When the user wants to get press coverage, appear on podcasts, or build relationships with journalists and content creators. Also use when the user mentions "podcast guesting", "press outreach", "PR", "media exposure", "get on podcasts", or "journalist outreach".
75
70%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/earned-media-outreach/SKILL.mdQuality
Discovery
62%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description excels at defining when to use the skill with rich, natural trigger terms and a clear niche, but critically fails to explain what the skill actually does. Without any concrete actions or capabilities listed, Claude knows when to select it but users and Claude cannot understand what outputs or processes to expect. The description is essentially all 'when' and no 'what'.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Drafts personalized pitch emails, researches relevant journalists and podcast hosts, creates targeted media lists, and develops PR outreach strategies.'
Restructure to lead with capabilities before the 'Use when...' clause, following the pattern: '[What it does]. Use when [triggers].' For example: 'Creates PR outreach plans, drafts pitch emails to journalists and podcast hosts, and builds media contact lists. Use when...'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lacks concrete actions entirely. It describes situations/goals ('get press coverage', 'appear on podcasts', 'build relationships') but never states what the skill actually does — no specific capabilities like 'drafts pitch emails', 'researches journalists', or 'creates media lists' are mentioned. | 1 / 3 |
Completeness | The 'when' component is very strong with explicit trigger guidance and natural keywords. However, the 'what' component is essentially missing — the description never explains what concrete actions or outputs the skill produces, only the goals/contexts for using it. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'podcast guesting', 'press outreach', 'PR', 'media exposure', 'get on podcasts', 'journalist outreach', 'press coverage', 'podcasts', 'journalists'. These are terms users would naturally use when seeking this type of help. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche around PR, media outreach, and podcast guesting. The specific trigger terms like 'podcast guesting', 'press outreach', and 'journalist outreach' are distinct enough to avoid conflicts with other skills. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with a clear workflow and concrete output format. Its main weakness is length — it includes some generic PR advice that Claude likely already knows and could benefit from splitting detailed reference material into separate files. The workflow sequencing and specific tooling recommendations are strong points.
Suggestions
Move the 'Frameworks & Best Practices' and 'Common Mistakes' sections into a separate MEDIA-OUTREACH-REFERENCE.md file, keeping only a brief summary and link in the main skill.
Trim generic advice Claude already knows (e.g., 'tells stories not features', 'don't hard-sell') to focus on non-obvious, startup-specific guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some content Claude would already know (e.g., general advice like 'tells stories, not features', 'short pitches win', common mistakes that are obvious). The frameworks section could be tightened, and some best practices are generic PR advice rather than novel instruction. | 2 / 3 |
Actionability | The skill provides highly concrete guidance: specific search tools (ListenNotes, Podchaser, Rephonic), exact word counts for pitches (150/200 words max), specific follow-up cadences (5-7 days, 7-10 days), detailed output tables with column headers, and pitch template structures. The examples section shows clear input/output expectations. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced from defining angles through preparation for appearances. Each step has explicit sub-steps, the follow-up cadence includes a clear stopping rule ('move on after 3 touches'), and the tiering system provides a decision framework for prioritization. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections, but it's quite long and monolithic — the frameworks, best practices, and common mistakes sections could be split into a separate reference file. The related skills section provides good cross-references, but the main file tries to contain everything inline. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
4ad31b4
Table of Contents
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.