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.

Quality

77%

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-designed dispatcher body with concrete routing, an executable download fallback, and genuine progressive disclosure — all detail lives in external one-level-deep files. Its main cost is the 83-line flat file catalog that inflates token usage while adding little beyond the routing map.

Suggestions

Move the 83-path file catalog out of SKILL.md into a separate index file (or group it by task category with one-line descriptions), keeping only the routing map inline to cut roughly two-thirds of the body's tokens.

Specify the primary fetch mechanism for github/gh-aw files (e.g., the exact gh api or MCP command) the same way the 403 curl fallback is specified, so the normal path is as executable as the fallback.

Add a brief post-load checkpoint, e.g. 'confirm the loaded prompt covers the requested task before proceeding', to close the workflow's feedback loop.

DimensionReasoningScore

Conciseness

The flat catalog of 83 file paths occupies roughly two-thirds of the body and duplicates many file names already given in the routing map, so the body could be tightened considerably even though the surrounding instructions are lean with no concept over-explanation.

3 / 5

Actionability

Provides exact task-to-file routing, a fully executable curl fallback command, and explicit conditional rules (e.g., "If the public download fails, report that error rather than proceeding"), but never concretely specifies the primary mechanism for loading files from github/gh-aw outside the 403 fallback.

4 / 5

Workflow Clarity

The dispatch sequence is clear ("identify the task type, load the matching workflow prompt/skill file, and follow it directly") with error-handling branches for HTTP 403 and failed downloads plus a clarifying-question loop, though there is no checkpoint confirming the loaded prompt actually matched the task.

4 / 5

Progressive Disclosure

As a pure router it keeps all detail in one-level-deep external files with a clear task-to-file map, but the ungrouped, unannotated 83-file catalog is a minor organization and navigation gap.

4 / 5

Total

15

/

20

Passed

Description

75%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 concise, third-person router description that clearly scopes the domain (gh-aw) and enumerates the task types it handles. Its main weaknesses are the missing "agentic workflow"/"GitHub" synonyms and a "when" clause that is implied by the enumerated request types rather than stated explicitly.

DimensionReasoningScore

Specificity

Names six concrete task types ("design, creation, diagnosis, patching, active debugging, and upgrade") matching the several-specific-actions anchor, but the only stated action is "Route ... to the right strategies" with no concrete outcome, so it falls short of comprehensive.

4 / 5

Completeness

The "what" (route requests to the right strategies) and "when" (explicitly enumerated request types) are both present, satisfying equivalent trigger guidance, but the "when" is embedded in the noun phrase rather than stated as a clear trigger clause.

4 / 5

Trigger Term Quality

Includes natural verbs users would say (design, create, debug, upgrade) plus the product name "gh-aw", giving good keyword coverage; misses common synonyms like "workflow(s)", "agentic workflows", or "GitHub".

4 / 5

Distinctiveness Conflict Risk

"gh-aw" carves out a clear niche with distinct triggers and minimal conflict risk, though broad verbs like "diagnosis" and "design" leave minor overlap risk with general debugging or design skills.

4 / 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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

FlemmingMertz/agentic-starter

Path

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

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.