economy-mode

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

Quality

64%

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

75%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 with concrete config, verbatim messages, and a clear model-selection table, and its workflows are well-sequenced. The main weakness is repeated restatement of the Layer-priority guardrail across sections, which inflates token usage without adding clarity.

Suggestions

State the Layer 0/1/2 priority rule once in Context and reference it from the spawn workflow, STOP, and Anti-Patterns instead of repeating the full rule each time.

Add a verify step after the persistent config write (e.g. re-read .squad/config.json to confirm economyMode: true merged correctly).

Consider extracting the economy model-selection table into a references/ file if it grows, to keep SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	Content is mostly efficient with compact tables and no concept over-explanation, but the Layer 0/1/2 priority rule is restated roughly four times (Context, spawn step 1, STOP, Anti-Patterns) and could be tightened; not 4 because the redundancy is noticeable rather than minor.	3 / 5
Actionability	Provides exact config paths, a copy-paste JSON snippet, verbatim acknowledgment strings, specific trigger phrases, and a complete model-selection table — fully executable instruction guidance covering the common cases.	5 / 5
Workflow Clarity	Four workflows (session start, phrase trigger, every-spawn, deactivation) are clearly sequenced and acknowledgments act as implicit checkpoints; not 5 because the persistent config-write step has no explicit verification feedback loop.	4 / 5
Progressive Disclosure	No bundle files exist and the skill is self-contained with well-organized headers (SCOPE, Context, Activation, Workflow, Schema, Anti-Patterns); at over 50 lines the simple-skill 5-exception does not strictly apply, so structure is good but not maximal.	4 / 5
	Total	16 / 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 names a clear niche, but it provides only one concrete action and conditions the 'when' on a state ('economy mode is active') rather than giving explicit trigger guidance. Adding a 'Use when...' clause with natural phrases like 'save costs' or 'go cheap' would lift completeness and trigger_term_quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user wants to reduce costs, save money, or go cheap across a session.'

Expand the action list beyond a single 'shifts' verb to surface the concrete outputs (modified selection table, config flag, spawn indicator).

Add natural synonym keywords ('save costs', 'reduce costs', 'budget mode') so the description matches phrases users actually say.

Dimension	Reasoning	Score
Specificity	Names the domain ('Layer 3 model selection') and one concrete action ('Shifts...to cost-optimized alternatives'), matching the anchor for 1-2 concrete actions; not 4 because only a single action is listed rather than several.	3 / 5
Completeness	The 'what' is clear ('Shifts Layer 3 model selection to cost-optimized alternatives'), but 'when economy mode is active' is a state condition rather than explicit 'Use when...' trigger guidance, which the rubric caps at 3.	3 / 5
Trigger Term Quality	Includes 'economy mode' and 'cost-optimized' as relevant keywords but omits natural variations users would actually say ('save costs', 'go cheap', 'reduce costs'), matching the anchor for some keywords missing common synonyms.	3 / 5
Distinctiveness Conflict Risk	'Layer 3 model selection' combined with 'economy mode' carves a clear niche with minor overlap risk against other model-selection skills; not 5 because the description lacks distinct user-facing trigger phrases.	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: a0d2563

Reviewed: about 15 hours 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.