self-improvement-ci
CI-only self-improvement workflow using gh-aw (GitHub Agentic Workflows). Captures recurring failure patterns and quality signals from pull request checks, emits structured learning candidates, and proposes durable prevention rules without interactive prompts. Use when: you want automated learning capture in CI/headless pipelines.
77
71%
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/self-improvement-ci/SKILL.mdQuality
Discovery
85%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 strong description that clearly articulates specific capabilities and includes an explicit 'Use when' trigger clause. Its main weakness is that the trigger terms lean toward specialized jargon (e.g., 'gh-aw', 'learning candidates') rather than the natural language users might employ when seeking this functionality. The description is concise, uses third person voice correctly, and carves out a distinct niche.
Suggestions
Add more natural trigger terms users might say, such as 'CI/CD', 'continuous integration', 'GitHub Actions', 'build failures', or 'pipeline errors' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'captures recurring failure patterns and quality signals from pull request checks', 'emits structured learning candidates', and 'proposes durable prevention rules without interactive prompts'. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (captures failure patterns, emits learning candidates, proposes prevention rules) and 'when' with an explicit 'Use when:' clause specifying 'automated learning capture in CI/headless pipelines'. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'CI', 'pull request checks', 'headless pipelines', 'gh-aw', and 'GitHub Agentic Workflows'. However, it misses common user variations like 'CI/CD', 'continuous integration', 'GitHub Actions', 'automated checks', 'build failures', or 'pipeline errors' that users would naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: CI-only, non-interactive, self-improvement workflow tied to gh-aw. The combination of 'CI-only', 'headless', 'failure patterns', and 'prevention rules' makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable overview of a CI-based self-improvement workflow with good structure and clear output schema. However, it leans more toward describing a system architecture than providing actionable, executable guidance—the core operational logic (inspecting PRs, deduplicating patterns, emitting candidates) is described conceptually rather than with concrete implementation. The authoring workflow section is the most actionable part but delegates to an external template.
Suggestions
Add concrete implementation examples for the core operations: how to inspect PR check results (e.g., specific gh CLI commands), how to parse and deduplicate learning candidates, and how to emit the output schema.
Include an inline minimal workflow template or at least the key YAML/configuration snippet rather than only referencing an external file, so the skill is self-contained enough to act on.
Add explicit validation/verification steps for the operational workflow (not just the authoring workflow)—e.g., how to verify candidates were correctly ingested and deduplicated before promotion.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary sections like the 'Context Limitation' explanation that could be condensed. The 'CI Contract' section restates constraints that are somewhat obvious from the purpose. Some phrasing could be tightened. | 2 / 3 |
Actionability | Provides some concrete commands (gh extension install, gh aw compile, gh aw run) and a clear output schema, but the core workflow relies on referencing an example template in 'references/workflow-example.md' rather than providing executable content inline. The actual CI behavior (how to inspect PR checks, how to ingest candidates, how to deduplicate) is described abstractly rather than with concrete implementation. | 2 / 3 |
Workflow Clarity | The authoring workflow has a clear 4-step sequence with a validation step (gh aw compile --validate --strict), but the core operational workflow (how the CI skill actually runs, inspects PRs, deduplicates patterns, and emits output) lacks explicit sequencing and validation checkpoints. The promotion rules are clear but the end-to-end execution flow is implicit. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections, appropriate references to external files (references/workflow-example.md), and cross-references to related skills (simplify-and-harden-ci, self-improvement). Content is appropriately split with one-level-deep references and clear navigation signals. | 3 / 3 |
Total | 9 / 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.
- Repository
- pskoett/pskoett-ai-skills
- Commit
d6c68fa
- 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.