CtrlK
BlogDocsLog inGet started
Tessl Logo

aegisops-ai

Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance.

52

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is well-organized and includes concrete setup steps, but the core audit workflows lack executable examples and validation feedback loops, and the single-document structure underuses progressive disclosure.

Suggestions

Provide executable examples or exact command invocations for each audit module rather than only describing them.

Add explicit validation/verification checkpoints (e.g., validate report output before gating a merge) with a fix-and-retry loop for the CI/CD gating workflow.

Move detailed per-module guidance into separate reference files and link to them one level deep instead of inlining all three module descriptions.

DimensionReasoningScore

Conciseness

The body is mostly efficient with useful sections, but is padded with marketing prose ('professional-grade Living Pipeline', 'intelligent gatekeeper') and emoji-laden conceptual framing that could be tightened.

2 / 3

Actionability

Setup commands are concrete and executable, but the core audit workflows (patch_analyzer, cost_auditor, k8s_policy_generator) are only described, not demonstrated with runnable examples, and the 'Over-Privileged Container' pattern gives vague direction.

2 / 3

Workflow Clarity

The multi-step audit/gate pipeline is sequenced at a high level ('python3 main.py') but lacks explicit validation checkpoints or validate-fix-retry feedback loops, which the rubric requires for batch/gating operations.

2 / 3

Progressive Disclosure

No bundle files exist (references/scripts/assets absent), so the three full module descriptions live inline in a single document with no one-level-deep references, yielding some structure but room for better organization.

2 / 3

Total

8

/

12

Passed

Description

67%

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 occupies a distinct niche, but it is missing an explicit when-to-use trigger clause and is padded with marketing buzzwords that dilute natural trigger terms.

Suggestions

Add an explicit 'Use when...' clause naming concrete user triggers (e.g., reviewing Linux kernel diffs, terraform plan cost review, hardening K8s securityContexts).

Drop promotional phrasing like 'Autonomous DevSecOps & FinOps Guardrails' and 'Orchestrates Gemini 3 Flash' in favor of plain third-person action verbs.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across distinct domains — 'audit Linux Kernel patches, Terraform cost drifts, and K8s compliance' — rather than vague abstractions, matching the score-3 anchor for enumerating specific concrete actions.

3 / 3

Completeness

Clearly states what the skill does (audits three targets via Gemini 3 Flash) but lacks any explicit 'Use when...' trigger clause, so per the judging guideline completeness is capped at 2.

2 / 3

Trigger Term Quality

Includes some natural terms a user might say ('Linux Kernel patches', 'Terraform cost drifts', 'K8s compliance') but leans on marketing buzzwords ('Autonomous DevSecOps & FinOps Guardrails', 'Orchestrates Gemini 3 Flash') and misses common variations.

2 / 3

Distinctiveness Conflict Risk

The combined kernel-patch + Terraform-cost + K8s-compliance niche is distinct and unlikely to trigger for unrelated skills, matching the clear-niche score-3 anchor.

3 / 3

Total

10

/

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
sickn33/antigravity-awesome-skills
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.