gh-workflow-monitor

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

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/gh-workflow-monitor/SKILL.md

Quality

Content

57%

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

The content is admirably concise and well-sectioned for a short skill, but it offers no executable gh commands and no validation/feedback loop around the fix step. Actionability is the clear weak point, with workflow clarity also limited by missing checkpoints.

Suggestions

Replace the vague step descriptions with concrete, copy-paste gh commands (e.g. `gh run list --branch <branch>`, `gh run view <run-id> --log-failed`).

Add a validation/feedback loop after 'propose a fix': apply the fix, re-run the workflow, and only report success once the run is green.

Fix the broken 'Use the `gh` for GitHub operations' phrasing to a complete, actionable instruction.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean — a one-line tool pointer plus five short step headers — with no concept explanations or padding, so every token earns its place and it is not the level below where unnecessary explanation lingers.	3 / 3
Actionability	No actual gh commands are given: steps say 'find the GitHub Actions workflow run ... Use the gh cli' and 'Monitor the workflow run for failures' without any executable code or commands, matching 'describes rather than instructs'.	1 / 3
Workflow Clarity	Five steps are sequenced (Step 1–5), but there are no validation checkpoints or feedback loops — 'propose a fix' has no verify/retry cycle and 'not green' is left implicit — fitting 'steps listed but validation gaps'.	2 / 3
Progressive Disclosure	This is a short skill under 50 lines with no bundle files and no need for external references, and it uses well-organized step sections, which the rubric says can score 3.	3 / 3
	Total	9 / 12 Passed

Description

60%

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 states concrete actions and a clear domain but lacks any explicit 'when to use' trigger guidance and natural user vocabulary like 'GitHub Actions' or 'CI'. This leaves it moderately strong on specificity but capped on completeness and trigger quality.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g. 'Use when a GitHub Actions / CI workflow run is failing or the user asks about build status.'

Include common user phrasings such as 'GitHub Actions', 'CI', and 'build failing' alongside 'GitHub workflows'.

Clarify the niche trigger so it is less likely to overlap with general git or code-review skills.

Dimension	Reasoning	Score
Specificity	Lists three concrete actions — 'Monitor GitHub workflows, propose fixes for failures, and report status' — rather than vague abstractions, matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	The 'what' is present (monitor, fix, report) but there is no 'Use when...' or equivalent trigger clause, which the guidelines say caps completeness at 2.	2 / 3
Trigger Term Quality	'GitHub workflows', 'failures', and 'fixes' are relevant, but it omits the natural terms users actually say such as 'GitHub Actions', 'CI', or 'build failing', so it lands at 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The GitHub-workflow niche is somewhat specific, but without explicit triggers it could still overlap with general CI/git skills, matching the 'somewhat specific but could still overlap' anchor.	2 / 3
	Total	9 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: PaloAltoNetworks/shifter
Path: .claude/skills/gh-workflow-monitor/SKILL.md
Commit: 9c0fe10

Reviewed: 3 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.