organic-first-campaign
Grassroots-first campaign design for anyone being outspent — startups vs. incumbents, NGOs vs. corporate comms, movements vs. state-backed machines, solo brands vs. big-budget competitors. Ideates awareness, launch, fundraising, mobilization, community-build, counter-narrative, referral, founder-story, and coalition campaigns. Triggers on "campaign plan", "marketing strategy", "ad budget", "should I advertise", "paid vs organic", "launch plan", "grassroots", "low budget marketing", "NGO campaign", "outspent", "competitor has bigger budget", "how do I compete without money". Also trigger on any spend asymmetry, collapsing organic reach, rising CPAs, or a trust/credibility problem — even without the word "campaign". Nudge activation when the user debates buying ads, boosting posts, or hiring influencers; they are likely about to burn money on a channel that will not persuade.
87
85%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 strong, well-crafted skill description that clearly defines its niche (grassroots campaigns for budget-disadvantaged entities), lists specific campaign types it can generate, and provides extensive explicit trigger terms covering both direct keyword matches and situational triggers. The nudge activation clause adds a proactive dimension. Minor concern: the description is somewhat long and the editorial voice in the last sentence ('they are likely about to burn money') is slightly opinionated rather than purely descriptive, but this doesn't significantly detract from its effectiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Ideates awareness, launch, fundraising, mobilization, community-build, counter-narrative, referral, founder-story, and coalition campaigns.' Also specifies concrete domains like startups vs. incumbents, NGOs vs. corporate comms, movements vs. state-backed machines. | 3 / 3 |
Completeness | Clearly answers both 'what' (grassroots-first campaign design across multiple campaign types for outspent entities) and 'when' (explicit trigger phrases listed, plus situational triggers like spend asymmetry and trust/credibility problems, plus a nudge activation clause for ad-buying debates). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'campaign plan', 'marketing strategy', 'ad budget', 'should I advertise', 'paid vs organic', 'low budget marketing', 'how do I compete without money', 'competitor has bigger budget'. These are highly natural phrases. Also includes conceptual triggers like 'spend asymmetry' and 'rising CPAs'. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a very clear niche: grassroots/underdog campaign strategy specifically for budget-disadvantaged entities. The framing around being 'outspent' and the specific campaign types (counter-narrative, coalition, mobilization) make it highly distinct from generic marketing or advertising skills. The nudge activation clause further sharpens its identity. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is exceptionally well-structured with outstanding actionability, workflow clarity, and progressive disclosure — it provides a genuinely executable campaign-design framework with rigorous validation gates and clear decision points. However, it is severely over-length: the anti-fabrication rule is restated 4+ times, the core premise section over-justifies with academic citations Claude doesn't need inline, and many principles are repeated across the Principles section and the stage descriptions. Cutting 40-50% of the content while preserving the decision logic and stage structure would make this significantly more effective as a skill.
Suggestions
Consolidate the anti-fabrication rule into a single authoritative statement (e.g., in Principles) and reference it by name in stages rather than restating it in full in Stages 2, 4, and 5.
Move the 'Core Premise' empirical citations (Lewis & Rao, CPA/ROAS trends, platform engagement rates, EU ad ban, Hungarian case) to a reference file or compress to 2-3 bullet points — Claude doesn't need persuading, it needs the decision rules.
Deduplicate the Principles section against inline stage instructions — many principles (capacity constraint, MMF refusal, no broad cold-paid for categorical asymmetry) are already stated with full specificity in their respective stages.
Consider compressing the Mode A/B/C intake logic into a decision table rather than prose paragraphs — the current format takes ~800 tokens for what could be expressed in ~200.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~4,000+ words. It over-explains concepts Claude already understands (diminishing returns of advertising, what ROAS is, what platform attribution means), repeats the anti-fabrication rule at least 4 times across stages, and restates principles that could be compressed to a fraction of the length. The 'Core Premise' section alone spends hundreds of tokens on empirical justifications Claude doesn't need inline. | 1 / 3 |
Actionability | The skill provides highly concrete, executable guidance: specific stage-by-stage workflows, exact scoring thresholds (0-2/3 = refuse, 3-4 = proceed with flags), precise allocation ratios (70/30, 80/20), named output sections, capacity-constraint rules with explicit cut logic, and detailed templates for every deliverable component. The 8-field interview, MMF gate questions, and preconditions checklist are all immediately actionable. | 3 / 3 |
Workflow Clarity | The six-stage workflow (1, 2, 3, 3a, 4, 5) is clearly sequenced with explicit dependencies ('later stages depend on the user's answers from earlier ones'). Critical validation checkpoints are built in: the MMF Gate (Stage 3a) can refuse to proceed, the preconditions check gates full-scale execution, the 24-48h organic traction gate prevents premature boosting, and capacity constraints force plan revision. Error recovery and feedback loops are explicit throughout. | 3 / 3 |
Progressive Disclosure | The skill maintains a clear overview structure with well-signaled one-level-deep references to 7 separate reference files (campaign-archetypes.md, asymmetry-audit-table.md, channel-tier-stack.md, authenticity-playbook.md, lift-test-templates.md, sector-riders.md, hungarian-case-study.md). Detailed data tables and templates are appropriately externalized rather than inlined, and each reference is cited at the point of use with clear context for when to consult it. | 3 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (609 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- bencium/bencium-marketplace
- Commit
20077d3
- 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.