CtrlK
BlogDocsLog inGet started
Tessl Logo

compute-ladder

Model selection by provider health, not task complexity. Tier 0 (local) handles most tasks. Paid models are break-glass only. Fallbacks activate on 429 or timeout — never on perceived task difficulty.

59

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./examples/jason-my-claw-is-the-law-deebee-4567b4/skills/compute-ladder/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

87%

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 tight, highly actionable reference with executable commands and concrete triggers, well-organized into clear sections. Its only gap is the absence of an explicit sequenced workflow with validation checkpoints, since it is structured as a policy rather than a procedure.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — tier tables, DO/DO-NOT fallback rules, and curl health/cost checks carry no explanatory padding, and every section earns its place.

3 / 3

Actionability

Provides fully executable bash commands for health checks and cost monitoring, specific model identifiers per tier, and concrete fallback triggers (HTTP 429, timeout > 90s) that are copy-paste ready.

3 / 3

Workflow Clarity

The content is a decision policy/reference organized by topic rather than a sequenced workflow; the fallback logic implies a process but lacks explicit validation checkpoints or a validate→fix→retry feedback loop.

2 / 3

Progressive Disclosure

Self-contained with well-organized sections (Tier Definitions, Fallback Rules, Health Check, Cost Guard), no external or nested references, and clear header navigation — appropriate for a stable reference that needs no split files.

3 / 3

Total

11

/

12

Passed

Description

50%

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 concise and conveys a clear, distinctive policy, but it answers 'what' far better than 'when' and lacks an explicit invocation trigger. Trigger terms are technical and somewhat narrow in coverage.

Suggestions

Add an explicit 'Use when…' clause, e.g. 'Use when handling 429 rate-limit errors, connection timeouts, or choosing between local and cloud models.'

Broaden trigger terms with natural user phrasings like 'rate limited', 'API quota exceeded', and 'switch models' alongside '429' and 'timeout'.

Reframe capabilities as concrete actions (e.g. 'Selects models by provider health, escalates tiers on rate limits and timeouts') rather than policy statements to improve specificity.

DimensionReasoningScore

Specificity

Names the domain ('Model selection by provider health') and concrete behaviors ('Fallbacks activate on 429 or timeout'), but these are framed as policy statements rather than a comprehensive list of concrete capabilities.

2 / 3

Completeness

Clearly states what the skill does ('Model selection by provider health, not task complexity') but provides only an implied 'when' (fallback on 429/timeout) with no explicit 'Use when…' trigger clause, capping completeness at 2.

2 / 3

Trigger Term Quality

Includes relevant technical keywords ('429', 'timeout', 'fallback') a user would say, but misses common natural variations such as 'rate limited', 'API quota', or 'switch models'.

2 / 3

Distinctiveness Conflict Risk

The 'compute ladder / break-glass paid models' niche is distinctive, but without explicit trigger guidance it could still overlap with general model-selection or cost-management skills.

2 / 3

Total

8

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
open-gitagent/opengap
Reviewed

Table of Contents

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.