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

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%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, action-oriented skill body with strong sequencing, explicit validation checkpoints, and clean progressive disclosure into a real templates bundle. The main leverage is tightening the authorization/contract prose and pushing a touch more concrete detail into the step lines themselves.

Suggestions

Tighten the Skill Contract "Promotes" bullet: move the registry-events.py / exact-authorization mechanics into the referenced skill-contract.md and keep only the rule in SKILL.md.

Add one concrete hint per step line (e.g., the key field or output shape) so the 8 steps are executable without always opening templates.md.

Dimension	Reasoning	Score
Conciseness	Mostly lean instructional prose that earns its place (commands, contract terms Claude would not know), though the Skill Contract "Promotes" bullet and authorization machinery are somewhat dense and could be trimmed.	4 / 5
Actionability	Provides copy-paste commands (gdelt.py, YouTube RSS URL) and `~~` connector placeholders, with each of the 8 steps linking to a fill-in template; the step headings themselves stay high-level, deferring concrete detail one level into templates.	4 / 5
Workflow Clarity	Eight clearly sequenced steps with explicit validation gates (NEEDS_INPUT return with collection plan, "Done when" checklist, per-action exact authorization) and a worked example demonstrating the NEEDS_INPUT feedback loop.	5 / 5
Progressive Disclosure	SKILL.md is a well-organized overview with one-level-deep references (templates.md for all steps, plus skill-contract/state-model/CONNECTORS), each clearly signaled and described in a Reference Materials section; the bundle file templates.md exists and is real.	5 / 5
	Total	18 / 20 Passed

Description

87%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 that clearly states purpose, trigger conditions, and scope boundaries with natural phrasing and an explicit disambiguation against a sibling skill. Minor room to tighten output framing and broaden trigger synonym coverage.

Suggestions

Reframe deliverables as distinct verbs (e.g., "Build a competitor partnership roster, break down campaigns..., estimate performance, rank gaps") to lift specificity from outputs to actions.

Add one or two more natural trigger variations a user might say (e.g., "who are my competitors sponsoring", "competitor influencer analysis") to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete deliverables ("competitor partnership roster, campaign and content-strategy breakdown, performance estimates, and a gap/opportunity list"), but they are framed as outputs of a single verb "produces" rather than distinct actions, leaving a minor coverage gap.	4 / 5
Completeness	Explicitly answers both what (the four deliverables produced) and when ("Use when the user asks to..."), with concrete trigger phrases and an explicit non-use boundary.	5 / 5
Trigger Term Quality	Three natural trigger phrasings ("track competitor influencer marketing", "see who my rivals partner with", "benchmark my influencer program") with synonyms, but a few common variations a user might say are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche (competitor influencer tracking) with an explicit "Not for finding your own new creators — use influencer-discovery" boundary, minimizing conflict with sibling skills.	5 / 5
	Total	18 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Commit: 888dd38

Reviewed: 3 days ago

Table of Contents

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.