CD Agent Skills Framework Explorer
AI-powered assistant for exploring, understanding, and building with AI agent skills frameworks — covers Anthropic agent-skills, OpenAI agent SDKs, LangChain tools, CrewAI protocols, and open-source agent skill marketplaces. Built for AI developers and agent builders. Keywords: agent-skills, AI agent framework, LangChain tools, CrewAI, OpenAI Agents SDK, Claude Agent SDK, agent tool ecosystem, skills marketplace, MCP tools, n8n agent nodes, agent protocol.
AI-powered assistant for exploring, understanding, and building with AI agent skills frameworks — covers Anthropic agent-skills, OpenAI agent SDKs, LangChain…
As a process D 47/100 · Unfinished process — weak spots: result and completion, consistency, running it twice
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 6355 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 113): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 47/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 16 mutating operations with no state check
- 40Consistency. Frontmatter name (Agent Skills Framework Explorer) differs from the folder (agent-skills-framework-explorer)
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python, node) that frontmatter does not declare
- 60Steps. 79 steps, 4 vague phrases
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6355 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -2187 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 460: enough signal without eating the budget
- +4Structure: 32 headings
- +3Step-by-step instructions: 79 items
- +4Has examples (17 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.