pokemon-player

Play Pokemon via headless emulator + RAM reads.

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/gaming/pokemon-player/SKILL.md

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a strong, experience-driven operational guide with an excellent validated gameplay loop, but it is a monolithic single file and its commands/API usage are described in prose rather than given as complete executable examples.

Suggestions

Move the battle strategy, Gen 1 type chart, and progression milestones into separate reference files (e.g., BATTLE.md, PROGRESSION.md) linked one level deep from SKILL.md to improve progressive disclosure.

Provide complete copy-paste command blocks for startup (e.g., `pokemon-agent serve --rom roms/pokemon_red.gb --port 9876 &`) and example API request payloads for POST /action and POST /save.

Consolidate the repeated vision-emphasis guidance into a single section to remove redundancy and tighten token usage.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and rich with non-obvious experience-based gotchas, but vision-importance is restated across four sections and the general type-chart basics ("Water beats Fire") restate knowledge Claude already has; could be tightened.	2 / 3
Actionability	Provides concrete endpoints, action names, and cursor sequences, but startup commands are described in prose rather than assembled into copy-paste blocks and no example API request payloads are shown, leaving key details missing.	2 / 3
Workflow Clarity	The gameplay loop (OBSERVE→ORIENT→DECIDE→ACT→VERIFY→RECORD→SAVE) is a clear sequence with explicit validation checkpoints (GET /health, screenshot verify after every move, re-evaluate after 3+ failed attempts) and an error-recovery feedback loop.	3 / 3
Progressive Disclosure	No bundle files exist and the entire ~210-line skill lives in one file; sections are well-organized, but content that could be split out (battle strategy, type chart, progression milestones) is inline with no one-level-deep references, and the under-50-line simple-skill exemption does not apply.	2 / 3
	Total	9 / 12 Passed

Description

57%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and distinctive but stops short of full completeness: it states what the skill does without an explicit when-to-use trigger clause, and its trigger-term coverage is limited to the core keyword plus technical mechanism language.

Suggestions

Add an explicit 'Use when…' clause naming natural triggers such as 'play pokemon', 'pokemon game', or when the user mentions a ROM file (.gb/.gbc/.gba).

Expand trigger terms beyond the single keyword to include common user phrasings like 'gameplay', 'gameboy', or 'watch an AI play Pokemon'.

Consider listing the concrete capabilities (serve the game, read RAM state, take screenshots, save/load) to lift specificity from a single action to multiple concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete mechanism ("Play Pokemon via headless emulator + RAM reads") but lists essentially a single action rather than multiple specific concrete actions as the score-3 anchor requires.	2 / 3
Completeness	Clearly states what the skill does, but provides no "Use when…" clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Includes the natural term "Pokemon"/"play", but leans technical with "headless emulator" and "RAM reads" and omits common variations ("pokemon game", "gameplay", "gameboy") that the body's When-to-Use section actually contains.	2 / 3
Distinctiveness Conflict Risk	Targets a clear, narrow niche (Pokemon gameplay via headless emulator with RAM reads) with distinct triggers unlikely to overlap with other skills.	3 / 3
	Total	9 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/gaming/pokemon-player/SKILL.md
Commit: 4c9628e

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.