Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when the user asks to "create an influencer brief" or "write a campaign brief"; produces a structured creator brief with deliverables, key messages, creative direction, timeline, disclosure rules, and compensation terms. Not for choosing how to split spend across creators — use budget-optimizer.
.claude/skills/aiskillstore-brief-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 32% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 177% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 126% | 0% |
This skill helps you create clear, comprehensive influencer briefs that set creators up for success. Good briefs lead to better content, fewer revisions, and stronger partnerships.
Shortest invocation:
Create an influencer brief for [campaign]Common scenario:
Generate a TikTok brief for micro-influencers promoting [product], 1 review video, with disclosure and timelinememory/projections/narrative.json, memory/projections/claims.json, and relevant creator/channel projections; HOT is only an index to those sources.memory/influencer/brief-generator/YYYY-MM-DD-<topic>.md; unresolved claims become authorized claims proposals.> Emit the standard shape from skill-contract.md §Handoff Summary Format, including the Narrative/claims dependency tuple.
Required fields: narrative_canon_id, narrative_canon_version, claims_projection_offset, and dependency_status: verified | approved-fallback | blocked.
This family has no live integrations required (Tier 1). The skill works end to end by asking the user for inputs: campaign details, deliverables, key messages, timeline, and compensation. Provide those in the prompt and you get a complete brief with zero setup.
Optional connectors that can enrich a brief when available:
~~influencer database — pull creator handles, audience size, and past collaboration notes to personalize the "Why You" section.~~social platform analytics — confirm current format specs and best-performing post lengths per platform.~~CRM — fetch the assigned point of contact and prior brief versions for an ambassador.Read accepted Narrative and claims projections before drafting. Claim approval is contextual: audience, market, media, offer window, and required disclaimer must match. No usable canon permits only an explicitly approved exploratory brief, never a creator-ready/on-canon label.
See CONNECTORS.md for the verified free/keyless recipe per category. None are required.
When a user requests a brief:
[needs source], submit it through registry-events.py as an authorized operation: propose event, and prevent creator-ready status until resolved.Disclosure and usage rights must be stated explicitly — never leave them as placeholders once the user has given input. Briefs are guidelines, not scripts: respect the creator's voice while pinning the key messages and compliance terms.
User: "Create a brief for micro-influencers to promote our new organic protein powder on Instagram and TikTok"
Output: Complete brief — messaging around organic ingredients and clean label, deliverables of 1 IG Reel + 1 TikTok video with platform specs, creative direction for "morning routine" / "workout fuel" angles, timeline with draft + go-live dates, #ad disclosure at caption start, and 12-month repost/paid usage rights. Saved to memory/influencer/brief-generator/.
Termination note: Maintain a visited-set. If a recommended skill was already invoked this session, stop and report chain-complete instead of re-running it. Cap any handoff chain at max-depth 3.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 32,070 | 16,143 | -50% | 1 | 1 | 0% | 5,101 | 4,137 | -19% | 0 | 0 | — |
case-02 | fail→pass | 22,140 | 18,627 | -16% | 1 | 1 | 0% | 3,354 | 4,413 | +32% | 0 | 0 | — |
case-03 | fail→pass | 22,165 | 17,153 | -23% | 1 | 1 | 0% | 3,335 | 4,138 | +24% | 0 | 0 | — |
case-04 | fail→fail | 7,667 | 14,526 | +89% | 1 | 1 | 0% | 1,082 | 3,811 | +252% | 0 | 0 | — |
case-05 | fail→fail | 18,523 | 20,902 | +13% | 1 | 1 | 0% | 2,976 | 5,071 | +70% | 0 | 0 | — |
case-06 | fail→fail | 18,265 | 16,627 | -9% | 1 | 1 | 0% | 3,045 | 4,190 | +38% | 0 | 0 | — |
case-07 | fail→pass | 8,549 | 13,194 | +54% | 1 | 1 | 0% | 1,334 | 3,701 | +177% | 0 | 0 | — |
case-08 | fail→pass | 10,576 | 12,693 | +20% | 1 | 1 | 0% | 1,588 | 3,595 | +126% | 0 | 0 | — |
case-09 | fail→pass | 13,443 | 9,903 | -26% | 1 | 1 | 0% | 2,158 | 3,203 | +48% | 0 | 0 | — |
case-10 | fail→pass | 10,042 | 5,611 | -44% | 1 | 1 | 0% | 1,474 | 2,421 | +64% | 0 | 0 | — |
case-11 | pass→pass | 8,967 | 3,465 | -61% | 1 | 1 | 0% | 1,351 | 2,004 | +48% | 0 | 0 | — |
case-12 | pass→pass | 10,520 | 13,298 | +26% | 1 | 1 | 0% | 1,701 | 3,690 | +117% | 0 | 0 | — |
case-13 | pass→pass | 12,713 | 9,650 | -24% | 1 | 1 | 0% | 1,830 | 2,961 | +62% | 0 | 0 | — |
case-14 | pass→pass | 18,181 | 17,226 | -5% | 1 | 1 | 0% | 2,575 | 4,043 | +57% | 0 | 0 | — |
case-15 | pass→pass | 12,102 | 16,715 | +38% | 1 | 1 | 0% | 1,832 | 4,091 | +123% | 0 | 0 | — |
case-16 | pass→pass | 16,577 | 12,679 | -24% | 1 | 1 | 0% | 2,349 | 3,398 | +45% | 0 | 0 | — |
case-17 | pass→pass | 16,071 | 13,439 | -16% | 1 | 1 | 0% | 2,439 | 3,472 | +42% | 0 | 0 | — |
case-18 | fail→pass | 9,465 | 2,654 | -72% | 1 | 1 | 0% | 1,508 | 1,923 | +28% | 0 | 0 | — |
case-19 | fail→pass | 11,911 | 6,960 | -42% | 1 | 1 | 0% | 1,927 | 2,719 | +41% | 0 | 0 | — |
case-20 | fail→pass | 6,893 | 3,379 | -51% | 1 | 1 | 0% | 1,092 | 2,074 | +90% | 0 | 0 | — |
case-21 | pass→pass | 17,030 | 12,498 | -27% | 1 | 1 | 0% | 2,606 | 3,474 | +33% | 0 | 0 | — |
case-22 | pass→pass | 15,487 | 7,095 | -54% | 1 | 1 | 0% | 2,277 | 2,681 | +18% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.