Tessl • The management layer for AI agent skills

A tight, safety-conscious instruction body with executable command examples and exemplary validation/confirmation checkpoints for a destructive-capability skill. The only real gaps are minor: unshown syntax for the verification commands and no pointer to the bundled script.

Suggestions

Reference the implementing script explicitly, e.g. 'run via scripts/douyin_interact.py', so the bundle structure is discoverable from the body.

Add one example for favorite (and note collection-move/collection-remove exist) since the script supports them but the body only names unlike/favorite in passing.

Dimension	Reasoning	Score
Conciseness	Every sentence carries operational information — verification commands, session path, confirm flag semantics, error codes, retry policy — with zero concept explanation or padding. The body is lean and assumes Claude's competence.	5 / 5
Actionability	The three bash examples are copy-paste ready with real flags (--url, --text, --comment-id, --confirm), covering the common like/comment/reply cases. Minor gaps: the douyin-hunter verification commands are named but not shown with syntax, and favorite/unfavorite/collection invocations are never exemplified.	4 / 5
Workflow Clarity	The sequence is explicit and well-checkpointed for a write-operation skill: verify target first, preview by default, require user confirmation via --confirm, submit exactly once, and on timeout/ambiguous results check the platform rather than auto-retry, with named error codes (SIGN_UNAVAILABLE, UNSUPPORTED_OPERATION) treated as failures.	5 / 5
Progressive Disclosure	For a short single-purpose skill the body is appropriately compact with no inlined bulk, but it never points to the bundled scripts/douyin_interact.py that implements the douyin-interact command, leaving the bundle relationship implicit.	4 / 5
	Total	18 / 20 Passed

Description

70%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 concise, concrete description of Douyin interaction capabilities with a strong safety-relevant preview-then-confirm framing. Its main weakness is the missing explicit 'when to use' trigger clause, and it undersells the full action set the script supports.

Suggestions

Add a 'Use when...' (使用场景) clause, e.g. 'Use when the user asks to like, favorite, comment on, or reply to Douyin works' — this would raise completeness from 3 and also strengthen trigger terms.

Mention the inverse/collection actions the script supports (unlike, unfavorite, collection moves) so the description covers the full capability set.

Consider including a natural synonym such as 抖音视频/短视频 alongside 作品 for broader trigger coverage.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — "点赞、收藏、评论或回复评论" plus the preview-then-confirm behavior "先预览目标与文字，再执行已确认的操作" — but omits unlike/unfavorite/collection operations the bundled script actually supports, leaving minor gaps in coverage.	4 / 5
Completeness	The 'what' is clear (like/favorite/comment/reply with preview-then-confirm), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Natural terms a user would say are present ("抖音", "点赞", "收藏", "评论", "回复"), giving good keyword coverage, but common variations/synonyms like "抖音视频" or "短视频" are missing.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche — write-side interactions on a specific platform (Douyin) with explicit interaction verbs — that is unlikely to trigger for unrelated skills such as content-fetching ones.	5 / 5
	Total	16 / 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: TeamWiseFlow/xiaobei
Path: crews/main/skills/expert-bd/tools/douyin-interact/SKILL.md
Revision: 47aea0b

Reviewed: 20 days ago

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.

douyin-interact

Table of Contents

Is this your skill?