cicd-setup
When the user needs to set up or improve CI/CD pipelines — GitHub Actions, GitLab CI, deployment automation, or says "set up CI", "automate deployment", "add tests to pipeline", "fix my build".
79
74%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/cicd-setup/SKILL.mdQuality
Discovery
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.
The description excels at trigger term coverage and distinctiveness, providing natural phrases users would say and clearly scoping to CI/CD pipelines. However, it's weaker on specifying concrete capabilities — it tells Claude when to use the skill but doesn't clearly enumerate what specific actions it can perform (e.g., configuring workflows, managing secrets, setting up test stages). The structure is inverted from the ideal pattern of 'what it does' followed by 'when to use it'.
Suggestions
Add explicit capability statements before the trigger clause, e.g., 'Configures CI/CD workflows, sets up build and test stages, manages deployment pipelines, and troubleshoots build failures.'
Restructure to follow the 'what then when' pattern: lead with concrete actions (create workflow files, configure runners, add caching) then follow with 'Use when...' triggers.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (CI/CD pipelines) and mentions some specific platforms (GitHub Actions, GitLab CI) and actions (set up, improve, deployment automation), but doesn't list multiple concrete actions like 'configure build steps, add test stages, set up deployment triggers, manage secrets'. | 2 / 3 |
Completeness | The description answers 'when' very well with explicit trigger phrases, but the 'what does this do' part is weak — it says 'set up or improve CI/CD pipelines' but doesn't clearly enumerate the specific capabilities or actions the skill performs. The 'what' is implied rather than explicitly detailed. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'set up CI', 'automate deployment', 'add tests to pipeline', 'fix my build', plus platform names like 'GitHub Actions' and 'GitLab CI'. These are very natural phrases a user would actually type. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche around CI/CD pipelines with specific platform mentions and distinct trigger phrases. It's unlikely to conflict with other skills unless there's a very similar DevOps skill, as the triggers are well-scoped to CI/CD concerns. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable CI/CD skill with a well-structured workflow, concrete examples, and useful reference tables. Its main weakness is length — it packs substantial reference material inline that could be split into separate files, and includes some guidance that Claude would already know (basic pipeline principles, what lockfiles are). The validation steps and safe deployment progression are particular strengths.
Suggestions
Move the caching strategies table, environment strategy table, and common pitfalls into a separate REFERENCE.md file, keeping only the quick-start workflow and one example inline.
Trim explanations of concepts Claude already knows, such as 'Lockfiles indicate package manager choice' and basic principles like 'fail early before expensive test runs' — these waste tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some content Claude already knows (e.g., explaining what lockfiles indicate, basic pipeline architecture principles like 'lint first'). The caching strategies table and environment strategy table add value, but sections like 'Common Pitfalls' contain fairly obvious guidance. Could be tightened by ~30%. | 2 / 3 |
Actionability | Provides fully executable YAML examples for GitHub Actions, concrete caching paths and keys per ecosystem, specific commands, and clear output format templates. The examples section includes copy-paste ready configurations with proper syntax. | 3 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with a logical progression from detection through validation. Step 6 explicitly includes validation before merge (syntactic validity, command existence, caching alignment, branch protections). The deployment stages in step 5 include a safe rollout pattern with manual approval gates. | 3 / 3 |
Progressive Disclosure | The skill references related skills (code-review, security-review) and mentions startup-context, but the main content is a long monolithic document with extensive inline tables and best practices that could be split into referenced files. The output format template, caching strategies, and examples could each be separate referenced documents. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- shawnpang/startup-founder-skills
- Commit
4ad31b4
- 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.