CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

reverse-engineer-marketing

When the user wants to know how another company grew and what to copy, or asks what a competitor did and when: a dated log of their moves against their traffic from public data, archives, job posts, reviews, and their funnel, compared with the user's data, ending in plays routed to other skills. Also finds where competitors are weak. For a snapshot profile, see competitor-profiling. For comparison pages, see competitors.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exemplary skill body: fully executable commands with exact thresholds and file schemas, a clearly sequenced nine-stage workflow with explicit pause/approval checkpoints and error-recovery guidance, and a well-organized one-level-deep reference bundle. The only inefficiency is mild duplication between "Before Starting" and "Task-Specific Questions" and the inline 31-row industry routing table.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence throughout — no general concepts (SEO, funnels, analytics) are explained — and commands/metrics are stated without padding. Minor trim opportunities remain: the "Task-Specific Questions" section largely restates items 1–7 of "Before Starting", and the 31-row inline industry table carries notable token weight. Between anchors 3 and 5, closer to 5.

4 / 5

Actionability

Copy-paste-ready commands with exact flags and outputs for every stage (site, stack, history, ads, detect, dns, hero, reviews, jobs, moves, diff, compare), explicit file schemas ("traffic.csv (month,visits,brand_searches)"), exact thresholds ("45+ days", "fewer than 24 settled posts", "18 months of data or 6 moves"), and a worked gap-table example with real numbers.

5 / 5

Workflow Clarity

Nine stages are explicitly sequenced with per-stage outputs, and checkpoints are explicit: "Pause between stages. Report what you found in three lines, what the next stage checks, and its cost. Continue, skip, or stop as the user prefers", approval gates and budget caps for paid calls and stage 3, a labeled evidence standard, a Common Mistakes error-recovery table, and a Watch-mode diff loop. No destructive or batch operations are involved, so no cap applies.

5 / 5

Progressive Disclosure

A clear overview with well-signaled, one-level-deep references: 11 method files and 29 industry packs are linked with descriptive context ("The rules, setup, and checklists are in references/go-inside.md"), all 40 referenced paths verified to exist, and no nested references inside the bundle files. Detail is appropriately split — stage summaries inline, full methods in references.

5 / 5

Total

19

/

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: explicit when-clauses with natural user phrasing, concrete multi-part capability statement, and active disambiguation against sibling skills. The only gap is a handful of missing natural trigger variants such as "marketing strategy" or "growth tactics".

DimensionReasoningScore

Specificity

Lists multiple concrete actions with comprehensive coverage: "a dated log of their moves against their traffic from public data, archives, job posts, reviews, and their funnel", "compared with the user's data", "ending in plays routed to other skills", and "Also finds where competitors are weak". Each action is specific to this skill's deliverables, not generic.

5 / 5

Completeness

Explicitly answers both: "When the user wants to know how another company grew and what to copy, or asks what a competitor did and when" (when, with concrete trigger phrases) and the dated-log-plus-plays pipeline (what). Also notes data sources and deliverables.

5 / 5

Trigger Term Quality

Good natural-phrase coverage — "how another company grew", "what to copy", "what a competitor did and when", with the company/competitor synonym pair — but a few natural terms users would say are missing (e.g., "marketing strategy", "growth tactics", "teardown"). Not clearly at the comprehensive-synonyms anchor 5, but above anchor 3's partial coverage.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (growth history over time) and actively disambiguates from siblings: "For a snapshot profile, see competitor-profiling. For comparison pages, see competitors." Trigger phrases ("how they grew", "what to copy") don't overlap with those skills' triggers.

5 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 31 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 31 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository

coreyhaines31/marketingskills

Path

skills/reverse-engineer-marketing/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.