CtrlK
BlogDocsLog inGet started
Tessl Logo

agentic-workflows

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

60

Quality

68%

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.

A well-structured dispatcher body with actionable file routing and a clear workflow, weakened mainly by a large undifferentiated file dump that adds tokens without proportional guidance.

Suggestions

Replace the 65-file bulk list with the routed subset only (the "After loading..." mapping), or annotate each bulk-listed file with its trigger task so the index carries guidance.

Make the routing workflow an explicit numbered sequence (1. identify task type → 2. load the file below → 3. follow it → 4. if unclear, ask a clarifying question) to surface the checkpoint.

Note which references are local vs. fetched from github/gh-aw inline in the routing map rather than only in the header, so navigation is unambiguous.

DimensionReasoningScore

Conciseness

The routing instruction and task→file mapping are lean, but the undifferentiated 65-file dump (lines 14-78) lists nearly every available file with no guidance on most of them — padding that could be trimmed to the routed set; sits between 2 and 4, closer to a tightened 3.

3 / 5

Actionability

The "After loading..." mapping gives concrete file paths per task type (e.g. "Create new workflows: .github/aw/create-agentic-workflow.md"), so Claude knows exactly what to load; a few task types in the bulk list lack routing guidance, holding it below 5.

4 / 5

Workflow Clarity

A clear sequence is stated — identify task type, load matching file, follow it directly — with a fallback ("ask a clarifying question if the correct prompt is unclear") acting as a decision checkpoint; this is a non-destructive router so the validation cap does not apply, but there are no explicit checkpoints beyond the fallback.

4 / 5

Progressive Disclosure

The body is an overview pointing one level deep to external workflow-prompt files, with task-labeled references that are easy to navigate; the dual listing (bulk index plus routing map) is a minor organization gap that keeps it at 4 rather than 5.

4 / 5

Total

15

/

20

Passed

Description

70%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.

A crisp, specific dispatcher description with a clear niche and natural trigger verbs, but it lacks an explicit "Use when..." clause, which caps its completeness at the midpoint.

Suggestions

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

Add common synonyms (build, edit, fix) alongside design/create/debug/upgrade to broaden natural-term coverage.

DimensionReasoningScore

Specificity

Names a concrete domain (gh-aw workflows) and several specific request types — "design/create/debug/upgrade" — which are real, distinguishable actions; not comprehensive (e.g. no "update"/"edit") so it sits at 4 rather than 5.

4 / 5

Completeness

The "what" is clear ("Route ... requests to the right prompts"), but there is no explicit "Use when..." trigger clause — per the rubric, weakly-implied "when" caps completeness at 3.

3 / 5

Trigger Term Quality

"design/create/debug/upgrade" are natural verbs users would say, giving good keyword coverage; it leans on the technical "gh-aw" token and omits common synonyms (build, edit, fix), keeping it just below 5.

4 / 5

Distinctiveness Conflict Risk

The niche is tightly scoped to gh-aw workflow lifecycle tasks with distinct triggers, making conflict with unrelated skills unlikely; matches the clear-niche anchor.

5 / 5

Total

16

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
bradygaster/squad
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.