Automate TikTok tasks via Rube MCP (Composio): upload/publish videos, post photos, manage content, and view user profiles/stats. Always search tools first for current schemas.
67
51%
Does it follow best practices?
Impact
97%
1.79xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/tiktok-automation/SKILL.mdQuality
Discovery
67%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 does a good job listing specific TikTok automation capabilities and is clearly distinguishable from other skills due to its platform-specific focus. However, it lacks an explicit 'Use when...' clause which limits its completeness score, and could benefit from more natural user-facing trigger terms beyond the technical integration names.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about TikTok posting, uploading TikTok videos, managing TikTok content, or checking TikTok analytics.'
Include more natural trigger terms users might say, such as 'social media posting', 'TikTok analytics', 'schedule TikTok content', or 'TikTok followers'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: upload/publish videos, post photos, manage content, and view user profiles/stats. Also includes a procedural instruction to search tools first for current schemas. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific TikTok automation tasks, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the nature of the tasks described. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'TikTok', 'upload', 'publish videos', 'post photos', 'user profiles/stats', but misses common user variations like 'schedule posts', 'analytics', 'followers', or 'social media'. The mention of 'Rube MCP (Composio)' is technical jargon unlikely to be used by end users. | 2 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to TikTok tasks via a specific integration (Rube MCP/Composio), making it highly distinctive and unlikely to conflict with other skills. The platform-specific focus creates a clear niche. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a reasonably well-structured overview of TikTok automation workflows with clear tool sequences and parameter documentation. However, it suffers from significant redundancy (pitfalls repeated across sections and in a summary section), lacks executable examples with concrete parameter values, and explains concepts Claude already knows (rate limiting, token expiry, exponential backoff). The content would benefit greatly from trimming and adding concrete example tool calls.
Suggestions
Remove the 'Known Pitfalls' section entirely since its content is already covered in per-workflow pitfall sections, or consolidate all pitfalls there and remove per-workflow ones.
Add at least one concrete example tool call with actual parameter values (e.g., a complete RUBE_SEARCH_TOOLS and TIKTOK_UPLOAD_VIDEO invocation) rather than just listing parameter names.
Remove explanations of concepts Claude already knows: exponential backoff, token expiry, defensive parsing, what MP4/WebM formats are.
Add explicit error recovery steps to the video publish workflow (e.g., what to do if FETCH_PUBLISH_STATUS returns a failure state, or if upload fails).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Significant verbosity throughout. The 'Known Pitfalls' section largely repeats pitfalls already stated in individual workflows. The quick reference table duplicates information from the workflow sections. Many pitfalls state things Claude already knows (e.g., 'implement exponential backoff on 429 responses', 'tokens expire'). The content could be cut by 40-50% without losing actionable information. | 1 / 3 |
Actionability | Tool sequences are clearly named and ordered, and key parameters are listed, which is helpful. However, there's no executable code—just tool names and parameter lists. The instruction to 'always call RUBE_SEARCH_TOOLS first to get current tool schemas' undermines the specificity of the documented parameters since they may be stale. No concrete example calls with actual parameter values are shown. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced (upload → poll status → publish), and the video publish flow includes a polling/validation checkpoint. However, the polling step lacks concrete guidance on what to do on failure (just 'failed publishes include error details'), and there's no explicit feedback loop for re-upload or retry on failure. The 'poll at reasonable intervals' advice is vague. | 2 / 3 |
Progressive Disclosure | The content is structured with clear sections and a quick reference table, which aids navigation. However, with no bundle files, all content is monolithic in a single file. The detailed pitfalls, common patterns, and per-workflow documentation could benefit from being split out. The external link to Composio docs is good but the skill itself is quite long for a single file. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
d065ead
Table of Contents
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.