write-like-meng-on-x

Write, rewrite, review, or continuously refine X/Twitter posts in Meng To's current voice using his deduplicated authored-post corpus, personal and product context, shared resources, and Content repo evidence. Use when asked to improve a tweet in Meng's tone, draft an original post, reply, thread, resource share, or quote post as Meng, check whether an angle repeats an earlier post, study Meng's writing style, ingest another 20-50 authored posts, or hone the reusable Meng X voice profile.

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%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.

The body is a lean, exemplar instruction skill: no padding, executable commands and precise rules throughout, workflows with real validation and failure handling, and a clean split between the overview and one-level-deep reference files that all exist. Batch corpus ingestion is paired with duplicate-receipt validation, so the destructive/batch cap does not apply.

Dimension	Reasoning	Score
Conciseness	The ~130-line body is dense, task-specific guidance ('Treat authored X posts as voice evidence, not as copy to splice together'; 'Do not load or restate the entire corpus when a focused rg search is enough') with no explanations of concepts Claude already knows; every rule is operational rather than explanatory padding, so nothing could be trimmed.	5 / 5
Actionability	Guidance is fully executable: copy-paste commands (git status --short --branch, node <skill-dir>/scripts/update-tweet-corpus.mjs --input <batch-path>, the --check validation block), exact X URLs, a hard 'return exactly five finished options' rule with a labeled remix taxonomy, and a concrete evidence order for drafting.	5 / 5
Workflow Clarity	Each workflow is a numbered sequence with explicit validation checkpoints: the script receipt check ('A healthy run reports zero duplicate IDs, URLs, and text hashes'), a dedicated Validate And Commit section, explicit failure handling ('If X is logged out, CAPTCHA-blocked, or the Codex browser cannot attach, stop and report the exact blocker'), and a no-op guard against churn.	5 / 5
Progressive Disclosure	SKILL.md serves as the operational overview while bulk material lives one level deep in verified, well-signaled linked files (references/voice-profile.md, references/content-source-map.md, tweet-corpus.jsonl searched via rg, scripts/update-tweet-corpus.mjs) — all of which exist in the bundle, with guidance to read only relevant rows.	5 / 5
	Total	20 / 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.

The description is a strong exemplar: it states concrete capabilities in third person, covers natural trigger phrasing including synonyms, includes an explicit 'Use when...' clause with enumerated triggers, and occupies a distinct niche with no realistic conflict risk. Its length is justified by trigger density rather than padding.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete, comprehensive actions in third-person imperative voice ('Write, rewrite, review, or continuously refine X/Twitter posts', 'ingest another 20-50 authored posts', 'hone the reusable Meng X voice profile'), enumerating the skill's full task surface rather than a generic domain.	5 / 5
Completeness	It clearly answers both 'what' (first sentence: writes/refines posts in Meng's voice using his deduplicated corpus and Content repo evidence) and 'when' via an explicit 'Use when asked to...' clause enumerating concrete trigger cases.	5 / 5
Trigger Term Quality	Natural user phrasing is comprehensively covered with synonyms: 'improve a tweet', 'in Meng's tone', 'draft an original post, reply, thread, resource share, or quote post', 'study Meng's writing style' — both tweet/post and tone/style/voice variants users would actually say are present.	5 / 5
Distinctiveness Conflict Risk	The niche is unambiguous — writing in Meng To's specific personal X voice with his authored-post corpus — so it is clearly distinguishable from any other skill and carries minimal wrong-skill trigger risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: MengTo/Skills
Path: agent-skills/codex/write-like-meng-on-x/SKILL.md
Commit: 798db0a

Reviewed: 5 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.