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 TMDB/Douban ID; 5) The user wants TV recognition to use a specific TMDB episode group.

Quality

88%

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

77%Weight 40%Scale 1-3

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

The body is highly actionable and workflow-clear with strong validation guardrails for a destructive list-replacement operation. Its main weakness is conciseness (repeated messages) and progressive disclosure (large inline example/reference sections that a multi-file bundle would offload).

Suggestions

De-duplicate the operator-spacing rule and the 'custom identifiers are global' message: state each once in its canonical section and cross-reference rather than restating in 'Important Rules', Step 2, and 'Safety Notes'.

Move the 'Common Scenarios and Examples' and 'WordsMatcher Processing Logic Reference' sections into separate reference files (e.g. examples.md, wordsmatcher.md) and link to them from SKILL.md to improve progressive disclosure.

Trim the conceptual restatement of regex escaping in 'Important Rules' since the concrete escaped examples already demonstrate it.

Dimension	Reasoning	Score
Conciseness	Most of the body is novel, dense domain knowledge (WordsMatcher format, Chinese-number handling, operator syntax), but the operator-spacing rule ('Operators must have spaces on both sides' vs rule #2) and the global-safety message are each repeated across three sections, so it could be tightened.	2 / 3
Actionability	Provides executable regex examples for all four rule formats, real tool signatures (query_custom_identifiers(), update_custom_identifiers(identifiers=[...]), recognize_media(title=...)), and copy-paste-ready scenario examples.	3 / 3
Workflow Clarity	A clear 7-step sequence includes a duplicate-check validation step (Step 4), a CRITICAL warning that update_custom_identifiers replaces the entire list (a destructive batch operation), and an optional recognize_media verification step, giving explicit checkpoints and a feedback loop.	3 / 3
Progressive Disclosure	No bundle files exist, so this is a single-file skill with well-organized sections, but the large inline 'Common Scenarios and Examples' (~70 lines) and 'WordsMatcher Processing Logic Reference' sections read as content that could be split into separate reference files.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, bilingual, and complete, with an explicit 'Use when...' trigger and concrete actions, all in third person. It is a strong, low-conflict description that needs no changes.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'generates identifier rules', 'checks for duplicates against existing rules, and saves them via MCP tools' — plus five enumerated scenarios, matching the anchor for listing multiple specific concrete actions rather than naming only a partial set.	3 / 3
Completeness	Explicit 'Use this skill when a user provides a torrent name or file name...' trigger answers when, while 'generates identifier rules... checks for duplicates... saves them via MCP tools' answers what, satisfying both halves.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — 'torrent name or file name', 'fix recognition issues', '自定义识别词', 'block unwanted keywords', 'episode offset', 'TMDB/Douban ID' — with good bilingual coverage rather than only technical jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear MoviePilot/WordsMatcher custom-identifier niche with bilingual, domain-specific triggers, making it unlikely to fire for an unrelated skill.	3 / 3
	Total	12 / 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: jxxghp/MoviePilot
Path: skills/generate-identifiers/SKILL.md
Commit: 1b065cc

Reviewed: 9 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.