SKILLEMALL.ai
GitHub ↗ RU Sign in

AB claudify

Agentic AI lifecycle: create + improve + persist. create - convert functionality into Claude Code automation (agent/skill/rule/hook/command) [SKILL.md], background-polling - mandatory ScheduleWakeup/timeout polling discipline for 5min+ background dispatches [background-polling.md], improve - self-improving loop: retrospect + hook/skill review + pattern detect [improve.md], persist - knowledge persistence: documentation + memory save [persist.md]. Use when "agentify", "agentic", "automate this", "create an agent", "make a plugin", "make a skill", "self-improve", "claudify improve", "claudify persist", "background polling", "ScheduleWakeup".

ClawHub Agent Skills author: es6kr v0.9.0 MIT-0 15 files body ≈ 3 164 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 67/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, running it twice

AnalyzerAI 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
A
96/100
safety, quality, tests
Safety 60%
100
Quality 40%
91
Run on models
none yet
Process rating
B
67/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

    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 · 0

    ✓ No critical or high findings

    Files scanned: 15. 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 67/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 18 mutating operations with no state check
    • 60Result and completion. Output format stated, no completion criterion
    • 85Steps. 49 steps, 1 vague phrases
    • 100Tools and files. Tools declared in frontmatter
    • 100Failures and branches. 5 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3164 tokens

    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

    • +4Description does not say when NOT to use the skill (false activations)
    • -212 emoji in the instructions: noise for the model
    • +2Single-language instructions
    • +5Description quotes 11 example trigger phrases
    • +3Description length 647: enough signal without eating the budget
    • +4Structure: 18 headings
    • +3Step-by-step instructions: 49 items
    • +3Output format is stated explicitly
    • +4Has examples (3 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.

    External checks

    ClawHub: suspicious
    This is mostly a coherent Claude automation builder, but it can persist session and project knowledge to an unspecified memory/RAG store without asking first.
    LLM: suspicious (high) · 5 Sept 2026