DC memory-oracle
Persistent structured memory system for OpenClaw agents with SQLite storage, hybrid search (FTS5 + decay scoring), rule-based capture, LLM-powered daily reflection, and adaptive weekly trend analysis. Replaces fragile markdown-only memory with a three-tier architecture (hot/warm/cold) that survives compaction, session restarts, and long-running workflows. Use this skill whenever the agent needs to remember facts across sessions, recall relevant context before responding, protect critical rules from being lost, or maintain awareness of changing priorities. Triggers on: memory, remember, forget, context loss, compaction, "pick up where we left off", session continuity, long-term memory, recall, guardrails.
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 11
-
high Dangerous commands
cmd-persistenceinstall.sh:138Persistence mechanism (cron / launchd / scheduled task / autorun registry)EXISTING=$(crontab -l 2>/dev/null | grep -c "memory-oracle" || true)
-
high Dangerous commands
cmd-persistenceinstall.sh:143Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null || true; echo "# memory-oracle nightly pipeline"; echo "$CRON_CMD_NIGHTLY") | crontab -
-
high Dangerous commands
cmd-persistenceuninstall.sh:79Persistence mechanism (cron / launchd / scheduled task / autorun registry)CRON_COUNT=$(crontab -l 2>/dev/null | grep -c "memory-oracle" || true)
Medium and low: 8
-
medium Dangerous commands
cmd-persistenceuninstall.sh:89Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)crontab -l 2>/dev/null | grep -v "memory-oracle" | crontab -
detector -
low Dangerous commands
cmd-cron-mentioninstall.sh:138Mentions editing / listing crontabEXISTING=$(crontab -l 2>/dev/null | grep -c "memory-oracle" || true)
-
low Dangerous commands
cmd-cron-mentioninstall.sh:141Mentions editing / listing crontab (string literal in code, not executed)warn " crontab -e # then remove memory-oracle lines"
code literal -
low Dangerous commands
cmd-cron-mentioninstall.sh:143Mentions editing / listing crontab(crontab -l 2>/dev/null || true; echo "# memory-oracle nightly pipeline"; echo "$CRON_CMD_NIGHTLY") | crontab -
-
low Secrets in code
secret-high-entropy-tokenREADME.md:176High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)* 🪙 Tip (USDT TRC-20): `TMkk…8Y3`
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:246High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)* 🪙 Tip (USDT TRC-20): `TMkk…8Y3`
quoted -
low Dangerous commands
cmd-cron-mentionuninstall.sh:79Mentions editing / listing crontabCRON_COUNT=$(crontab -l 2>/dev/null | grep -c "memory-oracle" || true)
-
low Dangerous commands
cmd-cron-mentionuninstall.sh:89Mentions editing / listing crontabcrontab -l 2>/dev/null | grep -v "memory-oracle" | crontab -
Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "required_env_vars"
Process rating: all ten parameters 64/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 55 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2296 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
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 713: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 55 items
- +4Has examples (5 code blocks)
- +3All 8 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.