Skill audit report

kb-article Audit report.

Draft a knowledge base article from a resolved issue or common question. Use when a ticket resolution is worth documenting for self-service, the same question keeps coming up, a workaround needs to be published, or a known issue should be communicated to customers.

EXPERIMENTAL · REVIEWNeeds reviewGenerated Oct 16, 2026Heuristic metadata audit

Audit

Trust

Quality

Security

100

Maintain

Install

OpenAgentSkill Trust Score

Strong shortlist

OpenAgentSkill Trust Score

The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.

GitHub adoption

PASS

100

30K GitHub stars

Stars/forks activity

PASS

30K stars, 3.4K forks; issue activity unavailable in current metadata

Recent maintenance

PASS

100

Pushed today

License clarity

PASS

Apache-2.0

README/SKILL.md completeness

PASS

Metadata includes enough usage and workflow context

Dependency/runtime risk

INFO

credential or environment access, network or browser surface

Install availability

PASS

npx skills add anthropics/knowledge-work-plugins --skill kb-article

Install command safety

PASS

standard package or runtime install path

Permission surface

WARN

secrets or environment access, filesystem or document access

Repository evidence

PASS

https://github.com/anthropics/knowledge-work-plugins/tree/main/customer-support/skills/kb-article

Review status

INFO

AI review data available

Agent Proven outcomes

INFO

No agent outcome data yet

Checks

Install and adoption review

8 Passed · 10 Needs review

Install path

PASS

npx skills add anthropics/knowledge-work-plugins --skill kb-article

Repository

PASS

https://github.com/anthropics/knowledge-work-plugins/tree/main/customer-support/skills/kb-article

License

PASS

Apache-2.0

Maintenance

100

PASS

Pushed today

AI review

CHECK

SKILL.md uses unresolved `~~support platform`, `~~knowledge base`, and `~~project tracker` placeholders instead of concrete connector names, which may make the skill ambiguous outside its original repo.

README/SKILL.md completeness

PASS

Usable description available

Dependency risk

CHECK

credential or environment access, network or browser surface

Install command safety

PASS

standard package or runtime install path

Permission surface

FIX

secrets or environment access, filesystem or document access

Stars/forks activity

PASS

30K stars, 3.4K forks; issue activity unavailable in current metadata

Adoption

PASS

30K GitHub stars

Warnings

Permission surface may require sandboxing
SKILL.md uses unresolved `~~support platform`, `~~knowledge base`, and `~~project tracker` placeholders instead of concrete connector names, which may make the skill ambiguous outside its original repo.
No explicit guidance for handling sensitive data (PII, internal notes, credentials) when reading tickets or internal systems; the skill should require redacting confidential information from any customer-facing draft.
The skill references CONNECTORS.md but the submitted directory only contains SKILL.md, so portability depends on files outside the skill.
Quality score needs review
Permission surface needs review: secrets or environment access, filesystem or document access
Permission surface: secrets or environment access, filesystem or document access

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.

Install path

Review the report before installing into production agents.

$ npx skills add anthropics/knowledge-work-plugins --skill kb-article

Agent-readable metadata

Machine decision packet

Embedded JSON exposes suited tasks, suited agents, install command, trust score, safety gate, alternatives, and do-not-use conditions for agent review.

Install policy: review
Best agents: Codex + Claude Code
Alternatives: 3

Open agent JSON

Signals

Audit score: 85/100
Quality: 92/100
Trust: 74/100
Install safety: 92/100
Permission surface: 46/100
Maintenance: Pushed today
Events: 6 events
GitHub stars: 30K
Last push: Oct 16, 2026

Agent safety v2

57/100 · Review before install

Experimentalreview

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

Test manually in an isolated workspace and compare against safer alternatives.

High-risk permission hints: Secrets or environment access
57/100 agent safety score

Network access

medium

Skill likely fetches remote pages, APIs, repositories, or external services.

Filesystem access

medium

Skill may read or write project files, documents, generated artifacts, or local workspace state.

Secrets or environment access

high

Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.

High-risk permission hints: Secrets or environment access
Permission surface may require sandboxing

Back to skill Alternatives Audit badge SVG

Compare nearby options

Related skills to audit next

full-output-enforcement

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

96K Stars · Audit report

distributed-llm-pretraining-torchtitan

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

13K Stars · Audit report

peft-fine-tuning

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

13K Stars · Audit report