Tessl • The management layer for AI agent skills

SkillPublic

yaml

YAML wire format for json-render with streaming parser, prompt generation, and AI SDK transform. Use when working with @json-render/yaml, YAML-based spec streaming, yaml-spec/yaml-edit fences, or YAML prompt generation.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

76%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 API-oriented skill: fully executable examples throughout, tight non-padded prose, and good section organization. Main gaps are the absence of an explicit end-to-end workflow (the pieces are documented but their composition is implicit) and some redundant restating of the fence types across sections.

Suggestions

Add a short end-to-end workflow section showing how the pieces compose (yamlPrompt generates the system prompt, the LLM emits yaml-spec/yaml-edit fences, pipeYamlRender transforms them into patches), so the pipeline assembly is explicit rather than inferred.

Consolidate the four fence types into one canonical description (currently repeated in Key Concepts, the transform section, Fence Constants, and the exports table) to remove redundancy and save tokens.

Include brief error/validation guidance — e.g., how the streaming parser behaves on malformed YAML or an unterminated fence, and how to detect and recover — to add a feedback loop to the workflow.

Dimension	Reasoning	Score
Conciseness	The body is lean — almost entirely executable code, option lists, and a table — with no explanation of concepts Claude already knows. Not 5 because the four fence types are documented redundantly (Key Concepts bullets, the 'recognizes four fence types' list, Fence Constants, and the Key Exports table), so some tokens could be trimmed; not 3 because there is no padded prose or unnecessary explanation.	4 / 5
Actionability	Every section contains complete, copy-paste-ready TypeScript with imports: yamlPrompt with options, pipeYamlRender including multi-turn previousSpec, compiler push/flush/reset, and buildEditInstructions/buildEditUserPrompt. Method signatures and exported constants are documented concretely, covering the common cases.	5 / 5
Workflow Clarity	Sections are organized by API area rather than task sequence: the end-to-end pipeline (generate prompt, LLM emits fences, transform, patches applied) is left implicit, and there is no validation or error-recovery guidance for malformed input. Not 4 because no explicit sequence with checkpoints exists to follow; not 2 because each individual section's usage is unambiguous and complete.	3 / 5
Progressive Disclosure	Well-organized single-file skill with clear section headers and an exports table, no buried content. Not 5 because the ~135-line body exceeds the simple-skill threshold and the API reference detail (full exports table, all API examples) could live in a one-level-deep reference file; not 3 because the structure is good and nothing that clearly belongs elsewhere is awkwardly inlined.	4 / 5
	Total	16 / 20 Passed

Description

87%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.

Strong description: it concisely states concrete capabilities and provides an explicit 'Use when' clause with four package-specific triggers. Third-person voice is used correctly and there is no fluff. The only improvement space is broader natural-term coverage (e.g., streaming YAML, yaml-patch/diff).

Dimension	Reasoning	Score
Specificity	"streaming parser, prompt generation, and AI SDK transform" lists several specific capabilities, matching the several-specific-actions anchor. Not 5 because capabilities are framed as noun phrases and coverage of the package surface (edit modes, diff, low-level compiler) is partial in the description; not 3 because it names more than 1-2 concrete actions.	4 / 5
Completeness	The description explicitly answers what ("YAML wire format for json-render with streaming parser, prompt generation, and AI SDK transform") and when ("Use when working with @json-render/yaml, YAML-based spec streaming, yaml-spec/yaml-edit fences, or YAML prompt generation") with four concrete trigger phrases. Not 4 because the 'when' clause is explicit and enumerated, not weakly implied; voice is third person throughout.	5 / 5
Trigger Term Quality	"@json-render/yaml", "yaml-spec/yaml-edit fences", "YAML-based spec streaming", and "YAML prompt generation" give good coverage of the terms a user of this package would naturally say. Not 5 because common variations like streaming YAML, yaml-patch/diff fences, or generic json-render rendering tasks are missing.	4 / 5
Distinctiveness Conflict Risk	Every trigger is tied to json-render/yaml-specific artifacts (the package name and fence names), giving a clear niche with minimal conflict risk. Not 4 because no meaningful overlap with generic YAML skills exists — the triggers are all qualified.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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: vercel-labs/json-render
Path: skills/yaml/SKILL.md
Revision: 1819412

Reviewed: 22 days ago

Discovery Implementation Validation

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.

yaml

Table of Contents

Is this your skill?