agentic-workflows

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

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/agentic-workflows/SKILL.md

The canonical home for this skill is agentic-workflows in github/gh-aw

Quality

Content

67%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 body is a well-structured dispatcher: it gives a clear load-and-follow sequence, concrete file targets per task type, and one-level-deep external references. Its main weaknesses are an undifferentiated 70-path file catalog that inflates token cost and the absence of validation checkpoints or a clear handling path for ambiguous routing.

Suggestions

Group the 70-file catalog by category (syntax, token-optimization, safe-outputs, etc.) or move it to a separate index file to cut inline tokens.

Add an explicit validation/ambiguity step, e.g. 'If the task type is ambiguous, ask one clarifying question before loading a prompt; confirm the prompt loaded before proceeding.'

Tighten the clarifying-question branch into a concrete decision rule so the routing action is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (no concept over-explanation) but inlines an undifferentiated ~70-path file catalog (lines 18-86) that could be trimmed or moved to a reference, matching anchor 3 (mostly efficient but could be tightened) rather than the minor-trim anchor 4.	3 / 5
Actionability	Quotes concrete guidance like 'load it with @.github/aw/instructions.md' and a routing table mapping each task type to a specific file (e.g. 'Design workflows ... via interview: .github/aw/designer.md'), giving mostly executable instruction-only guidance with minor gaps such as the vague 'ask a clarifying question if the correct prompt is unclear'.	4 / 5
Workflow Clarity	Quotes a clear sequence — 'identify the task type, load the matching workflow prompt/skill file, and follow it directly' — with stated overlay precedence, but there are no validation checkpoints and the clarifying-question branch is underspecified, fitting anchor 4 (clear sequence, minor gaps) rather than 5 (explicit validation/feedback loops).	4 / 5
Progressive Disclosure	The body is an overview pointing one level deep to external .github/aw/*.md prompts, well-signaled by the task→file routing table, but the flat 70-file catalog is not grouped by category, so anchor 4 (good structure, minor organization gaps) fits better than 5.	4 / 5
	Total	15 / 20 Passed

Description

53%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 clearly states what the skill does (route gh-aw workflow requests to the right prompts) and carves out a distinct niche, but it omits any 'Use when...' trigger guidance and leans on the jargon term 'gh-aw' rather than natural user language. These gaps cap completeness and trigger-term quality at 3.

Suggestions

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

Replace or expand the jargon 'gh-aw' with the natural phrase 'GitHub Agentic Workflows' so users' wording matches the description.

Surface a couple more concrete actions (e.g. 'configure engines', 'optimize tokens') to lift specificity toward 4-5.

Dimension	Reasoning	Score
Specificity	Quotes 'Route gh-aw workflow design/create/debug/upgrade requests to the right prompts' — it names the domain (gh-aw workflow) and lists several task variants, but the core action vocabulary is a single verb ('route'), so it matches anchor 3 (domain + 1-2 concrete actions) rather than the multi-action anchor 4.	3 / 5
Completeness	Quotes 'Route gh-aw workflow ... requests to the right prompts' — the 'what' is clear (routing to prompts) but there is no 'Use when...' clause or equivalent trigger guidance, so per the rubric's explicit cap it cannot exceed 3; anchor 3 (clear what, when missing) is the best fit.	3 / 5
Trigger Term Quality	Quotes 'gh-aw workflow design/create/debug/upgrade requests' — relevant task verbs are present, but the leading term 'gh-aw' is CLI jargon rather than a natural user phrase, and common synonyms like 'agentic workflows' are absent from the description, matching anchor 3 (some relevant keywords, missing variations).	3 / 5
Distinctiveness Conflict Risk	Quotes 'gh-aw workflow design/create/debug/upgrade' — this is a clear niche with distinct task triggers and low conflict risk, but the bare word 'workflow' could overlap with general CI/CD workflow skills, so anchor 4 (mostly distinct, minor overlap) fits better than 5.	4 / 5
	Total	13 / 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: Azure/azure-sdk-for-net
Path: .github/skills/agentic-workflows/SKILL.md
Commit: 2e6089e

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.