CtrlK
BlogDocsLog inGet started
Tessl Logo

ci-cd

CI/CD pipeline expert for GitHub Actions, GitLab CI, Jenkins, and deployment automation

57

Quality

64%

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 ./crates/openfang-skills/bundled/ci-cd/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

A well-organized, mostly lean reference of CI/CD principles, techniques, patterns, and pitfalls with good progressive disclosure for its size. Weaker on actionability (no complete executable pipeline examples) and workflow clarity (risky deployment operations lack explicit validation feedback loops).

Suggestions

Cut the persona-setting intro paragraph; assume Claude's competence and lead directly with the principles.

Add at least one complete, copy-paste-ready example pipeline (e.g. a minimal GitHub Actions YAML) to lift actionability.

For the deployment patterns, add explicit validation/rollback checkpoints (e.g. health-check before traffic switch, automatic rollback on error-rate threshold) to address workflow clarity.

DimensionReasoningScore

Conciseness

The Techniques and Common Patterns sections are reasonably lean, but the opening persona paragraph ('You are a senior DevOps engineer... You have deep expertise...') is padding Claude does not need. Not score 1 because it is not a wall of concept explanation; not score 3 because the role-setting intro could be cut.

2 / 3

Actionability

Provides concrete specifics such as `needs:`, `strategy.matrix`, `hashFiles('**/package-lock.json')`, `stages:`/`rules:`/`extends:`, and `maxUnavailable: 1`, but gives no complete, copy-paste-ready YAML pipeline. Not score 3 because nothing is fully executable end-to-end; not score 1 because it names real syntax keys and examples rather than vague direction.

2 / 3

Workflow Clarity

Content is organized into thematic sections but presents guidance as lists rather than a sequenced pipeline workflow, and the deployment operations described (blue-green, canary, rolling) are risky yet lack validate→fix→retry checkpoints, capping workflow clarity at 2. Not score 1 because the sections are clear; not score 3 because no explicit validation feedback loops exist for these destructive/risky operations.

2 / 3

Progressive Disclosure

Under 50 lines with no external references needed, and content is well-organized into clear sections (Key Principles, Techniques, Common Patterns, Pitfalls to Avoid), satisfying the simple-skill allowance for a top score. Not score 2 because organization is clean and not monolithic.

3 / 3

Total

9

/

12

Passed

Description

72%

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 concise, third-person description that names the domain and key platforms with strong natural trigger terms and low conflict risk. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when setting up or troubleshooting GitHub Actions, GitLab CI, Jenkins pipelines, or deployment automation.'

Reframe from listing platforms toward concrete actions (e.g. 'design, debug, and optimize CI/CD pipelines') to lift specificity.

DimensionReasoningScore

Specificity

Names the domain and concrete platforms ('CI/CD pipeline expert for GitHub Actions, GitLab CI, Jenkins, and deployment automation') but lists tools rather than enumerating specific concrete actions like 'design pipelines' or 'configure caching'. Not score 3 because it does not list multiple specific concrete actions; not score 1 because it names specific platforms rather than vague abstract language.

2 / 3

Completeness

States clearly what the skill covers (CI/CD pipelines for the named platforms), but provides no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 2 per the rubric. Not score 1 because the 'what' is explicit; not score 3 because the 'when' is only implied, not stated.

2 / 3

Trigger Term Quality

Includes natural terms users actually say — 'CI/CD pipeline', 'GitHub Actions', 'GitLab CI', 'Jenkins', 'deployment automation' — giving good coverage of the platform names a user would invoke when needing this skill. Not score 2 because the major natural variations are present rather than just a subset.

3 / 3

Distinctiveness Conflict Risk

The named CI/CD platforms carve a clear, distinct niche unlikely to trigger for unrelated skills. Not score 2 because the specific platform triggers reduce overlap with general dev skills; not below because it is not generic.

3 / 3

Total

10

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
RightNow-AI/openfang
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.