SKILLEMALL.ai
GitHub ↗ RU Sign in

BF self-improving-compound

Agent memory and self-improvement system. Replaces naive file-based agent memory with a structured SQLite learning engine: capture corrections, errors, and reusable lessons during active work, audit recent conversation context via isolated cron jobs with deterministic collectors when available, and promote proven rules into skills and agent instructions. 3+7 co-evolution model — 3 state directories (`memory/`, `learning/`, `skills/`) plus 7 root Markdown control-plane files (`AGENTS.md`, `HEARTBEAT.md`, `IDENTITY.md`, `MEMORY.md`, `SOUL.md`, `TOOLS.md`, `USER.md`) improve together. Adds daily factual memory and workspace stewardship loops. Python 3.8+ CLI with bash hooks. Use for: logging non-obvious failures, user corrections, tool/API gotchas, or missing capabilities before the final reply. Use for: setting up automated cron-based audit pipelines that catch what real-time capture misses. Do not use for trivial typos or routine noise.

ClawHub Agent Skills author: Rockway v6.2.5 MIT-0 40 files · 6 scripts body ≈ 8 345 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 45/100 · Will not run — References files that are not bundled: scripts/..., references/...

ProcedureAI and agentsInfrastructuretype 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
84/100
safety, quality, tests
Safety 60%
95
Quality 40%
67
Run on models
none yet
Process rating
F
45/100
Will not run
References files that are not bundled: scripts/..., references/...
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

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  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
  • medium Broad scope meta-agent-memory-dump memory.md
    Agent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokens
    memory.md

Files scanned: 36. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 8345 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: scripts/...
  • warning missing-ref reference to a missing file: references/...

Process rating: all ten parameters 45/100

Will not run. References files that are not bundled: scripts/..., references/...
  • 0Tools and files. 2 referenced file(s) missing: scripts/..., references/...
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Execution cost. Instruction body is 8345 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 85Steps. 128 steps, 1 vague phrases
  • 100Failures and branches. 10 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 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 14 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (7 tags): a typed call is more reliable

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
  • +3Description length 949: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -32 of 9 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +4Structure: 53 headings
  • +3Step-by-step instructions: 128 items
  • +4Has examples (23 code blocks)
  • +4Reference files are cited in the instructions (4 of 6)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.

External checks

ClawHub: clean
This is a disclosed local memory and self-improvement skill, but users should enable its cron, hooks, transcript collection, and auto-promotion features deliberately because they persist conversation and workspace data.
LLM: benign (high) · VirusTotal: · 29 May 2026