Tessl • The package manager for agent skills

pipeline-blueprint

Provide CI/CD best practices and pipeline templates for GitHub Actions and GitLab CI, recommending configurations based on project type (frontend, backend, fullstack, library, monorepo, mobile). Trigger when users ask about setting up CI/CD, automating builds, improving pipelines, or mention keywords like GitHub Actions, GitLab CI, pipeline templates, or deployment automation.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%

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

The body is highly actionable with concrete, copy-paste CI/CD templates and a clear decision guide, but it is monolithic (644 inline lines, no progressive disclosure to bundle files) and somewhat verbose via restated best-practice concepts and repetitive template steps. It is solid but leaves room on conciseness and file structure.

Suggestions

Trim or remove the 'General Best Practices' section, which restates widely-known CI/CD principles Claude already knows, and keep only non-obvious guidance to improve conciseness.

Extract the per-project-type YAML templates into one-level-deep reference files (e.g. references/frontend-github-actions.yml, references/backend-gitlab.yml) and have SKILL.md point to them, turning the monolithic body into a navigable overview.

Consolidate the repeated checkout/setup/install/lint/test/build steps — for example via the already-shown reusable workflow pattern — so individual templates reference shared logic instead of duplicating it six times.

Dimension	Reasoning	Score
Conciseness	The 'General Best Practices' section restates concepts Claude already knows ('Fail fast', 'Cache aggressively', 'Pin versions', 'Least privilege'), and the YAML templates repeat the same checkout/setup/install/lint/test/build steps across six project types; it is mostly efficient but carries unnecessary explanation and repetition, so it stops short of the lean anchor at 3.	2 / 3
Actionability	Provides extensive copy-paste-ready GitHub Actions and GitLab CI YAML with pinned versions, service containers, matrix builds, and caching; the few placeholder steps ('echo "Add your deployment command here"') are explicitly justified since no universal deploy/E2E command exists, fitting the fully-executable anchor.	3 / 3
Workflow Clarity	'How to Use' gives a clear identify-recommend-adapt sequence and the 'Decision Guide' table provides unambiguous routing from project shape to template; as a non-destructive recommendation skill it needs no validation checkpoints, so the simple-skill carve-out applies.	3 / 3
Progressive Disclosure	All 644 lines live inline in SKILL.md with no bundle files (references/scripts/assets absent); sections are well-organized with clear headings so it is not a disorganized monolith, but the per-project-type templates are content that could plausibly be split into one-level-deep reference files, fitting the 'content that should be separate is inline' anchor at 2.	2 / 3
	Total	10 / 12 Passed

Description

100%

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, trigger-rich, and clearly answers both what the skill does and when to use it, with a well-scoped CI/CD niche that avoids conflict with other skills. It is a strong, concise description with no significant weaknesses.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Provide CI/CD best practices and pipeline templates', 'recommending configurations based on project type' — and enumerates six project types, matching the multi-action anchor rather than the partial 'names domain and some actions' anchor.	3 / 3
Completeness	Explicitly answers both what ('Provide CI/CD best practices and pipeline templates... recommending configurations based on project type') and when ('Trigger when users ask about setting up CI/CD, automating builds...'), matching the both-what-and-when anchor rather than the implied-when anchor at 2.	3 / 3
Trigger Term Quality	Covers natural user phrasing — 'setting up CI/CD', 'automating builds', 'improving pipelines', 'GitHub Actions', 'GitLab CI', 'pipeline templates', 'deployment automation' — giving broad coverage of terms a user would actually say, not just technical jargon.	3 / 3
Distinctiveness Conflict Risk	Has a clear niche — CI/CD pipeline templates for GitHub Actions and GitLab CI — with distinct, specific triggers unlikely to fire for unrelated skills; uses third-person voice so no specificity penalty applies.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (652 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: zebbern/claude-code-guide
Path: skills/pipeline-blueprint/SKILL.md
Commit: af7d491

Reviewed: about 9 hours 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.