AD agentic-framework-auditor
Audit agentic framework directories, prompt systems, skills, planner files, workflow guidance, memory-like files, configs, and agent-facing documentation for behavioral failures, prompt bloat, instruction conflicts, over-enforcement, unsafe autonomy, prompt-injection exposure, inefficient tool-use guidance, layer drift, review-integrity risks, and production-readiness issues. Use for Hermes, Codex/OpenAI-style skills, OpenClaw/ClawHub skills, LangGraph, CrewAI, AutoGen, custom agent frameworks, or any project where prompts, configs, skills, workflows, memory, or local instructions shape agent behavior.
Audit agentic framework directories, prompt systems, skills, planner files, workflow guidance, memory-like files, configs, and agent-facing documentation for…
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 0
✓ No critical or high findings
Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 43/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 100Steps. 44 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2151 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +1No license
- +2Single-language instructions
- +3Description length 609: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 44 items
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 11 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.