CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tiktok-engagement

TikTok本人已发布作品数据获取和指标回填,不负责发布或其他账号数据分析。

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./crews/main/skills/expert-tiktok/tools/tiktok-engagement/SKILL.md
SKILL.md
Quality
Evals
Security

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.

The body is an exemplar of token efficiency: dense, purely operational, with copy-paste-ready commands and a clearly sequenced fetch workflow that includes genuine validation safeguards for a batch update operation. Remaining gaps are minor — unexplained check/daily subcommands, no stated ordering across commands, and no section headers. Strong result overall.

DimensionReasoningScore

Conciseness

The ~12-line body contains zero padding and no explanation of concepts Claude already knows — every sentence carries operational facts (limits, matching rules, write rules, boundaries). It matches 'lean and efficient; every token earns its place', and anchor 4 would imply trimmable content, of which there is none.

5 / 5

Actionability

The bash block gives copy-paste-ready commands with concrete flags for all four subcommands (check/list/fetch/daily), and the prose adds concrete behavioral rules (URL matching, skipped records, non-negative integers only). Minor gaps remain: `check` and `daily` are never explained, no example output is shown, and where a valid --record-id comes from is only implied — so it sits just below the fully-executable anchor 5.

4 / 5

Workflow Clarity

The fetch workflow is sequenced (在线核验当前用户 → 获取本人作品列表 → 按完整发布 URL 匹配 → 调用 update-metrics) with real validation checkpoints for this batch operation: author mismatch stops ("作者不符即停止"), unmatched records return skipped, and null never overwrites history — so the batch-operation cap does not apply. It falls short of anchor 5 because there is no error-recovery/feedback loop and the intended order across the four commands (check → list → fetch → daily) is never stated.

4 / 5

Progressive Disclosure

At under 50 lines with no bundle files, nothing needs splitting into references, and the layout is logically ordered (commands → semantics → rules/boundaries). However, there is only a single H1 with no section headers separating command usage, workflow semantics, and write rules, leaving minor organization gaps that keep it below the well-organized anchor 5.

4 / 5

Total

17

/

20

Passed

Description

53%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 communicates a clear, narrow scope with an effective exclusion clause, but it omits any explicit 'when to use' trigger guidance and has limited trigger-term coverage. Specificity is adequate (two concrete actions) without enumerating the skill's actual capabilities. Adding a use-when clause and richer natural keywords would lift most dimensions.

Suggestions

Add an explicit trigger clause (e.g. 'Use when backfilling engagement metrics for one's own published TikTok posts' / 需要回填本人 TikTok 作品数据时使用) — its absence currently caps completeness at 3.

Include natural synonyms users would actually say, such as 视频、互动数据、播放量、点赞、评论, so the description matches how the need is phrased.

Enumerate the concrete capabilities (check / list / fetch / daily and which metrics are backfilled) to raise specificity from two actions to several.

DimensionReasoningScore

Specificity

The description names the domain ("TikTok本人已发布作品") and two concrete actions ("数据获取" and "指标回填"), matching the '1-2 concrete actions' anchor. It does not list several specific actions (e.g. the check/list/fetch/daily subcommands or which metrics are backfilled), so it falls short of anchor 4.

3 / 5

Completeness

The 'what' is clear (fetch own published TikTok post data and backfill metrics), but there is no 'Use when...' clause or equivalent explicit trigger guidance — only a negative exclusion ("不负责发布或其他账号数据分析") that weakly implies when not to use it. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3.

3 / 5

Trigger Term Quality

It contains relevant keywords users might say ("TikTok", "作品", "数据", "指标", "回填", "账号") but misses common variations and synonyms such as 视频, 互动数据, 播放量, 点赞, or 评论. This matches 'some relevant keywords but missing common variations or synonyms' rather than the fuller coverage of anchor 4.

3 / 5

Distinctiveness Conflict Risk

It carves a clear niche (own-account published-works metrics backfill) and explicitly excludes adjacent tasks ("不负责发布或其他账号数据分析"), making it mostly distinct. However, trigger terms are thin — little beyond 'TikTok' — so it lacks the distinct trigger phrases of the anchor-5 example and retains minor overlap risk with closely related TikTok analytics/publishing skills.

4 / 5

Total

13

/

20

Passed

Validation

100%

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-tiktok/tools/tiktok-engagement/SKILL.md

Reviewed

Table of Contents

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.