levels are inconsistent ("# Windmill Script Writing Guide" and "# PostgreSQL" appear as H1s mid-document after top-level H2s), and general all-language Windmill guidance (General Principles, Return Values, Preprocessor Scripts — the latter explicitly TS/Python-only) is inlined in a PostgreSQL-specific skill where it belongs in a shared reference for the per-language skill family. Some structure, but content that should be separate is inline — anchor 3.

3 / 5

Total

15

/

20

Passed

Description

36%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 has a clear, explicit trigger clause but completely omits what the skill does. It reads as a bare imperative rather than a capability description, which limits discoverability and makes it indistinguishable from a generic PostgreSQL-help skill. Adding a one-sentence 'what' plus natural synonyms (SQL, Postgres, Windmill) would lift it substantially.

Suggestions

State what the skill does before the trigger, e.g. "Write and test Windmill PostgreSQL scripts: parameterized $1::type queries, (s3object) parameters, streaming results to S3, and the wmill preview / generate-metadata / deploy workflow. MUST use when writing PostgreSQL queries or scripts for Windmill."

Add natural synonyms users actually say — "SQL", "Postgres", "Windmill script" — to improve trigger-term coverage.

Scope the trigger to the Windmill context ("PostgreSQL scripts in Windmill") to avoid firing on plain psql/SQL help requests.

DimensionReasoningScore

Specificity

The description "MUST use when writing PostgreSQL queries" names a concrete domain (PostgreSQL queries) but lists zero concrete actions or capabilities — it says nothing about what the skill actually provides (Windmill script authoring, preview/metadata/deploy workflow, S3 streaming). It is not a 1 because "PostgreSQL queries" is a specific domain rather than pure abstraction, and not a 3 because no concrete actions (analogous to "extracts content", "fills forms") are stated at all.

2 / 5

Completeness

The trigger ('when') is explicitly present ("MUST use when writing PostgreSQL queries"), but the 'what' is entirely missing — the description never states what the skill does (write Windmill PostgreSQL scripts, keep lock metadata in sync, stream results to S3). This is the mirror image of the anchor-3 example (clear what, missing when), so by symmetry it lands at 3: one half explicit, the other absent.

3 / 5

Trigger Term Quality

"PostgreSQL queries" is a natural phrase a user would say, but coverage is essentially one keyword phrase; common variations and synonyms users actually type — "SQL", "Postgres", "psql", "queries" alone — are missing. Not 4 because anchor-4 descriptions cover several natural terms, while this has effectively a single one.

3 / 5

Distinctiveness Conflict Risk

"writing PostgreSQL queries" carves out a specific niche, but the trigger would also fire for plain psql/SQL work that has nothing to do with Windmill — the skill's actual subject — creating overlap risk with generic SQL/Postgres skills. Not 4 because a mostly-distinct description would scope the trigger to its actual domain (e.g. Windmill PostgreSQL scripts).

3 / 5

Total

11

/

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

windmill-labs/windmill

Path

system_prompts/auto-generated/skills/write-script-postgresql/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.