CtrlK
BlogDocsLog inGet started
Tessl Logo

arn-infra-execute-change

This skill should be used when the user says "execute infra change", "run infra plan", "apply infrastructure change", "execute change", "arn infra execute", "deploy infra plan", "execute infrastructure plan", "run infrastructure change", "apply infra plan", "infra execute", "arn-infra-execute-change", or wants to orchestrate the phased execution of a structured infrastructure change plan, invoking agents for IaC generation, security gates, cost gates, deployment, verification, and review.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-3

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-structured, highly actionable orchestration workflow with explicit checkpoints, confirmation gates, and recovery loops, and it practices good progressive disclosure by offloading detail to real reference files. The only weakness is minor verbosity from a repeated model-dispatch fallback note that could be consolidated.

Suggestions

State the agent model-dispatch convention (model from .arness/agent-models/infra.md with the ensure-config.md fallback) once near Step 2 and reference it from Steps 2.3–2.7 instead of repeating the full parenthetical four times.

Consider moving the per-agent context-block templates into the dispatch-loop.md reference to slim the main body, keeping SKILL.md focused on the phase-level orchestration logic.

DimensionReasoningScore

Conciseness

The body is largely efficient and instructional without explaining concepts Claude already knows, but the parenthetical 'passing the model from .arness/agent-models/infra.md ... (see .../ensure-config.md "Dispatch convention" for fallback)' is repeated verbatim four times and could be stated once as a convention, fitting the 'mostly efficient but could be tightened' anchor.

2 / 3

Actionability

Each agent invocation includes a concrete, copy-paste-ready structured context block with explicit placeholders, named files (PHASE_N_PLAN.md, PROGRESS_TRACKER.json), and precise PROGRESS_TRACKER field updates — fully executable guidance.

3 / 3

Workflow Clarity

A clearly sequenced Step 1–5 flow with a 7-step dispatch loop, explicit validation gates (security, cost, verification, review), mandatory user confirmation before every apply/deploy and every environment promotion, plus a dedicated Error Handling section with fix-and-retry/rollback feedback loops.

3 / 3

Progressive Disclosure

The body is an overview that signals one-level-deep references via blockquotes ('Read .../references/dispatch-loop.md', 'gate-policies.md', 'deploy-procedures.md'), all of which exist as real files in references/, with detailed material appropriately split out rather than inlined.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 strong across all dimensions: it states concrete capabilities, provides a rich set of natural trigger phrases, and explicitly covers both what the skill does and when to use it. It is clearly distinct within the Arness infra skill family.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: 'orchestrate the phased execution of a structured infrastructure change plan, invoking agents for IaC generation, security gates, cost gates, deployment, verification, and review' — matches the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what (orchestrate phased execution invoking named agents/gates) and when (an enumerated 'when the user says...' trigger list plus an 'or wants to...' clause), satisfying the explicit-triggers anchor.

3 / 3

Trigger Term Quality

Extensive natural phrasings a user would actually say ('execute infra change', 'run infra plan', 'apply infrastructure change', 'deploy infra plan') plus the canonical 'arn-infra-execute-change', giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

A clear niche (phased orchestration of a structured plan) with distinctive 'arn infra execute' / 'arn-infra-execute-change' triggers; minor overlap risk with a sibling deploy skill via 'apply/deploy infra plan' is not enough to drop it below the distinct-niche anchor.

3 / 3

Total

12

/

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
AppsVortex/arness
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.