influencer-discovery
Use when the user asks to "find influencers", "build an influencer list", or "discover creators in [niche]"; produces a multi-platform candidate pool, per-influencer evidence profiles, authenticity red-flag screening, and a Fit-readiness queue without action ranking.
Install / Use
npx skills add aaron-he-zhu/aaron-marketing-skills --skill influencer-discoveryInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of influencer-discovery
influencer-discovery scores 93/100 on our quality scale, 679th of 4,700 Development & Engineering skills we index (top 15%).
Its SKILL.md is 16 KB long, well organised into 10 sections with 2 code examples: a thorough specification that gives an agent plenty to work with.
With 2,835 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so influencer-discovery is actively maintained.
- Our last check on 2026-10-26 found the source still online.
- It is released under the Apache-2.0 license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-09-30. Automated pattern scan on 2026-09-29. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
influencer-discovery compared with similar skills
All 4 of these similar skills score higher than influencer-discovery; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| influencer-discovery (this skill)by aaron-he-zhu | 93 | 2.8k | 53d ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 116.8k | 8d ago | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 72.1k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 47.3k | 2d ago | CLAUDE.md |
| lobehubby lobehub | 100 | 85.6k | today | MCP Server |
Frequently asked questions
- How do I install influencer-discovery?
- Run
npx skills add aaron-he-zhu/aaron-marketing-skills --skill influencer-discovery. The install tabs above show the steps for each supported agent. - Which AI agents does influencer-discovery work with?
- It is written for Claude Code, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is influencer-discovery safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is Apache-2.0-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is influencer-discovery still maintained?
- The repository was last updated about 2 months ago, so influencer-discovery is actively maintained.
Skill content
View source on GitHubname: influencer-discovery slug: influencer-discovery displayName: "Influencer Discovery · 红人发现" summary: "多平台红人挖掘:候选池、证据画像、真实性红旗筛查与 Fit 就绪队列" description: 'Use when the user asks to "find influencers", "build an influencer list", or "discover creators in [niche]"; produces a multi-platform candidate pool, per-influencer evidence profiles, authenticity red-flag screening, and a Fit-readiness queue without action ranking. Not for STAR scoring or ranking a known shortlist — use fit-scorer. 达人挖掘/找达人/创作者名单' version: "20.1.0" license: Apache-2.0 compatibility: "Claude Code and compatible agent-skill hosts" homepage: "https://github.com/aaron-he-zhu/aaron-marketing-skills" when_to_use: "Activate when building an influencer roster from scratch, expanding into a new platform or niche, replacing churned partners, finding micro and nano creators at scale, identifying which influencers a competitor partners with, or standing up an always-on discovery pipeline. The user names a niche, platform, follower band, or brand and wants a list of candidate creators to evaluate." argument-hint: "<brand or niche> [platform] [follower-range]" metadata: {"author": "aaron-he-zhu", "version": "20.1.0", "discipline": "influencer", "phase": "scout", "geo-relevance": "low", "hermes": {"tags": ["marketing", "influencer", "scout"], "category": "influencer"}, "openclaw": {"emoji": "📣", "homepage": "https://github.com/aaron-he-zhu/aaron-marketing-skills"}}
Influencer Discovery
Find evidence-backed creator candidates across platforms, screen them against declared discovery filters, and build a non-ranked readiness queue for typed Fit evaluation.
