find-relevant-skill

find-relevant-skill is a skill for Claude Code, Codex from pnp/sharepoint-skills. It costs 121 tokens per session (2,250 once invoked), scanned A, original, MIT.

A procedure for checking whether a SharePoint site already has a reusable skill for a request. It also guides the agent through evaluating and proposing an external skill when needed.

In plain words
What is it for?
Checking local SharePoint skills before recurring work, deciding whether to use or adapt one, and asking permission before searching the PnP SharePoint Skills repository.
Why use it?
It helps avoid missing site-specific instructions and reduces the risk of using an unsuitable skill.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Checking local SharePoint skills before recurring work, deciding whether to use or adapt one, and asking permission before searching the PnP SharePoint Skills repository.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pnp/sharepoint-skills/find-relevant-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 pnp/sharepoint-skills --skill find-relevant-skill
Clone the repo
git clone --depth 1 https://github.com/pnp/sharepoint-skills

Made for: Claude Code, Codex.

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 find-relevant-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/pnp/sharepoint-skills/find-relevant-skill/github.svg)](https://agentmods.dev/skills/pnp/sharepoint-skills/find-relevant-skill)
Your own site
<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/find-relevant-skill"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/find-relevant-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 find-relevant-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/find-relevant-skill"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/find-relevant-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,250 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 62
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00121 $0.02250
Opus 5 $0.00060 $0.01125
Sonnet 5 $0.00024 $0.00450
Haiku 4.5 $0.00012 $0.00225

Measured 10d ago against content hash a86163d67b5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

find-relevant-skill 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.

Skills/find-relevant-skill/find-relevant-skill/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

find-relevant-skill

When to use

Use this skill when the user asks whether this site has a skill for a task, or when the agent is about to handle a recurring or site-specific procedure and no loaded or listed local skill obviously covers it. Don't use it for one-off questions or small talk that don't call for a reusable procedure — the check adds a step that only pays off when a skill could plausibly exist.

This skill helps avoid missing reusable site-specific procedures before doing work directly.

Inputs

Use or infer:

  • The user's current task or request
  • The current site context
  • Any skills already listed in the conversation context
  • Site skills stored wherever this site keeps its local skill library (commonly AgentAssets/Skills, but confirm the actual location for this site rather than assuming), when available
  • Optional external reference: PnP SharePoint Skills repo at https://github.com/pnp/sharepoint-skills/tree/main/Skills

Steps

  1. Restate the task in one short phrase.

  2. Check known skills first.

    • Review loaded skills and site skills already present in context.
    • If a clearly relevant skill exists, activate it (however this environment loads a skill) and follow it.
  3. If no known local skill clearly applies, inspect this site's skills.

    • Look for skill folders or SKILL.md files in this site's local skill library.
    • Read candidate skill descriptions or SKILL.md files as needed.
    • Don't guess skill names or claim a skill exists without finding it.
  4. If no local skill matches, ask before checking the PnP SharePoint Skills repo.

    • Use the repo as a known external source for possible reusable skill patterns: https://github.com/pnp/sharepoint-skills/tree/main/Skills.
    • Always ask the user before searching or accessing the PnP repo, even if they previously approved web search in another turn.
    • Ask exactly: "Want me to search the PnP SharePoint Skills repo for a matching skill?"
    • Do not search or access the public web unless the user explicitly confirms for this specific check.
    • If the user confirms, search the web for the task plus the repo URL.
    • Don't claim an external skill exists unless it was found through an allowed web search or already provided in conversation.

Read the full file on GitHub · 183 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 · 183 lines · 121 tokens per session scan A a86163d67b5c

Subscribe to this mod's changes

find-relevant-skill is a skill published in the GitHub repository pnp/sharepoint-skills (112 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 2,250 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.