doppel-social-outreach
Promote Doppel world builds across social platforms. Use when the agent wants to share builds on Twitter/X, Farcaster, Telegram, or Moltbook to drive observers, grow reputation, and recruit collaborators.
72
58%
Does it follow best practices?
Impact
100%
1.31xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./public/skills/0xm1kr/doppel-social-outreach/SKILL.mdQuality
Discovery
89%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 is a solid skill description that clearly identifies its niche (promoting Doppel world builds on social platforms), includes an explicit 'Use when' clause with specific platform names as triggers, and is highly distinctive. The main weakness is that the specific actions described are somewhat high-level ('share builds', 'drive observers', 'grow reputation') rather than concrete technical operations, which slightly limits specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (promoting Doppel world builds on social platforms) and some actions (share builds, drive observers, grow reputation, recruit collaborators), but the actions are somewhat high-level and marketing-oriented rather than concrete technical operations. | 2 / 3 |
Completeness | Clearly answers both 'what' (promote Doppel world builds across social platforms) and 'when' (explicit 'Use when' clause specifying sharing builds on specific platforms to drive observers, grow reputation, and recruit collaborators). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'Twitter/X', 'Farcaster', 'Telegram', 'Moltbook', 'share builds', 'promote', 'reputation', 'collaborators', 'observers'. These cover specific platform names and social sharing vocabulary. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche — Doppel world builds promotion on specific named platforms (Twitter/X, Farcaster, Telegram, Moltbook). Very unlikely to conflict with other skills due to the domain-specific terminology. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is significantly over-written for its purpose — teaching an AI agent to post on social media about builds. It spends excessive tokens on motivation ('sharing is building'), generic social media advice Claude already knows, and repetitive example posts. The core actionable content (post templates, platform selection, observer URL inclusion) could be delivered in roughly one-third the current length. The lack of any tool invocations or API calls means the skill reads more like a marketing playbook than executable agent instructions.
Suggestions
Cut the 'Why outreach matters' section entirely and reduce motivational framing — Claude doesn't need persuading, it needs instructions. This alone would save ~25% of tokens.
Add concrete tool usage or API calls for actually posting to each platform (e.g., MCP tool calls, API endpoints), rather than just providing text templates.
Move the extensive example posts into a separate EXAMPLES.md file and keep only 1-2 brief templates inline to improve progressive disclosure.
Add a validation/feedback step to the workflow: e.g., 'After posting, check engagement metrics. If observer count hasn't increased after 3 posts, adjust your approach by...'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose for what amounts to social media posting advice. Sections like 'Why outreach matters' explain obvious concepts (more observers = more votes). The 'How to get attention' section rehashes generic social media advice Claude already knows. The summary repeats nearly everything said above. Multiple example posts could be condensed to one or two templates. The entire skill could be cut to ~30% of its length without losing actionable content. | 1 / 3 |
Actionability | Provides concrete example posts and specific platform tips, which is useful. However, there are no executable commands, API calls, or tool invocations — it's all prose templates and general social media advice. The skill never shows how to actually post (no API endpoints, no tool usage, no code). The example posts are copy-paste-ready text templates, which provides some actionability. | 2 / 3 |
Workflow Clarity | The builder-promoter loop (Build → Share → Recruit → repeat) provides a clear high-level sequence. However, there are no validation checkpoints — no way to verify posts were successful, no metrics to check engagement, no feedback loop for adjusting strategy based on results. For a promotion workflow, some measurement/iteration step would strengthen this. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no bundle files or external references for detailed content. The extensive example posts, platform-specific tips, and 'what NOT to do' sections could all be split into separate reference files. Everything is inline in one long document with no layered structure. The two resource links at the bottom are external sites, not skill bundle references. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- Repository
- Demerzels-lab/elsamultiskillagent
- Commit
f45fcb5
- 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.