CtrlK
BlogDocsLog inGet started
Tessl Logo

apify-generate-output-schema

Generate output schemas (dataset_schema.json, output_schema.json, key_value_store_schema.json) for an Apify Actor by analyzing its source code. Use when creating or updating Actor output schemas.

60

Quality

71%

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 ./skills/apify-generate-output-schema/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 content is a well-sequenced, highly actionable 7-phase procedure with strong JSON templates and an explicit validation phase. Its weak spots are repetition of the same hard rules across four locations, inlined reference bulk that could be split into separate files, and a manual validation step instead of an executable validator with a retry loop.

Suggestions

Consolidate the repeated hard rules (nullable, additionalProperties+required on both levels) into a single source of truth and reference it from the checklist and warning rather than restating them verbatim in four places.

Move the field-type pattern catalog, anonymized-example table, and template-variable list into a references/ file (e.g. FIELD_TYPES.md) and link to it from Phase 2 so SKILL.md stays a lean overview.

Add an executable validation step (or a documented validator command) and an explicit 'if validation fails -> fix -> re-validate -> only proceed when valid' loop in Phase 6 to turn the manual checklist into a feedback loop.

DimensionReasoningScore

Conciseness

The body avoids teaching basics Claude already knows and stays concrete, but the same hard rules (nullable, additionalProperties+required on both levels) repeat across the core principles, hard-rules table, warning callout, and Phase 6 checklist, and the 7-block field-type catalog is reference bulk that could be tightened.

3 / 5

Actionability

Provides copy-paste-ready JSON templates for all three schema files, concrete per-field-type patterns, specific JS/Python search terms, and an explicit template-variable list; it is 4 rather than 5 because there is no complete end-to-end worked example for one real Actor and Phase 6 validation is a manual checklist rather than an executable command.

4 / 5

Workflow Clarity

A clear seven-phase sequence with explicit Goals and Actions, a dedicated Phase 6 validation checklist, and a 'present to user for review before writing' checkpoint; it is 4 rather than 5 because the explicit 'if validation fails -> fix -> re-validate' retry loop that anchor 5 highlights is not spelled out and there is no runnable validator.

4 / 5

Progressive Disclosure

No bundle files exist and the skill is a monolithic ~410-line document with reference-like catalogs (field-type patterns, template variables, anonymized-example table) inlined rather than split into referenced files; internal section structure is good, matching anchor 3's 'some structure but content that should be separate is inline', but there is no file-level navigation or one-level-deep referencing to reach anchor 4.

3 / 5

Total

14

/

20

Passed

Description

78%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 is concrete, domain-specific, and explicitly pairs a 'what' with a 'Use when' trigger, scoring well across all dimensions. Its main limitation is a slightly narrow single-trigger 'when' clause and limited synonym variation, which keep trigger quality and completeness at 4 rather than 5.

DimensionReasoningScore

Specificity

Names three concrete schema artifacts (dataset_schema.json, output_schema.json, key_value_store_schema.json) plus the 'analyzing its source code' action, giving comprehensive artifact coverage; it stays at 4 rather than 5 because only two distinct verb-actions ('generate', 'analyze') appear, narrower than the multi-verb anchor 5 example.

4 / 5

Completeness

Explicitly answers both 'what' (generate the three named schemas by analyzing source code) and 'when' ('Use when creating or updating Actor output schemas'); it is 4 rather than 5 because the 'when' clause is a single focused trigger rather than the multiple concrete trigger phrases the anchor 5 example lists.

4 / 5

Trigger Term Quality

Includes natural domain terms ('output schema', 'Apify Actor') and three concrete .json filenames that serve as file-extension-style triggers; it is not 5 because synonym coverage is limited and natural phrasing variations a user might say are thin.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (Apify Actor output schemas with three named file artifacts) and uses distinct, domain-specific triggers, making overlap with other skills minimal; this matches the anchor 5 'clear niche with distinct triggers; minimal conflict risk'.

5 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
apify/agent-skills
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.