SKILLEMALL.ai
GitHub ↗ RU Sign in

BF ai-pm-playbook

A comprehensive operating system for AI Product Management. Use this skill when planning, prototyping, evaluating, or launching AI-native products. It provides agentic workflows for roadmap planning under uncertainty, rapid prototyping, AI evaluations, cross-functional collaboration, go-to-market strategy, and responsible AI deployment.

ClawHub Agent Skills author: Daniel Foo Jun Wei v1.0.0 MIT-0 12 files body ≈ 1 019 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 28/100 · Will not run — References files that are not bundled: scripts/pm_feedback_loop.py

ProcedureInfrastructureOperations and projectstype 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
82/100
safety, quality, tests
Safety 60%
85
Quality 40%
78
Run on models
none yet
Process rating
F
28/100
Will not run
References files that are not bundled: scripts/pm_feedback_loop.py
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

How to improve

  1. 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 · 15

✓ No critical or high findings

Medium and low: 15
  • low Risky intent intent-offensive-security references/responsible_ai.md:3
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    This framework outlines the key pillars of responsible AI development, focusing on ethical principles, technical guardrails, and red teaming.
    detector
  • low Risky intent intent-offensive-security references/responsible_ai.md:25
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ## 3. AI Red Teaming: Proactively Identifying Risks
  • low Risky intent intent-offensive-security references/responsible_ai.md:26
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    Red teaming is a proactive, adversarial approach to testing AI systems for vulnerabilities and potential harms before release.
  • low Risky intent intent-offensive-security references/responsible_ai.md:29
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ### Types of Red Teaming
  • low Risky intent intent-offensive-security references/responsible_ai.md:30
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **Manual Red Teaming:** Human testers think like adversaries to craft complex attack strategies. Effective for identifying novel vulnerabilities.
  • low Risky intent intent-offensive-security scripts/pm_feedback_loop.md:45
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition; documentation table row)
    | `safety`, `guardrail`, `red team` | Review responsible AI practices and update the red teaming plan to cover identified safety gaps. | `references/responsible_ai.md`, `templates/red_teaming_plan.md`
    detectortable
  • low Risky intent intent-offensive-security scripts/pm_feedback_loop.md:105
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    if "safety" in point.lower() or "guardrail" in point.lower() or "red team" in point.lower():
    detector
  • low Risky intent intent-offensive-security SKILL.md:20
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    - Implementing ethical guardrails and red teaming for responsible AI.
    detector
  • low Risky intent intent-offensive-security SKILL.md:59
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    - **Action:** Implement multi-layered guardrails and conduct rigorous red teaming.
    detector
  • low Risky intent intent-offensive-security SKILL.md:75
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **`templates/`**: Standardized formats for roadmaps, evals, and red teaming plans.
  • low Risky intent intent-offensive-security templates/red_teaming_plan.md:1
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    # AI Red Teaming Plan Template
  • low Risky intent intent-offensive-security templates/red_teaming_plan.md:17
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ## 3. Red Teaming Objectives
  • low Risky intent intent-offensive-security templates/red_teaming_plan.md:18
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    *Define the specific goals of the red teaming exercise.*
  • low Risky intent intent-offensive-security templates/red_teaming_plan.md:24
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    *Describe the approach and techniques that will be used for red teaming.*
  • low Risky intent intent-offensive-security templates/red_teaming_plan.md:37
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    **Execution Timeline:** [Provide a schedule for the red teaming exercise]

Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: scripts/pm_feedback_loop.py

Process rating: all ten parameters 28/100

Will not run. References files that are not bundled: scripts/pm_feedback_loop.py
  • 0Tools and files. 1 referenced file(s) missing: scripts/pm_feedback_loop.py
  • 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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 2 mutating operations with no state check
  • 40Consistency. Frontmatter name (ai-pm-playbook) differs from the folder (ai-product-manager-playbook)
  • 100Steps. 27 steps
  • 100Execution cost. Instruction body is 1019 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +3Description length 338: enough signal without eating the budget
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 27 items
  • +4Reference files are cited in the instructions (6 of 6)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.

External checks

ClawHub: clean
This is a low-risk AI product management playbook made of markdown guidance and templates, with one privacy caution around using production data for evaluations.
LLM: benign (high) · VirusTotal: · 29 May 2026