Agent skill

Single Match Review

by 123Cx330Yrx in 123Cx330Yrx/riftcoach-agent

Review one specified completed match from a validated RiftCoach summary using attributable knowledge.

MITAuto-check passedAI & LLM Engineering

Install Single Match Review

skills CLI
$ npx skills add 123Cx330Yrx/riftcoach-agent --skill single-match-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install 123Cx330Yrx/riftcoach-agent single-match-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/123Cx330Yrx/riftcoach-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/single-match-review .claude/skills/single-match-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
single-match-review
GitHub stars
105
Token cost
~453 tokens
SKILL.md length
227 words
Files
2
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Review one specified completed match from a validated RiftCoach summary using attributable knowledge.

  • Works in 6 steps: Validate Player Summary Schema v1.0 and… → Isolate the target match instead of… → Check short-game and Timeline… → …
  • A deep review of this match
  • SKILL.md covers Objective, Workflow, Evidence Rules and Forbidden Behavior
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Single Match Review is an agent skill from 123Cx330Yrx/riftcoach-agent. Review one specified completed match from a validated RiftCoach summary using attributable knowledge. Use for a deep review of this match, one game, or an explicit match ID.

Its SKILL.md is about 450 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `manifest.yaml`).

It sits in AI & LLM Engineering. It works with FastAPI and Python. The repository describes itself as: A quality-gated League of Legends post-game coaching agent built on deterministic match data, RAG, and LLM evaluation. The licence is MIT.

When your agent uses it

  • A deep review of this match
  • An explicit match ID

Example prompts

  • “/single-match-review”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Validate Player Summary Schema v1.0 and locate target_match_id exactly once.
  2. Isolate the target match instead of turning other match rows into single-game facts.
  3. Check short-game and Timeline availability before interpreting the metrics.
  4. Use knowledge.search only to explain a metric, limitation, or general training principle.
  5. Separate measured facts, cautious interpretations, and bounded training actions.
  6. Return the typed output for independent Harness evaluation and publication control.

What it can do on your machine

Read from SKILL.md and the folder at commit 7cb66d2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Single Match Review loads about 453 tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 227 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~453

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from 123Cx330Yrx/riftcoach-agent at commit 7cb66d2, republished under its MIT licence (© 123Cx330Yrx). 227 words, ~453 tokens.

Download SKILL.mdSave it as .claude/skills/single-match-review/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
single-match-review
description
Review one specified completed match from a validated RiftCoach summary using attributable knowledge. Use for a deep review of this match, one game, or an explicit match ID.

Single Match Review

Objective

Produce a grounded review of exactly one completed match. Treat the selected match row and its deterministic report facts as the only sources of player-specific performance claims.

Workflow

  1. Validate Player Summary Schema v1.0 and locate target_match_id exactly once.
  2. Isolate the target match instead of turning other match rows into single-game facts.
  3. Check short-game and Timeline availability before interpreting the metrics.
  4. Use knowledge.search only to explain a metric, limitation, or general training principle.
  5. Separate measured facts, cautious interpretations, and bounded training actions.
  6. Return the typed output for independent Harness evaluation and publication control.

Evidence Rules

  • Preserve all target-match numbers from deterministic inputs exactly.
  • Cite retrieved knowledge by source_id when it affects a conclusion.
  • Treat a short game as reviewable but insufficient for long-term trend claims.
  • Do not treat unavailable Timeline data as zero or infer event timing from Match Detail.
  • State insufficient evidence when the target row or retrieved knowledge cannot support a claim.

Forbidden Behavior

  • Do not infer the lane opponent, hidden information, live match state, or real-time cooldowns.
  • Do not invent patch-meta, rank, matchup, win-rate, build, or rune comparisons.
  • Do not call Riot API or tools outside the manifest allowlist.
  • Do not use recent aggregate rows as if they were facts from the target match.
  • Do not publish a model draft without the configured quality gate.

© 123Cx330Yrx, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/single-match-review of 123Cx330Yrx/riftcoach-agent.

