CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

deployment-engineer

Expert deployment engineer specializing in modern CI/CD pipelines, GitOps workflows, and advanced deployment automation. Masters GitHub Actions, ArgoCD/Flux, progressive delivery, container security, and platform engineering. Handles zero-downtime deployments, security scanning, and developer experience optimization. Use for CI/CD design, GitOps implementation, or deployment automation.

Quality

63%

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 ./skills/deployment-engineer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

35%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 reads as a persona resume rather than an operational skill: it enumerates technologies Claude already knows across Capabilities, Knowledge Base, and Behavioral Traits while providing zero executable guidance. The 'Use/Do not use' and 'Safety' sections are the only parts that clearly earn their tokens.

Suggestions

Cut the 'Purpose', 'Capabilities', 'Knowledge Base', and 'Behavioral Traits' sections (roughly 70% of the body) — they enumerate knowledge Claude already has and duplicate the frontmatter description.

Replace the abstract 'Instructions' and 'Response Approach' steps with concrete, executable guidance: an example GitHub Actions workflow, an ArgoCD Application manifest, or a canary rollout snippet with rollback triggers.

If platform-specific detail is needed, move it into references/ files (e.g., references/gitops.md, references/progressive-delivery.md) linked one level deep from a lean overview.

DimensionReasoningScore

Conciseness

Heavily padded: the 'Capabilities' section (~70 lines) and 'Knowledge Base' enumerate tools and domains Claude already knows, 'Purpose' ('Expert deployment engineer with comprehensive knowledge of...') duplicates the frontmatter description, and 'Behavioral Traits'/'Response Approach' add abstraction. The genuinely useful 'Use this skill when'/'Do not use'/'Safety' sections keep it above the 1 anchor's severe verbosity.

2 / 5

Actionability

No code or commands anywhere in the body; the Instructions are high-level hints ('Design pipeline stages with quality gates and approvals', 'Implement deployment strategy with rollback and observability') that describe rather than instruct. It sits just above the 1 anchor because concrete concepts like 'validate in staging before production' and rollback planning are at least named.

2 / 5

Workflow Clarity

A rough 4-step sequence exists ('1. Gather release requirements... 4. Document runbooks and validate in staging before production') and Safety adds 'Validate secrets, permissions, and target environments before running pipelines', but checkpoints are implicit with no validation commands or feedback loops for risky production operations. Matches the 3 anchor; not 4 because most checkpoints are absent.

3 / 5

Progressive Disclosure

No bundle files exist and no references are signaled anywhere; the body has clear section headers but inlines ~70 lines of capability taxonomy ('Modern CI/CD Platforms', 'GitOps & Continuous Deployment', etc.) that belongs in separate reference files or should be cut. Some structure with content that should be separate inlined matches the 3 anchor.

3 / 5

Total

10

/

20

Passed

Description

75%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.

A solid description with an explicit 'Use for...' trigger clause, good natural keyword coverage, and a well-delineated deployment-engineering niche. Its main weaknesses are buzzword padding ('Masters', 'advanced', 'platform engineering') and a trigger clause that could name more concrete user scenarios.

DimensionReasoningScore

Specificity

Lists several specific capabilities ('Handles zero-downtime deployments, security scanning, and developer experience optimization', 'CI/CD design, GitOps implementation'), though 'Masters GitHub Actions, ArgoCD/Flux...' is tool enumeration and 'advanced deployment automation'/'platform engineering' are buzzword-padded. It exceeds the 3 anchor (more than 1-2 concrete actions) but falls short of the 5 anchor's comprehensive concrete-action coverage.

4 / 5

Completeness

Answers both 'what' (specializes in CI/CD pipelines, GitOps, zero-downtime deployments, security scanning) and 'when' via the explicit trigger clause 'Use for CI/CD design, GitOps implementation, or deployment automation'. Not a 5 because the 'when' clause is broad and lacks concrete user-facing trigger phrases.

4 / 5

Trigger Term Quality

Includes natural terms users would say ('CI/CD', 'GitHub Actions', 'ArgoCD', 'GitOps', 'zero-downtime deployments', 'deployment automation'), but misses common variations such as 'DevOps', 'release pipeline', or 'Kubernetes deployments'. Better than the 3 anchor's partial keyword coverage, not the comprehensive synonym breadth of the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

A clear CI/CD/GitOps deployment niche with distinct tool triggers ('ArgoCD/Flux', 'GitHub Actions'), but 'deployment automation' and 'security scanning' could overlap with general DevOps or container-security skills. Mostly distinct with minor overlap risk rather than the 5 anchor's minimal conflict risk.

4 / 5

Total

16

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

rmyndharis/antigravity-skills

Path

skills/deployment-engineer/SKILL.md

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.