AD self-awareness
Always-on self-awareness framework for OpenClaw agents. Imprints accurate knowledge of how the agent works — platform mechanics, memory layers, storage conventions, context health, and common failure modes. Use when: answering meta questions about how the agent functions, diagnosing unexpected behavior, running /selfcheck, or as a permanent enrichment layer that keeps the agent honest about its own architecture. Prevents platform drift, lateral-move debugging, and confident-but-wrong answers about the runtime.
As a process D 47/100 · 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securityreferences/failure-protocol.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)How to handle things that don't work. The goal is root cause, not lateral movement.
quoted
Files scanned: 6. 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 47/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (self-awareness) differs from the folder (delphi)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 85Steps. 35 steps, 1 vague phrases
- 100Execution cost. Instruction body is 1548 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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 515: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.