model-right-sizer-install

Stamp a model-right-sizer mandate onto the CURRENT repo's agent-instructions file — `CLAUDE.md`, `AGENTS.md`, or both, whichever the repo has. Idempotent and append-only: an existing file is never overwritten, only the marker-delimited mandate block is inserted or refreshed. The mandate's "before" hook runs `model-right-sizer-dryrun` to produce a schema-conformant JSON blueprint for the orchestrator to route by. Also checks whether the `model-right-sizer` agent and `model-right-sizer-dryrun` skill are discoverable and, if either is missing, installs the `model-right-sizer` Claude Code plugin to fix that (falling back to manual instructions otherwise). Deliberately narrow and organization-agnostic — installs only the right-sizing mandate (plus its own dependencies, if absent), not any broader development process. Use when someone says "install model-right-sizer in this repo", "init this repo for model-right-sizer", "add the right-sizer mandate here", or "make this repo consult model-right-sizer every turn".

Quality

90%

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

81%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 highly actionable and workflow-clear — a verbatim block to stamp, exact commands, a full decision tree, and explicit verify/re-check checkpoints. Its main weakness is conciseness: the same scope-narrowness rationale is repeated across sections and several prose justifications could be trimmed without losing guidance value.

Suggestions

Collapse the repeated scope-narrowness rationale (intro, 'Why this stays isolated from any bigger flow', and the matching lines inside the mandate block) into a single statement so the point is made once.

Compress the 'What "every turn" means in practice' section to a one-line scoping rule; model-right-sizer's own output scaling is already cited and need not be re-explained here.

Trim repeated 'say plainly in your report…' / 'don't let this happen silently' admonitions to a single reporting checklist in step 6.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but padded: the scope-narrowness point is restated three times (intro paragraph, the 'Why this stays isolated' section, and inside the mandate block) and the 'What every turn means in practice' section is largely justification; not 2 because it avoids explaining concepts Claude already knows and stays on-skill, but not 4 because the redundancy could be tightened.	3 / 5
Actionability	Provides copy-paste-ready guidance: the verbatim marker-delimited block, the exact /plugin commands, explicit manual-copy paths, and a concrete file-detection decision tree covering all four cases; not 4 because the common cases are fully specified with no real gaps.	5 / 5
Workflow Clarity	A clear 6-step sequence with explicit validation (step 5 'Verify, don't assume' re-reads every targeted file) and feedback loops (step 2 re-checks discoverability after plugin install, and refuses to stamp silently when prerequisites are still missing); not 4 because checkpoints and error-recovery branches are explicit.	5 / 5
Progressive Disclosure	Good section structure with a well-signaled 'Related' section of one-level-deep links (model-right-sizer.md, model-right-sizer-dryrun/SKILL.md, README.md) and no nested references; not 5 because no bundle files exist and most content is inlined in one ~190-line file, with justification prose that is inline rather than split out.	4 / 5
	Total	17 / 20 Passed

Description

100%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 specific, third-person, and answers both 'what' and 'when' with concrete, natural trigger phrases, scoring at the top of every dimension. Its only weakness is verbosity — implementation detail (the 'before' hook, schema-conformant blueprint) pads what could be a tighter summary — but the description rubric has no conciseness dimension so this does not lower any score.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — stamping a marker-delimited mandate block onto CLAUDE.md/AGENTS.md (idempotent, append-only), running model-right-sizer-dryrun for a schema-conformant blueprint, checking discoverability, and installing the plugin — giving comprehensive coverage; not 4 because no meaningful gaps in action coverage.	5 / 5
Completeness	Explicitly answers both what (stamp/refresh the mandate block, check discoverability, install plugin if missing) and when via a concrete 'Use when...' clause with trigger phrases; not 4 because the 'when' is explicit and specific, not merely present.	5 / 5
Trigger Term Quality	Provides four natural user phrases ('install model-right-sizer in this repo', 'init this repo for model-right-sizer', 'add the right-sizer mandate here', 'make this repo consult model-right-sizer every turn') with synonyms; not below 5 because common phrasing variants are well covered.	5 / 5
Distinctiveness Conflict Risk	Targets a clear niche (installing the model-right-sizer mandate) with distinctive triggers unlikely to fire for unrelated skills; minimal conflict risk, so not a lower anchor.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 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: 4 suspicious	Warning

	Total	14 / 16 Passed

Repository: Cloudzero/cloudzero-claude-marketplace
Path: plugins/model-right-sizer/skills/model-right-sizer-install/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.