CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-agent-development

AI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents.

77

0.97x
Quality

66%

Does it follow best practices?

Impact

97%

0.97x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/ai-agent-development/SKILL.md

The canonical home for this skill is ai-agent-development in sickn33/agentic-awesome-skills

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 content is a well-structured, concise workflow scaffold with clear phase sequencing and a quality-gate checklist. Its main weakness is actionability: the per-phase steps are abstract descriptions rather than concrete, executable guidance.

Suggestions

Replace abstract action items ("Implement agent logic", "Configure memory") with concrete, copy-paste-ready commands or minimal code snippets per phase.

Add explicit validation/checkpoint steps between phases (e.g., verify agent responds before moving to multi-agent) to strengthen workflow clarity.

Either confirm the referenced `@skill` names resolve to real bundle files, or note they are external skill invocations, to remove ambiguity in progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly lean lists and section headers with no padding explaining concepts Claude already knows; the repeated 7-phase scaffolding (Skills/Actions/Prompts per phase) is slightly repetitive and could be trimmed, but it stays efficient.

4 / 5

Actionability

Copy-paste prompts ("Use @crewai to build multi-agent system with roles") give some concrete guidance, but the per-phase action lists ("Define agent purpose", "Implement agent logic") are high-level descriptions rather than executable code or specific commands.

3 / 5

Workflow Clarity

Seven phases are clearly sequenced with numbered actions and a closing Quality Gates checklist; because the workflow is non-destructive the validation cap does not apply, though per-phase checkpoints/feedback loops are only implied rather than explicit.

4 / 5

Progressive Disclosure

The skill is well-organized into Overview, When-to-Use, seven phase sections, architecture, and gates; no bundle files exist and none are clearly required, so the single-file structure is appropriate with only minor organization gaps.

4 / 5

Total

15

/

20

Passed

Description

66%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 conveys a clear, framework-specific niche with good trigger terms, but it omits any explicit "Use when" trigger guidance, leaving the when-to-use question only weakly implied. Adding a trigger clause would lift completeness materially.

Suggestions

Append a "Use when..." clause naming concrete triggers (e.g., building autonomous agents, multi-agent systems, or agent orchestration with CrewAI/LangGraph).

Replace category-level verbs ("building", "orchestration") with more concrete actions to push specificity toward 5.

Add natural synonyms or phrasings users might say ("agent framework", "LLM agents", "agentic workflows") to broaden trigger term coverage.

DimensionReasoningScore

Specificity

Lists several specific targets ("autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents") with named frameworks, but the verbs ("building", "orchestration") are category-level rather than truly concrete operations, leaving minor coverage gaps.

4 / 5

Completeness

Clearly states what the workflow does but provides no "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural developer terms ("AI agent", "autonomous agents", "multi-agent", "CrewAI", "LangGraph") giving good keyword coverage, but misses common synonyms and variation phrasings that would round out coverage.

4 / 5

Distinctiveness Conflict Risk

Naming specific frameworks (CrewAI, LangGraph) carves out a mostly distinct niche with only minor overlap risk against closely related AI/agent skills.

4 / 5

Total

15

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.