CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

competitor-tracker

Use when the user asks to "track competitor influencer marketing", "see who my rivals partner with", or "benchmark my influencer program"; produces a competitor partnership roster, campaign and content-strategy breakdown, performance estimates, and a gap/opportunity list. Not for finding your own new creators — use influencer-discovery. 竞品达人合作追踪/竞品营销分析

Quality

90%

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

88%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.

A well-structured, highly actionable body: sequenced steps with evidence gates and copy-paste connector commands, backed by a real one-level-deep templates file whose anchors all resolve. Minor deductions for repeated evidence-policy statements and for reference links that do not resolve within the provided bundle.

DimensionReasoningScore

Conciseness

The body is dense and skill-specific with no re-teaching of concepts Claude already knows, and includes concrete commands rather than padding. It is not level 5 because the dated-evidence/NEEDS_INPUT rule is repeated roughly four times (Skill Contract, Data Sources, Instructions steps 2 and 5, Worked Example) and the 60-word "Promotes" bullet could be trimmed.

4 / 5

Actionability

Guidance is fully executable: copy-paste commands with arguments (gdelt.py '"<competitor>"' --days 30, youtube.py channel <partner-handle>, the keyless YouTube RSS URL into rss_monitor.py), eight steps each anchored to a fill-in template in references/templates.md, and a worked example showing the exact expected output. It is not level 4 because no step relies on vague direction — every step names its output artifact or command.

5 / 5

Workflow Clarity

The eight steps are clearly sequenced with explicit validation gates (step 2's dated-evidence requirement, step 5's declared-formula requirement), a NEEDS_INPUT-with-collection-plan feedback loop, and a three-item done-when checklist. This matches the top anchor's 'explicit validation steps; feedback loops; checklists' better than level 4's 'minor validation gaps'.

5 / 5

Progressive Disclosure

The SKILL.md is a genuine overview with one-level-deep, clearly signaled references — references/templates.md exists and every anchor link in the Instructions section resolves to a real header. It is not level 5 because most links in Reference Materials point outside the provided bundle (../../../references/skill-contract.md, ../../../CONNECTORS.md, sibling scout/campaign-planner skills) and the connector scripts under ${CLAUDE_PLUGIN_ROOT}/scripts/ are not included, so navigation is incomplete as bundled.

4 / 5

Total

18

/

20

Passed

Description

92%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 strong description: concrete deliverables, explicit third-person 'Use when…' triggers with natural phrasings, and a clear exclusion clause that separates it from sibling influencer skills. The only gap is a handful of missing natural trigger synonyms (e.g., 'competitive analysis', 'who partners with…').

DimensionReasoningScore

Specificity

The description lists multiple concrete deliverables — "competitor partnership roster, campaign and content-strategy breakdown, performance estimates, and a gap/opportunity list" — giving comprehensive, specific coverage of what the skill produces. It is not level 4 because no meaningful capability is left unspecified for this domain.

5 / 5

Completeness

Both halves are explicit: an "Use when the user asks to…" clause with concrete trigger phrases answers 'when', and the enumerated deliverables answer 'what', matching the top anchor. It even adds an explicit exclusion ("Not for finding your own new creators — use influencer-discovery"), which goes beyond the level-4 anchor's 'when could be more specific'.

5 / 5

Trigger Term Quality

It quotes natural user phrasings ("track competitor influencer marketing", "see who my rivals partner with", "benchmark my influencer program") plus Chinese synonyms, so keywords are good. It stays at 4 rather than 5 because common variations like "competitive analysis", "rival creators", or "who partners with [brand]" phrasings are missing.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (competitor-side influencer tracking) and explicitly disambiguates against the closest rival skill ("Not for finding your own new creators — use influencer-discovery"), so mis-trigger risk is minimal. It is not level 4 since the boundary is stated rather than merely implied by topic.

5 / 5

Total

19

/

20

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.

Validation — 12 / 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: 14 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 missing, 1 deeper-than-1-level

Warning

Total

12

/

16

Passed

Repository

aaron-he-zhu/aaron-marketing-skills

Path

influencer/target/competitor-tracker/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.