AB langchain
Builds and debugs LangChain apps in Python: LCEL chains, agents, tools, retrievers, streaming, and structured output. Use when writing or reviewing a chain, agent, tool, retriever, or prompt template; when a prompt raises KeyError or "missing variables"; when streaming arrives as one blob or astream_events yields nothing; when an agent loops until GraphRecursionError or repeats a tool; when tool calls fail validation or the provider rejects a tool_call_id; when chat history disappears or the context window overflows; when with_structured_output returns None or a parser crashes on valid JSON; when retrieval returns the wrong chunks; when LangSmith traces are empty; when retries, rate limits, or token cost need bounding; or when imports break after an upgrade. Covers LangGraph state, checkpointers, and middleware. Not for framework-agnostic agent architecture (agents), retrieval design (rag), or chunk tuning (rag-chunking).
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, running it twice
How to improve
- 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 · 1
✓ No critical or high findings
Medium and low: 1
✓ Guard found no suspicious behaviour. 1 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 9 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4935 tokens
- 100Steps. 40 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
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
- +3Description length 935: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 40 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.