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.

Quality

67%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/self-improvement-ci/SKILL.md

Quality

Content

50%

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 a useful output schema and clear promotion rules. However, it suffers from incomplete actionability — key workflows are described abstractly rather than with executable examples — and missing bundle files that are referenced. The workflow steps lack error recovery feedback loops, which is important for CI automation contexts.

Suggestions

Add concrete, executable examples for the Heal Handoff Intake parsing logic (e.g., how to parse HEALS.md Handoff blocks and map them to candidates), rather than describing the steps abstractly.

Include the referenced 'references/workflow-example.md' template file in the bundle so the authoring workflow section is actionable.

Add explicit error recovery steps to the authoring workflow (e.g., what to do when 'gh aw compile --validate --strict' fails) and to the handoff intake (e.g., handling malformed HEALS.md entries).

Trim the 'Context Limitation' and 'CI Contract' sections — merge the key constraints into a single concise block since several points overlap with the Purpose section.

Dimension	Reasoning	Score
Conciseness	The skill is moderately efficient but includes some sections that could be tightened. The 'Context Limitation' section explains reasoning Claude can infer, and the 'CI Contract' section partially restates what's already covered in 'Purpose'. The output schema and promotion rules are valuable additions, but some prose around them is redundant.	2 / 3
Actionability	The skill provides some concrete commands (gh aw compile, gh aw run) and a clear output schema, but the core workflow lacks executable code. The 'Heal Handoff Intake' section describes steps abstractly rather than providing concrete implementation. The authoring workflow references a template file that isn't provided in the bundle.	2 / 3
Workflow Clarity	The authoring workflow has a clear 4-step sequence with a validation step (gh aw compile --validate --strict), and the Heal Handoff Intake has numbered steps. However, there are no feedback loops for error recovery — what happens if validation fails? What if the heal handoff parsing encounters malformed entries? The promotion workflow lacks explicit verification checkpoints.	2 / 3
Progressive Disclosure	The skill references 'references/workflow-example.md' for templates and mentions other skills for integration, but no bundle files are provided to support these references. The content is reasonably structured with clear sections, but the output schema and promotion rules could potentially be split into reference files. The single reference that exists points to a file not included in the bundle.	2 / 3
	Total	8 / 12 Passed

Description

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 well-structured 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 ('gh-aw', 'structured learning candidates') rather than natural language users would employ when seeking this functionality. The description is distinctive and would not easily be confused with other skills.

Suggestions

Add more natural trigger term variations such as 'CI/CD', 'continuous integration', 'build failures', 'automated pipeline checks', or 'GitHub Actions' to improve discoverability when users describe their needs in common language.

Dimension	Reasoning	Score
Specificity	Lists multiple specific 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 distinct, concrete 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', but misses common user variations like 'CI/CD', 'continuous integration', 'automated checks', 'build failures', or 'pipeline errors'. The term 'gh-aw' is niche jargon that most users wouldn't naturally say.	2 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche: CI-only, non-interactive, self-improvement workflow tied to GitHub Agentic Workflows. The combination of 'CI-only', 'headless', 'gh-aw', and 'failure patterns' makes it very unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: pskoett/pskoett-ai-skills
Commit: 20e64ce

Reviewed: 15 days 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.