CtrlK
BlogDocsLog inGet started
Tessl Logo

apify-competitor-intelligence

Analyze competitor strategies, content, pricing, ads, and market positioning across Google Maps, Booking.com, Facebook, Instagram, YouTube, and TikTok.

75

3.10x
Quality

66%

Does it follow best practices?

Impact

90%

3.10x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/apify-competitor-intelligence/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 delivers a clear, well-sequenced workflow with mostly executable commands and useful error recovery, but its central script is missing from the bundle and the large actor table is inlined rather than split out. Tightening JSON_INPUT guidance and moving the catalog to a reference file would materially improve it.

Suggestions

Move the 28-row Actor selection table to a reference file (e.g., references/actors.md) and keep only a few representative examples inline in SKILL.md.

Add a concrete example showing how to translate the schema fetched in Step 2 into the JSON_INPUT string used in Step 4, since that handoff is currently implicit.

Include a verification checkpoint after Step 4 (e.g., check exported row count or preview the file) to close the feedback loop for batch scraping runs.

DimensionReasoningScore

Conciseness

Steps are lean with a terse error-handling table and no explanation of concepts Claude already knows, but there is minor fluff to trim — the odd parenthetical "(No need to check it upfront)" and the vague "Number of results: Based on character of use case".

4 / 5

Actionability

The mcpc schema-fetch command and the three node script invocations with format flags are concrete, but every run command depends on ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js, which is absent from the bundle, and no example shows how to build JSON_INPUT from the schema fetched in Step 2.

3 / 5

Workflow Clarity

A tracked 5-step checklist with a clear sequence and an error-handling section giving recovery actions for common failures, but there is no output verification step (e.g., checking row counts or inspecting the exported file) after batch scraping runs.

4 / 5

Progressive Disclosure

Sections are well organized, but the 28-row Actor catalog is bulk reference data inlined in SKILL.md that belongs in a separate file, and the only file reference (reference/scripts/run_actor.js) does not exist in the bundle.

3 / 5

Total

14

/

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 specific, third-person description with strong platform-level trigger terms and a distinct niche, but it omits any "when to use" guidance and misses a few natural keywords like reviews and benchmarking. Adding an explicit trigger clause would lift it to top-tier quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks for competitor analysis, benchmarking, or market research on any of these platforms."

Add commonly used keywords such as "reviews", "benchmarking", and "competitor scraping" to improve trigger-term coverage.

Mention the deliverable (structured data exports in CSV/JSON plus synthesized takeaways) so the "what" covers outputs, not just analysis types.

DimensionReasoningScore

Specificity

Lists several concrete analysis actions ("competitor strategies, content, pricing, ads, and market positioning") across six named platforms, but coverage has minor gaps — nothing about reviews, data export formats, or benchmarking outputs.

4 / 5

Completeness

The "what" is clear (analyze competitor strategies, content, pricing, ads, positioning), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Natural terms like "competitor", "pricing", "ads", "content", and all six platform names (Google Maps, Booking.com, Facebook, Instagram, YouTube, TikTok) are present; a few common user phrasings such as "reviews", "benchmarking", or "scraping" are missing.

4 / 5

Distinctiveness Conflict Risk

Competitor intelligence across six specifically named platforms is a clear niche with distinct triggers, making conflict with other skills unlikely.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
sickn33/agentic-awesome-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.