gh-workflow-monitor

Monitor GitHub workflows, propose fixes for failures, and report status

Quality

31%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/gh-workflow-monitor/SKILL.md

Quality

Discovery

32%

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 provides a reasonable but surface-level overview of the skill's capabilities around GitHub workflow monitoring and fixing. It lacks a 'Use when...' clause, which is critical for skill selection, and misses important natural trigger terms like 'GitHub Actions', 'CI/CD', 'pipeline', and 'build failed'. The actions listed are somewhat generic and could benefit from more concrete specifics.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about GitHub Actions failures, CI/CD pipeline issues, or workflow run status.'

Include natural trigger term variations such as 'GitHub Actions', 'CI/CD', 'pipeline', 'build failed', 'workflow run', and '.yml' to improve keyword coverage.

Add more specific concrete actions, e.g., 'parse workflow logs, identify failing steps, suggest YAML fixes, retry failed jobs' to better distinguish this skill.

Dimension	Reasoning	Score
Specificity	Names the domain (GitHub workflows) and lists some actions (monitor, propose fixes, report status), but these are fairly high-level and not deeply specific about concrete capabilities like parsing logs, retrying jobs, or editing workflow YAML files.	2 / 3
Completeness	Describes what the skill does (monitor workflows, propose fixes, report status) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and since the 'what' is also somewhat thin, this scores a 1.	1 / 3
Trigger Term Quality	Includes relevant terms like 'GitHub workflows' and 'failures', but misses common natural variations users might say such as 'CI/CD', 'GitHub Actions', 'pipeline', 'build failed', 'workflow run', or '.yml'.	2 / 3
Distinctiveness Conflict Risk	Mentioning 'GitHub workflows' provides some specificity, but 'monitor', 'propose fixes', and 'report status' are generic enough that this could overlap with general GitHub skills, CI/CD tools, or debugging skills.	2 / 3
	Total	7 / 12 Passed

Implementation

29%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is essentially a high-level outline rather than actionable instructions. It lists steps at an abstract level without providing any concrete gh CLI commands (e.g., `gh run list`, `gh run view`, `gh run watch`), specific examples of failure analysis, or guidance on what 'propose a fix' means. The content fails to leverage Claude's capabilities by not giving it the specific tools and patterns needed to execute the workflow.

Suggestions

Add concrete `gh` CLI commands for each step, e.g., `gh run list --branch $(git branch --show-current)`, `gh run view <run-id> --log-failed`, `gh run watch <run-id>`.

Define what 'propose a fix' means concretely — should Claude read log output, identify error patterns, suggest code changes, or create a PR?

Add a validation/feedback loop: after proposing a fix, specify how to verify the fix (e.g., re-trigger the workflow with `gh workflow run` and monitor again).

Include an example of parsing workflow failure logs and mapping common error patterns to fix strategies.

Dimension	Reasoning	Score
Conciseness	The content is relatively short and doesn't over-explain concepts, but the step descriptions are vague filler rather than substantive instructions. The tokens used don't add much value.	2 / 3
Actionability	The steps are entirely abstract with no concrete commands, code examples, or specific gh CLI invocations. 'Find the GitHub Actions workflow run' and 'propose a fix' are vague directions, not executable guidance.	1 / 3
Workflow Clarity	While steps are numbered, they lack any concrete commands, validation checkpoints, or error recovery loops. 'Monitor the workflow run for failures' and 'propose a fix' are undefined actions with no specifics on how to accomplish them.	1 / 3
Progressive Disclosure	This is a simple, short skill with no need for external references or complex organization. The content is organized into clear sequential sections, which is appropriate for its scope.	3 / 3
	Total	7 / 12 Passed

Validation

90%

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 — 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: PaloAltoNetworks/shifter
Commit: a7c1694

Reviewed: 6 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.