CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

github-project-automation

GitHub repository automation (CI/CD, issue templates, Dependabot, CodeQL). Use for project setup, Actions workflows, security scanning, or encountering YAML syntax, workflow configuration, template structure errors.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/github-project-automation/skills/github-project-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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, command-dense skill body with genuinely good progressive-disclosure signaling and a clear, checkpointed setup workflow. Its two significant weaknesses are the missing templates/ directory that breaks the primary copy commands, and substantial structural redundancy (Quick Start vs. 5-Step Process vs. Checklist) that inflates the token budget.

Suggestions

Ship the templates/ directory (workflows, issue-templates, security, pr-templates, misc) that every cp command depends on, or replace the cp-based flow with inline template content — as written, the primary action fails out of the box.

Collapse the three redundant passes over the same setup (Quick Start, 5-Step Complete Setup Process, Complete Setup Checklist) into one canonical walkthrough plus a compact checklist, cutting roughly 40% of the body.

Reference the existing scripts/ bundle files (e.g., validate-workflows.sh for the "Validate YAML before committing" step, setup-github-project.sh as the automated path) from the body so they are discoverable, and move the inline action version pins (checkout@v4.2.2 etc.) into a single maintainable reference instead of the header.

DimensionReasoningScore

Conciseness

The body is mostly dense, actionable content with little explanation of concepts Claude already knows, but the same setup is presented three times (Quick Start, 5-Step Complete Setup Process, Complete Setup Checklist) with identical cp commands repeated, and the "Known Issues Prevention (Top 5)" section duplicates content already in references/common-errors.md. Inline time-sensitive version pins ("actions/checkout@v4.2.2, actions/setup-node@v4.1.0...") and a twice-repeated "Last Updated: 2025-12-17" add staleness-prone tokens; this sits between anchors 2 and 3 — could be tightened substantially, but most sections still earn their tokens.

3 / 5

Actionability

Commands are concrete and copy-paste styled (cp, mkdir, gh secret set, yamllint, ✅/❌ YAML comparisons), but the skill's core mechanic — "cp templates/workflows/ci-react.yml .github/workflows/" — depends on a templates/ directory that does not exist in the bundle, so the primary commands fail immediately. Additionally, four real scripts in scripts/ (e.g., validate-workflows.sh, setup-github-project.sh) are never referenced from the body. This matches anchor 3 (concrete guidance but incomplete, missing key details) rather than anchor 4, where gaps would be minor.

3 / 5

Workflow Clarity

The 5-Step process is clearly sequenced with explicit checkpoints ("Verify structure" tree output, yamllint validation, "Test workflows on feature branch first", a final verification checklist). Not anchor 5 because error-recovery feedback loops are delegated to reference files rather than stated inline, and the flow is split across three overlapping presentations (Quick Start, 5-Step, Checklist), leaving minor ambiguity about which to follow — but the sequence and most checkpoints are solidly anchor 4.

4 / 5

Progressive Disclosure

The bundle has five real reference files, all one level deep, each surfaced through a "When to Load References" section with specific trigger conditions — well-signaled navigation matching anchor 4/5. Kept below 5 because inline content that belongs in references is duplicated in the body (Top 5 issues excerpt from common-errors.md), the scripts/ files are never linked from the body, and the heavily-referenced templates/ files are absent from the bundle.

4 / 5

Total

14

/

20

Passed

Description

70%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 when" clause, good natural trigger terms, and a clear niche. Its main weakness is that the capability statement stays at the level of named tools and areas rather than concrete actions, which keeps specificity and completeness just below the top anchors.

Suggestions

Replace the generic "GitHub repository automation" lead-in with concrete verbs, e.g., "Set up GitHub Actions CI/CD workflows, issue/PR templates, Dependabot, and CodeQL security scanning from pre-validated templates."

Add a few high-frequency natural phrases users actually say to the description text (e.g., "GitHub Actions", "CI pipeline", "repo setup") rather than keeping them only in the keywords list.

Trim the trailing error list ("YAML syntax, workflow configuration, template structure errors") to the two or three most common phrasings so the trigger clause reads naturally.

DimensionReasoningScore

Specificity

"GitHub repository automation (CI/CD, issue templates, Dependabot, CodeQL)" names the domain and enumerates four specific sub-areas, but the only action verb is the generic "automation" — no concrete actions like create, configure, or validate are stated. It falls between anchor 2 (generic action, domain named) and anchor 3 (1-2 concrete actions); the specific tool enumeration gives it slightly more substance than a bare anchor-2 example, but not the concrete actions of anchor 4.

3 / 5

Completeness

Both "what" (repository automation covering CI/CD, issue templates, Dependabot, CodeQL) and "when" (explicit "Use for..." clause with concrete triggers like YAML syntax and workflow configuration errors) are present. Not anchor 5 because the "what" half stays at the level of named areas rather than concrete actions, matching the anchor-4 example where one half could be more specific.

4 / 5

Trigger Term Quality

"Use for project setup, Actions workflows, security scanning, or encountering YAML syntax, workflow configuration, template structure errors" plus "CI/CD", "Dependabot", "CodeQL" gives good coverage of natural terms users would say. Not anchor 5 because a few common variations are missing from the description itself (e.g., "GitHub Actions", "pipeline", "repo setup"), though several appear only in the keywords list.

4 / 5

Distinctiveness Conflict Risk

The GitHub-repository-automation niche with Distinct triggers (Dependabot, CodeQL, workflow YAML syntax, template structure errors) is mostly distinct from other skills. Minor overlap risk remains with closely related skills (generic git skills, cloud-deploy skills), so not anchor 5.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (563 lines); consider splitting into references/ and linking

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

secondsky/claude-skills

Path

plugins/github-project-automation/skills/github-project-automation/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.