SKILLEMALL.ai
RU Sign in

BF local-coding-orchestrator

Use OpenClaw as a supervisor-driven orchestration scaffold for local coding CLIs such as Codex, Claude Code, and OpenCode. Supports task records, lifecycle transitions, worker launch and reconcile, retry briefs, pipeline presets, and environment-aware blocking for local coding workflows.

ClawHub Agent Skills author: lijiejoy v0.2.2 MIT-0 35 files body ≈ 5 103 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process F 61/100 · Will not run — References files that are not bundled: assets/scripts/run-codex.ps1, assets/scripts/run-claude-code.ps1, assets/scripts/run-opencode.ps1

TemplateSoftware developmenttype 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
83/100
safety, quality, tests
Safety 60%
92
Quality 40%
69
Run on models
none yet
Process rating
F
61/100
Will not run
References files that are not bundled: assets/scripts/run-codex.ps1, assets/scripts/run-claude-code.ps1, assets/scripts/run-opencode.ps1
Tools and files w 18
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

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 · 8

✓ No critical or high findings

Medium and low: 8
  • low Dangerous commands cmd-execpolicy-bypass docs/operator-playbook.md:18
    Runs PowerShell with execution policy bypassed (documentation of a security skill)
    powershell -ExecutionPolicy Bypass -File assets/scripts/supe…ps1 \
    security skill
  • low Dangerous commands cmd-execpolicy-bypass docs/operator-playbook.md:25
    Runs PowerShell with execution policy bypassed (documentation of a security skill)
    powershell -ExecutionPolicy Bypass -File assets/scripts/reco…ps1 \
    security skill
  • low Dangerous commands cmd-execpolicy-bypass docs/operator-playbook.md:32
    Runs PowerShell with execution policy bypassed (documentation of a security skill)
    powershell -ExecutionPolicy Bypass -File assets/scripts/supe…ps1 \
    security skill
  • low Dangerous commands cmd-execpolicy-bypass docs/usage-guide.md:49
    Runs PowerShell with execution policy bypassed (documentation of a security skill)
    powershell -ExecutionPolicy Bypass -File assets/scripts/task…ps1 \
    security skill
  • low Dangerous commands cmd-execpolicy-bypass docs/usage-guide.md:58
    Runs PowerShell with execution policy bypassed (documentation of a security skill)
    powershell -ExecutionPolicy Bypass -File assets/scripts/task…ps1 \
    security skill
  • low Dangerous commands cmd-execpolicy-bypass docs/usage-guide.md:64
    Runs PowerShell with execution policy bypassed (documentation of a security skill)
    powershell -ExecutionPolicy Bypass -File assets/scripts/supe…ps1 \
    security skill
  • low Dangerous commands cmd-execpolicy-bypass docs/usage-guide.md:70
    Runs PowerShell with execution policy bypassed (documentation of a security skill)
    powershell -ExecutionPolicy Bypass -File assets/scripts/supe…ps1 \
    security skill
  • low Dangerous commands cmd-execpolicy-bypass docs/usage-guide.md:76
    Runs PowerShell with execution policy bypassed (documentation of a security skill)
    powershell -ExecutionPolicy Bypass -File assets/scripts/reco…ps1 \
    security skill

Files scanned: 35. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5103 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: assets/scripts/run-codex.ps1
  • warning missing-ref reference to a missing file: assets/scripts/run-claude-code.ps1
  • warning missing-ref reference to a missing file: assets/scripts/run-opencode.ps1
  • warning missing-ref reference to a missing file: assets/scripts/route-task.ps1
  • warning missing-ref reference to a missing file: assets/scripts/multi-orchestrate.ps1
  • warning missing-ref reference to a missing file: assets/scripts/task-state.ps1
  • warning missing-ref reference to a missing file: assets/scripts/evaluate-done.ps1
  • warning missing-ref reference to a missing file: assets/scripts/generate-retry-brief.ps1
  • warning missing-ref reference to a missing file: assets/scripts/start-pipeline.ps1
  • warning missing-ref reference to a missing file: assets/scripts/supervise-task.ps1
  • warning missing-ref reference to a missing file: assets/scripts/launch-worker.ps1
  • warning missing-ref reference to a missing file: assets/scripts/reconcile-worker.ps1

Process rating: all ten parameters 61/100

Will not run. References files that are not bundled: assets/scripts/run-codex.ps1, assets/scripts/run-claude-code.ps1, assets/scripts/run-opencode.ps1
  • 0Tools and files. 12 referenced file(s) missing: assets/scripts/run-codex.ps1, assets/scripts/run-claude-code.ps1, assets/scripts/run-opencode.ps1
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 8 mutating operations with no state check
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 5103 tokens
  • 85Steps. 288 steps, 2 vague phrases
  • 100Result and completion. Output format and completion criterion are stated
  • 100Failures and branches. 7 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • low 24 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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 288: enough signal without eating the budget
  • +4Structure: 57 headings
  • +3Step-by-step instructions: 288 items
  • +3Output format is stated explicitly
  • +4Has examples (3 code blocks)
  • +4Reference files are cited in the instructions (10 of 27)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

External checks

ClawHub: clean
The skill appears coherent and disclosed, with one Windows script-running safety caveat users should understand before use.
LLM: benign (medium) · VirusTotal: · 29 May 2026