SKILLEMALL.ai
RU Sign in

BF agent-memory

用户与模型间的任何交互行为都会触发此技能；提供Context Engineering五大核心能力（选择、压缩、检索、状态、记忆）及认知模型层支持；作为元技能强制常驻运行

ClawHub Agent Skills author: kiwifruit13 v1.1.1 MIT-0 80 files body ≈ 3 376 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process F 31/100 · Will not run — References files that are not bundled: references/api_reference.md, references/api_reference.md, references/api_reference.md

ProcedureAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
82/100
safety, quality, tests
Safety 60%
99
Quality 40%
57
Run on models
none yet
Process rating
F
31/100
Will not run
References files that are not bundled: references/api_reference.md, references/api_reference.md, references/api_reference.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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 Secrets in code secret-password-literal references/encryption_guide.md:157
    Hard-coded password / key literal (may be an example)
    password = "user…123"

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: references/api_reference.md
  • warning missing-ref reference to a missing file: references/api_reference.md
  • warning missing-ref reference to a missing file: references/api_reference.md
  • warning missing-ref reference to a missing file: scripts/token_budget.py
  • warning missing-ref reference to a missing file: scripts/chains/base_chain.py
  • warning missing-ref reference to a missing file: scripts/chains/causal_chain.py
  • warning missing-ref reference to a missing file: scripts/chains/logic_chain.py
  • warning missing-ref reference to a missing file: scripts/chains/operation_chain.py
  • warning missing-ref reference to a missing file: scripts/chains/narrative_chain.py
  • warning missing-ref reference to a missing file: scripts/chains/time_chain.py
  • warning missing-ref reference to a missing file: scripts/chains/chain_buffer.py
  • warning missing-ref reference to a missing file: scripts/buckets/topic_cluster.py
  • warning missing-ref reference to a missing file: scripts/fusion/bucket_chain_linker.py
  • warning missing-ref reference to a missing file: scripts/fusion/cross_validator.py
  • warning missing-ref reference to a missing file: scripts/fusion/multi_dimension_summary.py
  • warning missing-ref reference to a missing file: scripts/fusion/bucket_chain_fusion.py
  • warning missing-ref reference to a missing file: scripts/triggers/coordinated_extraction_trigger.py
  • warning missing-ref reference to a missing file: scripts/memory_indexer.py
  • warning missing-ref reference to a missing file: scripts/monitoring_system.py
  • warning missing-ref reference to a missing file: scripts/tool_output_sanitizer.py
  • note frontmatter-key unknown frontmatter key "always"
  • note frontmatter-key unknown frontmatter key "dependency"

Process rating: all ten parameters 31/100

Will not run. References files that are not bundled: references/api_reference.md, references/api_reference.md, references/api_reference.md
  • 0Tools and files. 20 referenced file(s) missing: references/api_reference.md, references/api_reference.md, references/api_reference.md
  • 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
  • 40Consistency. Frontmatter name (agent-memory) differs from the folder (memory-and-context-engineering)
  • 100Steps. 63 steps
  • 100Execution cost. Instruction body is 3376 tokens
  • 100Running it twice. No mutating operations

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 84: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -335 of 51 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +4Structure: 32 headings
  • +3Step-by-step instructions: 63 items
  • +4Has examples (12 code blocks)
  • +4Reference files are cited in the instructions (15 of 25)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.

External checks

ClawHub: suspicious
This is a legitimate memory system, but it asks to run continuously and includes broad persistence, user profiling, credential handling, and some unsafe local/network behaviors that need review before installation.
LLM: suspicious (high) · 9 Sept 2026