SKILLEMALL.ai
GitHub ↗ RU Sign in

BD review-agent

Pre-meeting review coach for Lark/Feishu (or WeCom). Invoked when a Requester DMs their dedicated review-agent subagent with a draft, proposal, plan, or 1:1 agenda. Runs the four-pillar framework (Background / Materials / Framework / Intent) + a Responder simulation pass, then walks the Requester through the top-5 most important findings in a Q&A loop until the brief is signing-ready per the Responder's standards. Produces a 6-section decision brief on close. Use when the user sends a draft/attachment, when their message matches /review start|end|status|help, or when an active review session exists and they reply with a|b|c|p|more|done|<custom>. Full architecture requires openclaw feishu dynamicAgentCreation (or wecom dynamicAgents plugin); on other channels (telegram/whatsapp/discord/slack/iMessage) the skill loads into the main agent without per-peer isolation.

ClawHub Agent Skills author: YinghaoJia v2.1.2 MIT-0 26 files body ≈ 1 222 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches

AnalyzerSlackDiscordTelegramWhatsAppAI 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
88/100
safety, quality, tests
Safety 60%
92
Quality 40%
83
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
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 · 8

    ✓ No critical or high findings

    Medium and low: 8
    • low Risky intent intent-offensive-security references/agent_persona.md:161
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      > 原七轴（BLUF / Completeness / Evidence / Assumptions / Red Team / Stakeholder / Decision Readiness）降级为内部 sub-reference（`axes_decision_brief_reference.md`），给 LLM 在决策 brief 场景下扫描 Materials 柱时作参考。用户可见只有四柱。
    • low Risky intent intent-offensive-security references/annotation_schema.md:107
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Red Team | Materials |
    • low Risky intent intent-offensive-security references/axes_decision_brief_reference.md:3
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      Synthesizes Completed Staff Work (1942 US Army), BLUF, Staff Study, Policy Memo, and Devil's Advocate / Red Team patterns.
      detector
    • low Risky intent intent-offensive-security references/axes_decision_brief_reference.md:81
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ## Axis 5: Red Team / Counterarguments
    • low Risky intent intent-offensive-security references/axes_decision_brief_reference.md:90
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Red team treated as a checkbox
    • low Risky intent intent-offensive-security references/four_pillars.md:169
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      原七轴（Ask Clarity / Completeness / Evidence / Assumptions / Red Team / Stakeholder / Decision Readiness）**保留为内部 sub-reference**（见 `axes_decision_brief_reference.md`），给 LLM 在决策 brief 场景下扫描时作 checklist 参考
    • low Risky intent intent-offensive-security references/template/AGENTS.md:19
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      7. **CSW gate**: a session can only transition to `ready` when Axis 1 (BLUF), Axis 2 (Completeness), Axis 4 (Assumptions), Axis 5 (Red Team), Axis 7 (Decision Readiness) are all PASS or explicitly fla
    • low Risky intent intent-offensive-security references/template/AGENTS.md:25
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Prefer Socratic style for Axes 3/5/6 (evidence, red team, stakeholders); direct punch-list for Axes 1/2/4/7.

    Files scanned: 26. 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 49/100

    • 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
    • 30Running it twice. 12 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 27 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1222 tokens
    • low The response is described with custom markup (5 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
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Description length 875: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • -33 of 12 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +4Structure: 7 headings
    • +3Step-by-step instructions: 27 items
    • +4Has examples (1 code blocks)
    • +4Reference files are cited in the instructions (4 of 5)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

    External checks

    ClawHub: suspicious
    This appears to be a legitimate review-coach skill, but it needs Review because it processes confidential drafts with broad bot scopes, third-party LLM calls, persistent archives, and an external installer/patch outside the reviewed package.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026