SKILLEMALL.ai
GitHub ↗ RU Sign in

AB shift

Multi-identity delegation for OpenClaw. Turns a single agent into a system of specialized sub-identities (coding, research, quick tasks) each powered by different AI models. Use when: (1) the user asks a coding task (write, debug, implement, refactor, explain code), (2) the user asks for research, analysis, comparison, or explanation, (3) the user asks a quick question, lookup, or reminder, (4) the user asks anything that would benefit from a specialized model. NOT for: trivial greetings, acknowledgments, or meta-conversation about the chat itself. SHIFT handles routing, delegation, sub-identity-to-sub-identity consultation, synthesis, and cost management entirely within one conversation.

LeoYeAI/openclaw-master-skills Agent Skills author: LeoYeAI MIT 14 files · 1 script body ≈ 3 886 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Multi-identity delegation for OpenClaw.

As a process B 69/100 · Nearly there — weak spots: result and completion, inputs and preconditions

ProcedureSoftware developmentAI 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
92/100
safety, quality, tests
Safety 60%
99
Quality 40%
81
Run on models
none yet
Process rating
B
69/100
Nearly there
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
50
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 · 1

    ✓ No critical or high findings

    Medium and low: 1
    • low Risky intent intent-offensive-security README.md:293
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      `scripts/setup.sh` only creates local directories and copies files. No network calls, no privilege escalation.

    Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Multi-identity delegation for OpenClaw. Turns a single agent into … ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value

    Process rating: all ten parameters 69/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 50When it triggers. No condition that starts the skill
    • 100Tools and files. No external tools needed
    • 100Steps. 65 steps
    • 100Failures and branches. 1 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3886 tokens
    • 100Running it twice. Mutating operations check current state
    • 100Progress reporting. Reports progress
    • low 21 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
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 697: enough signal without eating the budget
    • +4Structure: 47 headings
    • +3Step-by-step instructions: 65 items
    • +4Has examples (21 code blocks)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.