agentic-workflows

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

Quality

64%

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

63%Weight 40%Scale 1-5

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

The skill is a well-structured, actionable router with a clear dispatch sequence and concrete file mappings. Its main weakness is token efficiency: a long inline file enumeration duplicates the task mapping and crowds the overview.

Suggestions

Remove or collapse the ~68-file inline enumeration; rely on the task→file mapping and have Claude list/read files on demand from github/gh-aw instead.

Add a brief disambiguation rule for overlapping task types (e.g. 'update' vs 'upgrade' vs 'debug') so routing is deterministic without a clarifying question.

Move the full file manifest into a separate references file (e.g. references/available-prompts.md) and link to it from SKILL.md to keep the overview lean.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence, but the ~68-file inline enumeration (lines 18-85) is verbose and largely redundant with the task→file mapping below it, so it could be tightened significantly.	3 / 5
Actionability	Concrete, executable guidance is provided via the task→file mapping ('Create new workflows: .github/aw/create-agentic-workflow.md') and explicit overlay/OTEL handling; minor gaps remain in how to disambiguate overlapping task types.	4 / 5
Workflow Clarity	A clear sequence is given — identify task type, load matching prompt, follow it, with a clarifying-question checkpoint and overlay precedence rule — but there is no validation/feedback loop for ambiguous routing decisions, leaving minor gaps.	4 / 5
Progressive Disclosure	References are one level deep and clearly signaled as loaded from github/gh-aw, but the full 68-file manifest is inlined in SKILL.md rather than split into a separate reference file, which is content that belongs elsewhere.	3 / 5
	Total	14 / 20 Passed

Description

66%Weight 40%Scale 1-5

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 is specific and well-scoped to a clear niche, naming concrete task types and a crisp routing action. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness at 3.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when a user asks to design, create, update, debug, or upgrade GitHub Agentic Workflows.'

Include user-friendly synonyms alongside 'gh-aw' (e.g. 'GitHub Agentic Workflows', 'gh-aw') so the description matches how users actually phrase the request.

Align the task-type list with the body (which adds 'update') so the description's coverage is comprehensive.

Dimension	Reasoning	Score
Specificity	Quotes 'Route gh-aw workflow design/create/debug/upgrade requests to the right prompts' — names the domain and enumerates several concrete task types (design, create, debug, upgrade) plus the routing action, with only minor coverage gaps (e.g. 'update' appears in the body but not the description).	4 / 5
Completeness	It gives a clear 'what' (route requests to the right prompts) but lacks an explicit 'Use when...' clause; the 'when' is only weakly implied via the listed task types, so per the boundary guidance completeness is capped at 3.	3 / 5
Trigger Term Quality	Natural user phrasings like 'design', 'create', 'debug', 'upgrade' workflows are present, but 'gh-aw' is jargon and common synonyms such as 'GitHub Actions' or 'CI workflow' are missing, so it stops short of comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The 'gh-aw workflow' niche is mostly distinct with task-specific triggers, though the jargon term 'gh-aw' and generic word 'workflow' create minor overlap risk with general CI/Actions skills rather than minimal conflict.	4 / 5
	Total	15 / 20 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: dotnet/maui
Path: .github/skills/agentic-workflows/SKILL.md
Commit: 90afade

Reviewed: ~17 hours 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.