CD amygdala-memory
Emotional processing layer for AI agents. Persistent emotional states that influence behavior and responses. Part of the AI Brain series.
Emotional processing layer for AI agents.
As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
The same skill appears in 2 more places: ClawHub, ClawHub
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 45/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 17 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2199 tokens
- 100Progress reporting. Reports progress
- low 14 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -221 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 137: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 17 items
- +4Has examples (14 code blocks)
- +3All 11 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.
In the sandbox The scripts write outside their folder
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Запущено 12 скриптов; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
Из них 6 не дошли до работы, и об их поведении мы ничего не узнали.
install.sh | пишет или удаляет вне своей папки (~/.openclaw/workspace/memory/emotional-state.json, ~/.openclaw/workspace/AMYGDALA_STATE.md) |
scripts/decay-emotion.sh | не запустился: scripts/decay-emotion.sh: line 30: jq: command not found |
scripts/encode-pipeline.sh | завершился с кодом 1 |
scripts/generate-dashboard.sh | не запустился: scripts/generate-dashboard.sh: line 61: jq: command not found |
scripts/get-state.sh | не запустился: scripts/get-state.sh: line 56: jq: command not found |
scripts/load-emotion.sh | не запустился: scripts/load-emotion.sh: line 37: jq: command not found |
scripts/log-event.sh | пишет или удаляет вне своей папки (~/.openclaw/workspace/memory/brain-events.jsonl) |
scripts/preprocess-emotions.sh | завершился с кодом 1 |
scripts/sync-state.sh | пишет или удаляет вне своей папки (~/.openclaw/workspace/AMYGDALA_STATE.md) |
scripts/update-state.sh | ничего за пределами своей папки |
scripts/update-watermark.sh | не запустился: Usage: update-watermark.sh --from-signals OR --to <id> |
scripts/visualize.sh | не запустился: scripts/visualize.sh: line 20: jq: command not found |
23 Oct 2026