CtrlK
BlogDocsLog inGet started
Tessl Logo

share-of-voice-tracker

Use when the user asks to "track our share of voice", "what share of the conversation do we own vs competitors", or "trend our SOV this quarter"; computes SOV% = brand mentions ÷ (brand + competitor panel mentions) per platform per period on a LOCKED competitor panel — a panel switch invalidates the trend (restart the series and log the break; the ECHO O3 rule) — plus a sentiment-weighted SOV variant (sentiment labeled Estimated unless human-coded) and a Wikipedia-pageviews attention-share alternative; built from keyless listening connectors, gdelt.py news echo, and user exports — public counts only, closed platforms are never scraped. Not for backlink or offsite SEO signals — use offsite-signal-analyzer. 声量份额/竞品声量对比/提及份额/注意力份额

72

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

A well-structured, actionable skill body with a clearly sequenced workflow, concrete per-cell labeling rules, and good progressive disclosure through signaled references. Its one weakness is conciseness — several safety/scope guardrails are repeated verbatim across multiple sections.

Suggestions

Consolidate the 'closed platforms never scraped / 风控封号' red line and the 'competitor-tracker owns strategy' handoff so each is stated once (e.g. in Scope guard) and only referenced elsewhere, to cut repetition.

The Scope guard, Skill Contract, and Reference Materials sections overlap on routing rules (competitor-tracker, offsite-signal-analyzer, social-pulse-monitor) — consider listing the cross-skill routing once and trimming the restatements.

Tighten the parenthetical ECHO-rule asides (O1/O3 labels) so they label the rule once rather than re-explaining the panel-break mechanism in both the intro and step 2.

DimensionReasoningScore

Conciseness

The body is substantive and assumes competence (no concept-explaining fluff), but several guardrails are restated multiple times — the 'closed platforms never scraped / 风控封号' red line and the 'competitor-tracker owns strategy' point each recur across Scope guard, Reads/Writes, and Reference Materials — so it could be tightened.

2 / 3

Actionability

Provides concrete, executable guidance — named scripts (hn.py/bluesky.py/gdelt.py/pageviews.py), exact per-cell labeling rules (Measured/proxy/Estimated), the ≥5s gdelt spacing, and the explicit SOV% formula — copy-paste ready despite being instruction-only.

3 / 3

Workflow Clarity

An 8-step sequence with explicit validation checkpoints and red lines (NEEDS_INPUT on missing panel, 'never splice or backfill across a break', 'an asymmetric query is a broken denominator', the ECHO-O1 denominator red line), matching the anchor for clear sequence with explicit validation.

3 / 3

Progressive Disclosure

Acts as an overview pointing to well-signaled one-level-deep references (echo-benchmark.md, CONNECTORS.md, SECURITY.md, skill-contract.md, and sibling skills) in dedicated Reference Materials and Next Best Skill sections, with the SOV mechanics kept inline and connector recipes deferred.

3 / 3

Total

11

/

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.

A strong, specific description with explicit trigger phrasing, concrete capabilities, and clear scope boundaries that distinguish it from neighboring skills. Voice is appropriately third-person and it avoids vague fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'computes SOV% = brand mentions ÷ (brand + competitor panel mentions) per platform per period', a 'sentiment-weighted SOV variant', a 'Wikipedia-pageviews attention-share alternative', and the panel-break restart rule — matching the anchor for listing several specific actions.

3 / 3

Completeness

Explicitly answers both what it does (computes SOV% and variants) and when to use it via an explicit 'Use when the user asks to...' clause, so it is not capped at 2.

3 / 3

Trigger Term Quality

Gives natural trigger phrases a user would say ('track our share of voice', 'what share of the conversation do we own vs competitors', 'trend our SOV this quarter') plus SOV and the Chinese 声量份额/提及份额/注意力份额 variants, covering common phrasings well.

3 / 3

Distinctiveness Conflict Risk

Owns a clear niche (locked-panel SOV) and explicitly redirects overlap with 'Not for backlink or offsite SEO signals — use offsite-signal-analyzer', making wrong-skill triggering unlikely.

3 / 3

Total

12

/

12

Passed

Validation

75%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 32 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

12

/

16

Passed

Repository
aaron-he-zhu/aaron-marketing-skills
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.