CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agentic-workflows

Route gh-aw design, creation, diagnosis, patching, active debugging, and upgrade requests to the right strategies.

55

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

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-structured dispatcher with a clear task-to-file routing table and thoughtful addenda for OTEL and work-queue cases. Its main weaknesses are the redundant, unannotated 80-file listing and the unstated mechanism for loading external files from github/gh-aw.

Suggestions

Drop the flat 80-file listing or replace it with a one-line pointer (e.g., "the full prompt index lives in github/gh-aw/.github/aw/"), since the routing table already names every file needed per task.

State how to load the external files (e.g., a gh CLI or raw.githubusercontent.com URL pattern) so "load from github/gh-aw" is executable.

Fix or explain the inconsistent relative link ../../aw/debug-agentic-workflow.md so it matches the .github/aw/ paths used everywhere else.

DimensionReasoningScore

Conciseness

The body is mostly efficient routing guidance, but the ~80-entry flat file list duplicates the targets already named in the routing section (e.g., designer.md, create-agentic-workflow.md, debug-agentic-workflow.md appear twice), which could be consolidated.

3 / 5

Actionability

Concrete per-task file mappings, precedence rules, and addendum conditions make the router actionable without code, but it never says how to actually load files "from github/gh-aw" given "they are not available locally" (no gh CLI command or URL pattern).

4 / 5

Workflow Clarity

The sequence (identify task type, load matched prompt, apply optional overlay, follow the prompt) is clear with a clarifying-question checkpoint, though "Read only the files you need" immediately followed by an 80-item load list creates minor ambiguity.

4 / 5

Progressive Disclosure

References are one level deep, organized by task type with descriptive signals, but there is no local bundle, the unannotated flat list weakens navigation versus the routing table, and one link uses a confusing path (../../aw/debug-agentic-workflow.md).

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 specific about the domain and request types it handles, but lacks an explicit "Use when..." trigger clause and relies on the insider term "gh-aw" rather than natural user language. It is distinct from other skills but would be more discoverable with spelled-out triggers.

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) in this repository."

Replace or supplement the shorthand "gh-aw" with the full name "GitHub Agentic Workflows" and natural synonyms users would say (e.g., "create a workflow", "fix my workflow").

Make the routing outcome concrete by naming what gets loaded (e.g., "load the matching workflow prompt file and follow it") instead of "the right strategies".

DimensionReasoningScore

Specificity

The description names the domain (gh-aw) and several concrete request types ("design, creation, diagnosis, patching, active debugging, and upgrade"), but the outcome "route to the right strategies" is abstract, leaving minor gaps versus fully comprehensive concrete actions.

4 / 5

Completeness

The "what" is clear (routing requests to strategies), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

"gh-aw" is technical shorthand and natural user phrases like "GitHub Agentic Workflows", "create a workflow", or "fix my workflow" are absent, so relevant keywords exist but common variations and synonyms are missing.

3 / 5

Distinctiveness Conflict Risk

The description is scoped to a niche (gh-aw request routing) with distinct request categories, carrying only minor overlap risk with generic workflow-debugging or code-review skills.

4 / 5

Total

14

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

dotnet/macios

Path

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

Revision

4512b89

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill