Tessl • The package manager for agent skills

aif-ci

Generate CI/CD pipeline (GitHub Actions / GitLab CI) with linting, static analysis, tests, security. Use when user says "ci", "setup ci", "github actions", "gitlab ci", "pipeline".

Quality

85%

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

81%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 well-structured, highly actionable CI generator skill with explicit workflows and validation checklists, leveraging a clean reference-file bundle. Its main weaknesses are a missing templates/ directory that the body repeatedly depends on, and an inconsistent reference-path prefix that complicates navigation.

Suggestions

Provide the referenced templates/ directory (templates/github/*.yml, templates/gitlab/*.yml) or inline minimal base templates so generation does not depend on absent files.

Normalize reference paths — Step 3 uses "skills/ci/references/" and "skills/ci/templates/" while other steps use "references/" — pick one form and apply it consistently.

Tighten Step 4.1, which re-states template usage already covered in Step 3, to reduce length without losing the per-file job-organization guidance.

Dimension	Reasoning	Score
Conciseness	The body is information-dense (detection tables, exact commands, version mappings) and avoids explaining concepts Claude already knows, but at ~500 lines it has minor redundancy and a path inconsistency (Step 3 uses "skills/ci/references/" while other steps use "references/") that could be trimmed.	4 / 5
Actionability	Provides concrete Glob/Grep patterns, per-package-manager install commands, pinned setup actions (e.g. "shivammathur/setup-php@v2", "actions/setup-node@v4"), and inline YAML headers — but the full workflow templates it directs Claude to read ("templates/<platform>/<language>.yml") are not present in the bundle, leaving a gap in copy-paste-ready output.	4 / 5
Workflow Clarity	A clear Step 0–7 sequence with explicit mode branches (Path A/B/C) and a dedicated "Quality Checks (Before Writing)" checklist (Correctness / Best practices / No over-engineering) plus an audit fix-flow gives explicit validation checkpoints and feedback loops for this batch file-writing operation.	5 / 5
Progressive Disclosure	The five reference files are clearly signaled one level deep via "read references/X.md" and SKILL.md stays an overview, but the templates/ directory is referenced ("templates/github/<lang>.yml", "skills/ci/templates/...") yet absent from the bundle, and the path prefix is inconsistent across steps.	4 / 5
	Total	17 / 20 Passed

Description

88%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, concise description that states concrete capabilities and gives explicit user-facing trigger phrases for both supported platforms. It would reach the top anchor on trigger quality and distinctiveness by adding synonyms like "continuous integration"/"CI/CD" and trimming reliance on the generic word "pipeline".

Suggestions

Add synonyms and file/extension triggers (e.g. "continuous integration", "CI/CD", ".github/workflows", ".gitlab-ci.yml") to broaden natural-term coverage.

Qualify the generic trigger "pipeline" (e.g. "ci pipeline", "ci/cd pipeline") to reduce overlap with build/deployment skills.

Consider noting the three modes (generate/enhance/audit) briefly in the description so users with existing CI know the skill applies to them.

Dimension	Reasoning	Score
Specificity	"Generate CI/CD pipeline (GitHub Actions / GitLab CI) with linting, static analysis, tests, security" lists multiple concrete generation actions across two named platforms with four named concern categories — comprehensive coverage rather than just 1-2 actions.	5 / 5
Completeness	It explicitly answers both 'what' (generate CI/CD pipeline with linting/SA/tests/security) and 'when' (concrete "Use when user says..." trigger phrases), matching the anchor for clearly answering both with concrete triggers.	5 / 5
Trigger Term Quality	"Use when user says 'ci', 'setup ci', 'github actions', 'gitlab ci', 'pipeline'" provides good natural trigger phrases, but lacks common synonyms (e.g. "continuous integration", "CI/CD") and file-extension triggers that would push it to comprehensive.	4 / 5
Distinctiveness Conflict Risk	"CI/CD pipeline (GitHub Actions / GitLab CI)" with platform-specific triggers carves a clear niche, but the generic term "pipeline" carries minor overlap risk with adjacent build/deployment skills, keeping it just below the minimal-conflict anchor.	4 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (507 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: lee-to/ai-factory
Path: skills/aif-ci/SKILL.md
Commit: e144f95

Reviewed: 5 days ago

Table of Contents

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.