FC qst-memory
Universal Memory Management System v1.8.2 for OpenClaw agents. Provides: 1. Multi-Agent Support (qst, mengtian, lisi, custom) 2. Agent State System ("I'm Doing") - IDLE/DOING/WAITING/PAUSED/COMPLETED/FAILED/BLOCKED 3. Heartbeat Integration - State-driven intelligent checking strategy 4. **NEW v1.8.2**: Loop Protection & User Priority - Auto-detection and handling of stuck tasks 5. Tree-based classification structure (3-level hierarchy) 6. Three search methods: Tree, Semantic, Hybrid 7. Auto-classification with AI inference 8. Appendix Indexing for technical documents 9. Memory encryption (AES-128-CBC + HMAC) for sensitive data 10. Event history tracking with timeline Use when: Agent needs intelligent memory management with state awareness. Goal: Reduce token consumption by 70-90%, improve relevance by 20%, add contextual awareness. **v1.8.2 Anti-Loop Protection**: Prevents infinite task loops with heartbeat throttling, timeout detection, and auto-recovery.
Universal Memory Management System v1.8.2 for OpenClaw agents. Provides: 1. Multi-Agent Support (qst, mengtian, lisi, custom) 2. Agent State System ("I'm…
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, 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 files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
- 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 · 8
-
critical Secrets in code
secret-openai-keydata/qst_memories.md:246OpenAI-style API key- API Key: sk-0…mwH
-
critical Secrets in code
secret-openai-keydata/qst_memories.md:271OpenAI-style API key- API Key: sk-0…mwH
Medium and low: 6
-
medium Secrets in code
secret-labelled-tokendata/qst_memories.md:246Labelled token / key literal (vendor format unknown — verify it is not a live credential)- API Key: sk-0…mwH
-
medium Secrets in code
secret-labelled-tokendata/qst_memories.md:271Labelled token / key literal (vendor format unknown — verify it is not a live credential)- API Key: sk-0…mwH
-
medium Broad scope
meta-agent-memory-dumpSOUL.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensSOUL.md
-
low Secrets in code
secret-high-entropy-tokendata/qst_memories.md:185High-entropy token-like string (may be an id, hash or a credential)[Tech_Config] 【ClawHub 認證資訊】token: clh_…5ZE, registry: https://clawhub.ai。配置檔案：~/.config/clawhub/config.json。狀態：已配置（2026-02-05）。
-
low Dangerous commands
cmd-cron-mentionINTEGRATION.md:27Mentions editing / listing crontabcrontab -e
-
low Dangerous commands
cmd-cron-mentionSKILL.md:393Mentions editing / listing crontabcrontab -e
Files scanned: 50. 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 51/100
- 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
- 100Tools and files. No external tools needed
- 100Steps. 7 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3370 tokens
- low 16 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)
- +3Description length 972: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -216 emoji in the instructions: noise for the model
- -41 reference files, but SKILL.md never points to them: the model will not open them
- -314 of 24 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 46 headings
- +3Step-by-step instructions: 7 items
- +4Has examples (27 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.