model-right-sizer-schema

Prescribe a minimal output schema for ONE agent's handoff to its controller — the `model-right-sizer` agent's "Agent-to-agent message-schema design" lever, scoped to a single seam instead of a whole flow's blueprint. Given a target agent (a path to an existing agent `.md` file, or a description of one not yet written), returns a schema-conformant JSON prescription (`schemas/agent-schema.schema.json`) naming the reusable family the agent's reply fits, typed `in`/`out` fields, an exclusion list, and a ready-to-insert `## Agent-to-agent schema` markdown stamp — reproduced here in portable, organization-agnostic form. Offers to stamp that block directly into the target agent's file, idempotently. The point: an agent that used to hand its controller unscoped prose now hands it typed fields plus one bounded prose slot. Use when someone says "give this agent an output schema", "prescribe a schema for …", "minimize what this agent returns", or "stamp an agent-to-agent contract on …".

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/model-right-sizer/skills/model-right-sizer-schema/SKILL.md

Quality

Content

66%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 well-sequenced, validated workflow with concrete commands and clear external references, but it is notably verbose — several sections restate the same invariant multiple times and include meta-commentary that pads the token budget without adding guidance.

Suggestions

Tighten the 'Untrusted input' blockquote: state the data-vs-instructions rule once and drop the comparisons to model-right-sizer-audit and the repeated re-justification of why the confirmation gate is not sufficient.

Compress step 7's marker-matching cases by stating the count-then-branch rule once and listing the cases as a compact table or bulleted enum, removing the repeated 'stop for a human' refrains and the 'earlier version of this skill made' meta-commentary.

Consider extracting the detailed marker-state taxonomy in step 7 into a references file (e.g. MARKER-STATES.md) and summarizing the decision rule inline, which would improve both conciseness and progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose with several padded sections — the 'Untrusted input' blockquote re-explains the data-vs-instructions distinction at length and step 7 restates the marker-matching constraints multiple times with meta-commentary like 'the mistake an earlier version of this skill made'.	2 / 5
Actionability	Provides an executable validation command ('echo "$PRESCRIPTION_JSON" \| uv run --no-project --with jsonschema scripts/validate_agent_schema.py -'), named schema/catalogue files, and concrete dispatch instructions; minor gaps since the actual JSON shape lives in referenced files.	4 / 5
Workflow Clarity	An 8-step sequence with an explicit validate-before-stamp checkpoint (step 6), a re-emit-on-invalid feedback loop, a user confirmation gate, and a re-read-after-write verification — exactly the feedback-loop discipline a destructive file-writing skill needs.	5 / 5
Progressive Disclosure	Well-sectioned body with one-level-deep, clearly signaled markdown references (schema.json, example.json, families.md, sibling skill); the only gap is the very long step-7 marker-matching logic being inlined rather than split into a reference file.	4 / 5
	Total	15 / 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, third-person description that concretely names the skill's actions and gives explicit trigger phrases for when to use it. The only mild gap is trigger-term breadth, since the abstract domain offers no file extensions or obvious synonyms to round out coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'returns a schema-conformant JSON prescription ... naming the reusable family ... typed in/out fields, an exclusion list, and a ready-to-insert ## Agent-to-agent schema markdown stamp' and 'Offers to stamp that block directly into the target agent's file, idempotently' — comprehensive and specific rather than vague.	5 / 5
Completeness	Explicitly answers both 'what' (prescribe a minimal output schema, return a JSON prescription with named family/fields/exclusion/stamp) and 'when' ('Use when someone says ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural quoted trigger phrases users would say ('give this agent an output schema', 'prescribe a schema for ...', 'minimize what this agent returns', 'stamp an agent-to-agent contract on ...') but lacks the synonyms/file-extension breadth of a top anchor since the domain has no natural file extensions.	4 / 5
Distinctiveness Conflict Risk	Carves a clear single-seam niche ('scoped to a single seam instead of a whole flow's blueprint') and distinguishes itself from the sibling model-right-sizer-dryrun, with distinct triggers and minimal overlap risk.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 10 suspicious	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: Cloudzero/cloudzero-claude-marketplace
Path: plugins/model-right-sizer/skills/model-right-sizer-schema/SKILL.md
Commit: 62c27f3

Reviewed: 1 day ago

Table of Contents

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.