economy-mode

Shifts Layer 3 model selection to cost-optimized alternatives when economy mode is active.

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./.squad/skills/economy-mode/SKILL.md

Quality

Content

82%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 highly actionable and well-structured, with concrete model mappings, exact config, and clear sequenced workflows including a STOP guard; the main weaknesses are mild redundancy of the override-priority rule and a missing verify step on the persistent config write.

Dimension	Reasoning	Score
Conciseness	The body is efficient and well-organized with tables and scoped statements rather than padded prose, but the 'economy mode does NOT override Layer 0/1/2' rule is restated several times across Context, Workflow, and Anti-Patterns, which is minor over-explanation that could be trimmed.	4 / 5
Actionability	Fully executable guidance: an exact model selection table with concrete model IDs, exact config JSON, exact trigger phrases, CLI flag, and copy-paste acknowledgment strings cover all common cases.	5 / 5
Workflow Clarity	Sequences are clearly laid out (session start, session-only vs persistent trigger, per-spawn priority checks, deactivation, STOP) with a STOP guard, but the persistent config write lacks an explicit verify-after-merge checkpoint, leaving a minor validation gap.	4 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), so the single-file body is scored on its structure: clear section headers (SCOPE, Context, Activation, Table, Workflow, Config Schema, Anti-Patterns) with no nested or buried references, well-organized with minor room to split the model table into a reference file.	4 / 5
	Total	17 / 20 Passed

Description

53%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 and distinct, naming a clear domain and action with a defining condition, but it omits explicit 'Use when...' trigger guidance and natural user phrasings, which limits completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when the user wants to save costs, go cheap, or reduce model spending across a session').

Include common natural synonyms users would actually say ('save costs', 'reduce costs', 'go cheap') directly in the description rather than only in the body.

Optionally enumerate the concrete effects (e.g., 'shifts Layer 3 model selection to lower-cost alternatives and writes economyMode to config') to raise specificity from a single action to comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Layer 3 model selection') and one concrete action ('Shifts ... to cost-optimized alternatives') with a clear condition, matching the score-3 anchor of domain plus 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	Clearly states the 'what' (shifts Layer 3 model selection) but lacks an explicit 'Use when...' trigger clause — the 'when economy mode is active' condition describes state, not invocation guidance, so completeness is capped at 3 per the rubric.	3 / 5
Trigger Term Quality	Contains relevant keywords ('economy mode', 'cost-optimized') but misses the natural user phrasings ('save costs', 'go cheap', 'reduce costs') that appear only in the body, matching 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The 'Layer 3 model selection' + 'economy mode' niche is mostly distinct with minimal overlap risk, though 'cost-optimized alternatives' could marginally collide with general cost skills; not a 5 because trigger phrasing is less comprehensive than the 5-anchor example.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: bradygaster/squad
Path: .squad/skills/economy-mode/SKILL.md
Commit: 9587fcd

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.