Tessl • The management layer for AI agent skills

SkillPublic

ci-cd-and-automation

Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%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.

A highly actionable body with complete GitHub Actions configurations, explicit failure feedback loops, staged-rollout validation, and a verification checklist — an agent knows exactly what to do. It runs long, re-explains familiar CI/CD philosophy, and inlines advanced scenario examples that would be better split into reference files for progressive disclosure.

Suggestions

Trim the conceptual coaching Claude already knows — the Shift Left / Faster is Safer paragraphs and the Common Rationalizations table — to reclaim roughly 50 lines of token budget.

Replace the 25-line ASCII gate diagram with a one-line ordered list of gates, since the YAML configs and prose already encode the sequence.

Move the specialized workflow examples (database integration, E2E, rollback, CI optimization) into references/ files linked from SKILL.md so the core file stays a lean overview with one-level-deep references.

Dimension	Reasoning	Score
Conciseness	The body includes unnecessary explanation of concepts Claude already knows ('A bug caught in linting costs minutes; the same bug caught in production costs hours', the Shift Left and Faster is Safer paragraphs, the Common Rationalizations coaching table), and the 25-line ASCII gate diagram duplicates the sequence already encoded in the YAML — more than 'minor' over-explanation, though the bulk is concrete config rather than padding.	3 / 5
Actionability	Provides fully executable, copy-paste-ready guidance covering the common cases: a complete ci.yml workflow, postgres integration job, Playwright E2E job, rollback workflow, dependabot config, and parallel-jobs example, plus specific commands (npx tsc --noEmit, npm audit --audit-level=high); the only gaps (the illustrative featureFlags snippet and the never-configured bundlesize gate) are minor.	5 / 5
Workflow Clarity	Clear gate sequencing with explicit validation checkpoints: the CI-failure feedback loop (fail → paste error to agent → fix → push → re-run), the staged rollout with a 15-minute monitoring window and a rollback branch, and a final Verification checklist; destructive deployment operations have validation, so no cap applies.	5 / 5
Progressive Disclosure	No bundle files exist and everything is inlined in a ~390-line body; well-sectioned and navigable, but ~150 lines of specialized workflow examples (integration, E2E, rollback, CI optimization) are inline content that should live in separate reference files, fitting the anchor-3 pattern of 'content that should be separate is inline'.	3 / 5
	Total	16 / 20 Passed

Description

78%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 strong description that explicitly answers both what the skill does and when to use it, with multiple concrete trigger conditions in the canonical 'Use when...' pattern. Its weaknesses are the second-person 'you need' phrasing (which draws a voice penalty) and the absence of common platform synonyms such as 'GitHub Actions' or 'continuous integration'.

Suggestions

Rewrite the second trigger clause in third person to match the first (e.g., 'Use when automating quality gates, configuring test runners in CI, or establishing deployment strategies') to avoid the second-person voice penalty.

Add natural trigger synonyms users actually say — 'GitHub Actions', 'GitLab CI', 'Jenkins', 'continuous integration' — to broaden keyword coverage toward the top anchor.

Consider mentioning 'debugging CI failures' in the description since it is a listed use case in the body but absent from the description's action coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('automate quality gates, configure test runners in CI, or establish deployment strategies'), which fits the anchor-4 level, but the second-person phrasing 'Use when you need to...' violates the third-person voice requirement and applies the mandated -1 penalty; it is well above anchor 2's 'actions are minimal or generic'.	3 / 5
Completeness	Clearly answers what ('Automates CI/CD pipeline setup') and when via two explicit trigger clauses ('Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates...'), matching the anchor-5 example pattern; the 'when' is already maximally explicit.	5 / 5
Trigger Term Quality	Good natural keyword coverage — 'CI/CD', 'build and deployment pipelines', 'quality gates', 'test runners', 'deployment strategies' — but common user phrases like 'GitHub Actions', 'Jenkins', or 'continuous integration' are missing, so it does not reach anchor 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	The CI/CD pipeline niche is clear with distinct triggers, but 'configure test runners in CI' and 'establish deployment strategies' could overlap with dedicated testing or deployment skills — minor overlap risk per anchor 4, though more focused than anchor 3.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: addyosmani/agent-skills
Path: skills/ci-cd-and-automation/SKILL.md
Revision: 301b02b

Reviewed: 12 days ago

Discovery Implementation Validation

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.

ci-cd-and-automation

Table of Contents

Is this your skill?