fetch-ci-build
Fetch CI build results and diagnose failures. Auto-detects provider from project files or URLs. Supports GitHub Actions, Buildkite, and CircleCI.
Install with Tessl CLI
npx tessl i github:Dicklesworthstone/pi_agent_rust --skill fetch-ci-build75
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description with strong specificity and clear domain focus on CI build diagnostics. The main weaknesses are the lack of an explicit 'Use when...' clause and missing natural trigger phrases users might say when experiencing CI failures. Adding explicit trigger guidance would improve Claude's ability to select this skill appropriately.
Suggestions
Add a 'Use when...' clause with trigger scenarios like 'Use when the user mentions CI failures, broken builds, pipeline errors, or asks about GitHub Actions/Buildkite/CircleCI status'
Include more natural user phrases like 'build broken', 'pipeline failed', 'workflow error', 'CI red', 'tests failing in CI'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Fetch CI build results', 'diagnose failures', 'Auto-detects provider'. Also specifies supported platforms (GitHub Actions, Buildkite, CircleCI). | 3 / 3 |
Completeness | Clearly answers 'what' (fetch results, diagnose failures, auto-detect provider) but lacks explicit 'Use when...' clause. The 'when' is only implied through the capabilities listed. | 2 / 3 |
Trigger Term Quality | Includes good technical terms like 'CI', 'build results', 'GitHub Actions', 'Buildkite', 'CircleCI', but missing common user phrases like 'pipeline failed', 'build broken', 'CI failing', 'workflow error'. | 2 / 3 |
Distinctiveness Conflict Risk | Very clear niche focused on CI/CD build diagnostics with specific provider names. Unlikely to conflict with other skills due to the specific domain (CI builds) and named platforms. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has strong workflow clarity and good progressive disclosure with appropriate use of reference files. However, it lacks concrete executable examples for the core functionality (fetching builds, parsing failures) and includes a DOT graph that adds tokens without practical value since Claude cannot render it. The actionability suffers from deferring too much to reference files without providing inline examples.
Suggestions
Add at least one concrete executable example showing how to fetch and parse a build failure (e.g., a `gh` CLI command with output parsing)
Remove or replace the DOT graph with a simple numbered list or markdown flowchart - the graph syntax wastes tokens and cannot be rendered
Include a brief inline example from one provider reference showing the actual command pattern, rather than only linking to reference files
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some unnecessary elements like the DOT graph visualization (which Claude can't render) and verbose table formatting. The step-by-step process section partially duplicates the workflow diagram. | 2 / 3 |
Actionability | Provides some concrete guidance (bash detection commands) but lacks executable code for the actual fetching and parsing of CI results. Steps like 'Use the provider-specific commands' are vague - the actual commands are deferred to reference files without examples here. | 2 / 3 |
Workflow Clarity | Clear multi-step workflow with explicit decision points (check for failures, ask user, complex failure check). The process includes validation checkpoints and user confirmation before applying fixes, with appropriate branching for complex cases. | 3 / 3 |
Progressive Disclosure | Well-structured with clear overview, provider-specific details appropriately delegated to reference files (one level deep), and logical section organization. References are clearly signaled with relative paths. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.