agentic-workflows

Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.

Quality

66%

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 ./.github/skills/agentic-workflows/SKILL.md

Quality

Content

65%

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

An effective dispatcher with concrete, actionable task-to-file routing, but its conciseness and organization suffer from a large redundant flat file dump that interrupts the flow and dilutes workflow clarity and progressive disclosure.

Suggestions

Replace the 50+ item flat file dump with a grouped or summarized catalog (or move it to a reference file) to remove redundancy with the routing table.

Group the routing entries under task-category headings (Design / Create / Update / Debug / Upgrade / Shared) to make the dispatch flow and navigation clearer.

Move the stray "- .github/skills/agentic-workflow-designer/SKILL.md" line (line 68) into the routing table where it is already referenced, to avoid the dangling bullet.

Dimension	Reasoning	Score
Conciseness	The prose is lean, but the 50+ line flat dump of every .github/aw/* path is largely redundant with the task-to-file routing table and could be trimmed or summarized, fitting the score-2 anchor of mostly efficient but could be tightened.	2 / 3
Actionability	The routing table maps each task type to a concrete, specific file path to load (e.g. "Create new workflows: .github/aw/create-agentic-workflow.md"), giving copy-paste-ready actionable guidance appropriate for an instruction-only dispatcher.	3 / 3
Workflow Clarity	The dispatch sequence (identify task → load matching prompt → follow it, with a clarifying-question checkpoint) is stated, but the body's organization is muddled by the giant undifferentiated file list and the stray line 68, leaving the sequence present but checkpoints implicit.	2 / 3
Progressive Disclosure	References are one level deep and the routing table signals them well, but the uncategorized flat dump of 50+ paths is inline catalog content that should be separate/grouped, matching the score-2 anchor of structure present but not well organized.	2 / 3
	Total	9 / 12 Passed

Description

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.

A specific, well-niched dispatcher description that names concrete actions, but it relies on jargon ("gh-aw") and lacks an explicit "Use when..." trigger clause, capping completeness and trigger-term quality at 2.

Suggestions

Expand the domain term to the natural phrase users would say, e.g. "GitHub Agentic Workflows (gh-aw)" instead of only "gh-aw".

Add an explicit trigger clause such as "Use when the user asks to design, create, update, debug, or upgrade a GitHub Agentic Workflow."

Consider adding common trigger synonyms ("agentic workflow", "workflow automation") to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "design/create/debug/upgrade" — matching the score-3 anchor of naming several specific actions rather than vague language.	3 / 3
Completeness	It states what the skill does ("Route ... requests to the right prompts") but the "when" is only implied via the inline task list with no explicit "Use when..." clause, which caps completeness at 2 per the guideline.	2 / 3
Trigger Term Quality	The action verbs (design/create/debug/upgrade) are natural, but the domain term "gh-aw" is technical jargon and the natural full phrase "GitHub Agentic Workflows" is omitted, leaving common variations missing.	2 / 3
Distinctiveness Conflict Risk	"gh-aw workflow design/create/debug/upgrade requests" carves out a clear niche with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 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: Azure/azure-sdk-for-net
Path: .github/skills/agentic-workflows/SKILL.md
Commit: 2f47f87

Reviewed: 2 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.