generate-identifiers

Use this skill when a user provides a torrent name or file name and wants to fix recognition issues, or asks to add/manage custom identifiers (自定义识别词). This skill generates identifier rules based on the WordsMatcher preprocessing logic, checks for duplicates against existing rules, and saves them via MCP tools. Because custom identifiers are global, generated rules must default to conservative, sample-specific regex patterns instead of broad matches unless the user explicitly wants global cleanup. Applicable scenarios include: 1) A torrent or file name is incorrectly recognized (wrong title, season, episode, etc.); 2) The user wants to block unwanted keywords from torrent names; 3) The user needs episode offset rules for series with non-standard numbering; 4) The user wants to force recognition of a specific media by source-native ID; 5) The user wants TV recognition to use a specific TMDB episode group.

Quality

91%

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

Quality

Content

82%Weight 40%Scale 1-5

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

A thorough, actionable skill body with executable examples and a sound workflow, including proper guardrails for a destructive global operation. Slightly verbose due to repeated narrow-vs-broad guidance and could benefit from splitting the processing-logic reference into a bundled file.

Suggestions

Consolidate the 'narrow vs broad / sample-specific anchors' guidance, which currently appears in Global Scope Guardrails, Narrow vs Broad Examples, Workflow Step 2, and Safety Notes, into one authoritative section to reduce repetition.

Move the 'WordsMatcher Processing Logic Reference' into a bundled references/ file (e.g. WORDSMATCHER.md) and link to it from the body, tightening the main SKILL.md overview.

Promote the optional verify step into a recommended checkpoint with a clear fix-and-retry loop, since update_custom_identifiers replaces the entire rule list and misrules affect all future recognition.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and densely packed with domain-specific syntax Claude does not already know, but the 'narrow not broad' guidance is restated across Global Scope Guardrails, Narrow vs Broad Examples, Workflow Step 2, and Safety Notes, which could be consolidated.	4 / 5
Actionability	Fully executable: concrete regex examples with proper escaping, exact tool-call signatures (query_custom_identifiers, update_custom_identifiers with the full identifiers list), and worked examples for every common case.	5 / 5
Workflow Clarity	A clear 7-step sequence with validation checkpoints (query existing rules, duplicate/conflict checks, the CRITICAL full-list-replacement warning), but the optional verify step and lack of an explicit fix-and-retry loop leave a minor gap for this destructive/batch operation.	4 / 5
Progressive Disclosure	Single file with well-organized, clearly headed sections and no nested references; appropriate for a self-contained skill, though the length and inlined reference-style content (WordsMatcher processing logic) could live in a separate reference file.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

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

A strong description that clearly states what the skill does and when to use it, with concrete bilingual trigger terms and a distinct niche. Minor verbosity in the enumerated scenarios does not detract from clarity.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('generates identifier rules', 'checks for duplicates against existing rules', 'saves them via MCP tools') plus five enumerated scenario types, giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both: what it does (generate/duplicate-check/save identifier rules via MCP) and when to use it (an explicit 'Use this skill when...' clause followed by five concrete trigger scenarios).	5 / 5
Trigger Term Quality	Covers natural user phrasing in both languages — 'torrent name or file name', 'fix recognition issues', '自定义识别词', 'block unwanted keywords', 'episode offset rules', 'TMDB episode group' — with synonyms and concrete trigger phrases.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (MoviePilot/WordsMatcher custom identifier management) with distinct, domain-specific triggers that would not plausibly fire for unrelated skills.	5 / 5
	Total	20 / 20 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: jxxghp/MoviePilot
Path: skills/generate-identifiers/SKILL.md
Commit: f28e8b1

Reviewed: 4 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.