CtrlK
BlogDocsLog inGet started
Tessl Logo

agentic-workflows

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

56

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

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-designed router: a clear task-to-file mapping, an optional repository overlay with explicit precedence, and one-level-deep external references. Its main weaknesses are a 68-entry flat file catalog that duplicates the routing map and an unspecified mechanism for loading files from the external github/gh-aw repository, plus the absence of any validation step confirming the routed file was the right one.

Suggestions

Replace the 68-file flat catalog with the categorized routing map itself (or group the catalog by purpose), eliminating the duplication between the catalog and the routing list.

Specify how to load files from the external github/gh-aw repository (e.g. the exact fetch command or URL pattern), since the paths alone are not locally resolvable.

Add a brief validation step after loading a prompt — e.g. confirm the loaded file matches the identified task type before following it — to close the workflow's feedback loop.

DimensionReasoningScore

Conciseness

The instruction "Read only the files you need:" is followed by a flat catalog of 68 file paths, 14 of which are then repeated in the routing map — a duplication that could be merged, and a catalog that contradicts the read-only-what-you-need guidance. The rest of the body is lean with no concept over-explanation, so this fits "mostly efficient but could be tightened" rather than the noticeably verbose anchor.

3 / 5

Actionability

The routing map gives concrete task-to-file guidance (e.g. "Debug, audit, or investigate workflows: .github/aw/debug-agentic-workflow.md") plus an explicit overlay mechanism (@.github/aw/instructions.md). It is mostly executable, but how to actually load files "from github/gh-aw" (they are not local) is never specified — a minor gap that keeps it below the fully executable anchor.

4 / 5

Workflow Clarity

The dispatcher sequence is clear — identify task type, load the matching prompt, follow it, with an optional overlay and precedence rule — and includes an explicit checkpoint ("ask a clarifying question if the correct prompt is unclear"). No verification that the loaded file matches or exists keeps it at the anchor for most checkpoints present rather than the explicit-validation anchor.

4 / 5

Progressive Disclosure

All references are one level deep and clearly signaled, and the body is appropriately split between router logic and external detail files (no local bundle files exist to check). The 68-file catalog is an ungrouped flat list with no categorization, a minor organization gap that fits the good-structure anchor rather than the clear-and-easy-navigation one.

4 / 5

Total

15

/

20

Passed

Description

58%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 concise and names a specific domain with several concrete task types, but it lacks an explicit "Use when..." trigger clause and relies on the technical abbreviation "gh-aw" rather than natural user phrasing like "GitHub Agentic Workflows". It is distinguishable from most skills but not comprehensive about the tasks the skill actually routes.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to design, create, update, debug, or upgrade GitHub Agentic Workflows (gh-aw)."

Include natural synonyms alongside the abbreviation — "GitHub Agentic Workflows", "gh-aw", "edit", "fix" — so the description matches how users actually phrase requests.

Mention the additional task types the router handles (update, configure engines, optimize tokens, shared components) for full coverage.

DimensionReasoningScore

Specificity

"Route gh-aw workflow design/create/debug/upgrade requests to the right prompts" names the domain and four concrete task types, matching the anchor for several specific actions with minor gaps; it is not comprehensive since the body also covers update, configure, optimize, and shared-component tasks.

4 / 5

Completeness

The "what" is clear (routes requests to the right prompts) but there is no "Use when..." clause or equivalent explicit trigger guidance — the "when" is only weakly implied by the listed request types, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Relevant keywords exist (workflow, design, create, debug, upgrade) but "gh-aw" is a technical abbreviation and natural variations users would say — "GitHub Agentic Workflows", "edit", "update", "fix" — are missing, matching the anchor for some relevant keywords but missing common synonyms.

3 / 5

Distinctiveness Conflict Risk

The "gh-aw workflow" niche is fairly distinct with task-specific triggers, but the bare word "workflow" leaves minor overlap risk with generic GitHub Actions/CI workflow skills, fitting the mostly-distinct anchor rather than the minimal-conflict one.

4 / 5

Total

14

/

20

Passed

Validation

100%

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
Reviewed

Table of Contents

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.