  • SKILL.md
  • manifest.yaml

Open the folder on GitHubat commit 7cb66d2

Compare with similar skills

Single Match Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Single Match Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Single Match Review this skill123Cx330Yrx/riftcoach-agent105—~453Automated safety check: PassMIT
Kefu Corewhichmen/dxl-commerce-agent130—~1.6kAutomated safety check: PassMIT
Runtime Skillsllama-farm/llamafarm836—~1.3kAutomated safety check: PassApache-2.0
Openrouter Streaming Setupjeremylongshore/tons-of-skills-marketplace2.8k—~2.6kAutomated safety check: PassMIT
Cloudbase Agent PythonTencentCloudBase/CloudBase-AI-Toolkit1.1k2 repos~2.9kAutomated safety check: NotesMIT
Cognee Local Server Setuptopoteretes/cognee32k—~702Automated safety check: NotesApache-2.0

Similar skills

  • Kefu Core

    whichmen/dxl-commerce-agent

    电商客服主调度技能。用于顾客咨询分类、工具选择(订单/物流/退款/图像)、风险分级与回复策略. An agent skill from whichmen/dxl-commerce-agent.

    130 GitHub stars~1.6k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • Runtime Skills

    llama-farm/llamafarm

    Universal Runtime best practices for PyTorch inference, Transformers models, and FastAPI serving.

    836 GitHub stars~1.3k tokensUpdated 4 mo ago
    AI & LLM EngineeringAuto-check passed
  • Openrouter Streaming Setup

    jeremylongshore/tons-of-skills-marketplace

    Implement streaming responses with OpenRouter for real-time UIs.

    2.8k GitHub stars~2.6k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Cloudbase Agent Python

    TencentCloudBase/CloudBase-AI-Toolkit

    Build production-ready AI agent backends using the CloudBase Agent Python SDK — create agents with LangGraph/CrewAI/LlamaIndex, serve them via FastAPI with AG-UI protocol streaming +…

    1.1k GitHub starsUsed in 2 repos~2.9k tokens
    AI & LLM EngineeringAuto-check: notes
  • Cognee Local Server Setup

    topoteretes/cognee

    Starts the cognee API server and web UI on your own machine, checks its health, connects the SDK or CLI to it and helps you pick between multi-tenant and single-user auth.

    32k GitHub stars~702 tokensUpdated yesterday
    Backend & APIsAuto-check: notes
  • Create Plugin

    lbedner/aegis-stack

    A skill your agent uses when building an Aegis Stack plugin, a separate package (aegis-stack-<name) that renders files into a project through aegis add <name.

    143 GitHub stars~1.3k tokensUpdated today
    Backend & APIsAuto-check passed

More from 123Cx330Yrx/riftcoach-agent

  • Recent Form Review

    123Cx330Yrx/riftcoach-agent

    Review a validated recent-match summary and deterministic report using attributable RiftCoach knowledge.

    105 GitHub stars~367 tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Single Match Review

What does Single Match Review do?

Review one specified completed match from a validated RiftCoach summary using attributable knowledge. Single Match Review is an agent skill from 123Cx330Yrx/riftcoach-agent. Review one specified completed match from a validated RiftCoach summary using attributable knowledge.

When should I use Single Match Review?

Single Match Review fits situations like: A deep review of this match; an explicit match ID.

How do I install Single Match Review in Claude Code?

Run `npx skills add 123Cx330Yrx/riftcoach-agent --skill single-match-review -a claude-code`. Or copy the skill folder (skills/single-match-review in 123Cx330Yrx/riftcoach-agent) into .claude/skills/single-match-review in your project. Claude Code loads it when a task matches its description.

How do I install Single Match Review in Codex?

Run `npx skills add 123Cx330Yrx/riftcoach-agent --skill single-match-review -a codex`. Or copy the skill folder (skills/single-match-review in 123Cx330Yrx/riftcoach-agent) into .agents/skills/single-match-review in your project. Codex loads it when a task matches its description.

Can I use Single Match Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add 123Cx330Yrx/riftcoach-agent --skill single-match-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/single-match-review, .gemini/skills/single-match-review, .github/skills/single-match-review and .opencode/skills/single-match-review in your project.

What does Single Match Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Single Match Review is instructions for the agent only.

Does Single Match Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Single Match Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Single Match Review use?

Single Match Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Single Match Review use?

About 453 tokens (SKILL.md is roughly 1.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Single Match Review?

Skills that share tags, products or a category with Single Match Review: Kefu Core (whichmen/dxl-commerce-agent, 130 stars), Runtime Skills (llama-farm/llamafarm, 836 stars), Openrouter Streaming Setup (jeremylongshore/tons-of-skills-marketplace, 2.8k stars) and Cloudbase Agent Python (TencentCloudBase/CloudBase-AI-Toolkit, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Single Match Review?

123Cx330Yrx (a GitHub user) maintains it in 123Cx330Yrx/riftcoach-agent, which has 105 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 10, 2026.

Source: 123Cx330Yrx/riftcoach-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.