checking-skill-quality

checking-skill-quality is a skill for OpenCode from rianvdm/product-ai-public. It costs 111 tokens per session (1,504 once invoked), scanned A, original, MIT.

A checklist for reviewing a coding-agent skill and its supporting files against recommended writing and design practices.

In plain words
What is it for?
Use it to audit a SKILL.md file, its description, supporting materials, process instructions, gotchas, and overall structure.
Why use it?
It helps find unclear triggers, missing failure guidance, unnecessary instructions, and other problems before a skill is used.

Skill for OpenCode

Written for OpenCode: installed under .opencode/.

Good fit Use it to audit a SKILL.md file, its description, supporting materials, process instructions, gotchas, and overall structure.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rianvdm/product-ai-public/check-skill
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add rianvdm/product-ai-public --skill check-skill
Clone the repo
git clone --depth 1 https://github.com/rianvdm/product-ai-public

Made for: OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for checking-skill-quality

README.md
[![agentmods](https://agentmods.dev/badge/skills/rianvdm/product-ai-public/check-skill/github.svg)](https://agentmods.dev/skills/rianvdm/product-ai-public/check-skill)
Your own site
<a href="https://agentmods.dev/skills/rianvdm/product-ai-public/check-skill"><img src="https://agentmods.dev/badge/skills/rianvdm/product-ai-public/check-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for checking-skill-quality

Your own site · 80×15
<a href="https://agentmods.dev/skills/rianvdm/product-ai-public/check-skill"><img src="https://agentmods.dev/badge/skills/rianvdm/product-ai-public/check-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,504 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00111 $0.01504
Opus 5 $0.00056 $0.00752
Sonnet 5 $0.00022 $0.00301
Haiku 4.5 $0.00011 $0.00150

Measured 10d ago against content hash 64dcdfaabe66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

checking-skill-quality scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.opencode/skills/check-skill/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Checking Skill Quality

Context Required

Read the target SKILL.md file before running. If the skill has a folder with supporting files (templates, examples, scenarios), read those too to assess context binding.

Steps

  1. Ask for the skill path if not provided
  2. Read the full SKILL.md at that path — do not skim
  3. If a skill folder exists, list its contents and read any supporting files
  4. Check the frontmatter:
    • Name: lowercase, hyphens only, max 64 chars, gerund form (verb-ing)?
    • Description: starts with "Use when..."? Lists trigger phrases? Written in third person? Loud and specific?
  5. Check for the 5 Skill Killers:
    • Killer 1 — Vague/quiet description: Is it specific, loud, third-person, with "Use when..." format and edge-case triggers?
    • Killer 2 — Over-defined process: Is freedom matched to task fragility? Tight for fragile ops, loose for creative?
    • Killer 3 — Stating the obvious: Does every paragraph add signal the model doesn't already know? Challenge each section.
    • Killer 4 — Missing gotcha section: Is there a dedicated Gotcha Section with documented failure patterns specific to this skill?
    • Killer 5 — Monolithic blob: Is the SKILL.md under 500 lines?
  6. Check skill anatomy completeness and quality:
    • Steps: numbered list (not prose)?
    • Output: literal template/example shown (not just described)?
    • Gotcha Section: present and substantive — not empty, not generic?
    • Constraints: sharp and specific to this skill (not generic model behavior)?
    • Identity/role section: absent? Flag explicitly if present — "Act as a senior X" is always an anti-pattern
  7. Check scoping:
    • Can you describe the skill's job in one sentence?
    • Does it have two distinct triggers suggesting it should be two skills?
    • Would two different people use different halves of it?
  8. Check context binding:
    • Are files specific to this skill in the folder?
    • Are shared/org-level references pointed to externally (not duplicated)?
    • Is any context that should be external being embedded inline?
  9. Classify the skill type:
    • Capability Uplift: new function the model can't do well alone — note it may become obsolete as models improve
    • Encoded Preference: your workflow for something the model can do — note it gets more valuable over time
  10. Generate the audit report per the output format below

Read the full file on GitHub · 129 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 129 lines · 111 tokens per session scan A 64dcdfaabe66

Subscribe to this mod's changes

checking-skill-quality is a skill published in the GitHub repository rianvdm/product-ai-public (15 stars, last pushed 2d ago), licensed MIT. It adds 111 tokens to every session and 1,504 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.