Quick Start
Find 20 influencers in [niche] for [brand/product]
Find influencers in [niche] with 50K-200K followers on TikTok and Instagram,
based in [location], engagement above 4%, who have worked with brands like [brand]
Skill Contract
- Reads: brand/product, niche or category, target platforms, follower range, engagement floor, decision-relevant geography/language, audience demographics, exclusions; dated candidate records from a user export, public source, roster, or live connector; the current campaign's STAR
evidence_windowwhen supplied; priorentity-registrybrand profile and anyaudience-mapperoutput if present in memory; existing roster records undermemory/creators/(dedupe only through verified identity links against creators already rostered by creator-registry). - Writes: return discovery results inline by default; only with separate exact authorization, save them to
memory/influencer/influencer-discovery/YYYY-MM-DD-<topic>.md. A saved artifact uses a stable opaquecreator_refplus pseudonymousrecipient_ref,contact_source_ref, andagency_ref, keeps raw handles, profile URLs, and contact coordinates transient-only, and retains geography only at the granularity required by the declared filter. Save an opaquehandle_ref/source_refidentity resolver only when the authorized source artifact or verified creator-registry link can resolve it. Without one, keepidentity_status: unresolved, save no hidden raw-locator mapping, and setcross_session_locator_required: true. Reuse a verified creator-registry aggregate ID when one exists; otherwise generatecreator-<UUIDv4>once for the candidate lineage. Never setcreator_refto a raw handle, name, URL, email, provider ID, or a deterministic hash of any of them. Each roster-worthy creator update requires another exact authorization for anoperation: proposerequest throughregistry-events.pytomemory/events/creators.ndjson; onlycreator-registrywrites canonical records undermemory/creators/. - Promotes: only with separate exact authorization, durable facts (verified creator/handle refs, confirmed niche/platform coverage, competitor-saturated creators) to
memory/hot-cache.md; discovery readiness or queue position is not a durable ranking fact. - Done when:
- The required search criteria are present; otherwise stop with
NEEDS_INPUTand name the missing criteria without fabricating candidates. - Exactly two raw locators without complete criteria/evidence remain
NEEDS_INPUT, not a vetted shortlist. A separately authorized partial checkpoint is labeledPARTIAL, lists every gap, and contains no tier or rank. - A candidate pool exists with at least the requested count screened past follower, engagement, and brand-safety filters.
- Each candidate has a field-level evidence trail (
provider/tool,source_ref,observed_at, window, evidence label), an audience read, and an evidence-completeness triage state (READY_FOR_FIT | NEEDS_REFRESH | INELIGIBLE) that is neither a score nor a STAR Suitability verdict. - Every candidate keeps one stable opaque
creator_refacross the report and handoff; raw identity locators remain transient and are never copied intocreator_ref. - Conflicting observations remain separate, identity merges have a verified cross-link, and the Fit handoff marks each volatile field
current,stale, orunknownagainst the current STARevidence_windowwith anyrefresh_requiredfields named. - A non-ranked Fit-readiness queue is compiled with next-step pointers; every stale/unknown required field produces
NEEDS_REFRESH,NOT_RANKED, andNEEDS_INPUTuntil refreshed.
- The required search criteria are present; otherwise stop with
- Primary next skill: fit-scorer — score and rank the discovered candidates with weighted criteria.
Handoff Summary
Emit the standard shape from skill-contract.md §Handoff Summary Format.
Data Sources
Planning and screening need no live integration (Tier 1), but a real creator list still needs candidate records: public handles/links or an export supplied by the user, existing roster records, or a live search connector. Search criteria alone are not evidence that any specific creator or metric exists. If no candidate source is available, return a query/collection plan and NEEDS_INPUT; never invent handles, profiles, counts, or audience data.
Normalize evidence only in the report template, not through a new ingestion layer. For every factual field retain provider/tool, source_ref, observed_at, the measurement window (or not-supplied), and one label: Measured, Calculated, Estimated, User-provided, or Proxy. Keep conflicting values for the same field as parallel observations; do not average them, prefer the newest automatically, or merge identities from names/handles alone. A cross-provider identity becomes one creator only after a verified cross-link or explicit user confirmation.
Where a tool could sharpen results, use ~~ connector placeholders:
~~influencer database— bulk discovery, follower/engagement metrics, audience demographics.~~social platform analytics— native creator-marketplace data, trending sounds, related accounts.~~CRM— surface possible existing-partner matches for verified identity-link review; never auto-merge records.~~audience overlap— estimate creator-audience vs. brand-audience match.
Keyless candidate-card metadata (oEmbed): YouTube (https://www.youtube.com/oembed?url=<video-url>&format=json), TikTok (https://www.tiktok.com/oembed?url=<post-url>), and X (https://publish.twitter.com/oembed?url=<post-url>) return a post's title, author name/handle, and thumbnail with no key — enough to resolve a candidate transiently and retain an opaque verified-handle evidence ref instead of hand-copying identity data. A handle ref remains separate from creator_ref: only an explicitly carried upstream creator_ref or a verified creator-registry identity link may resolve the aggregate; otherwise create a fresh random opaque ref and preserve the identity gap. Metadata only: no follower or engagement metrics, so those stay ~~influencer database or manual export — except YouTube, below.
Measured YouTube metrics (free key): python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/youtube.py" channel @handle returns the real displayed subscriber count, total views, and video count, and youtube.py videos @handle --limit 10 adds per-video views/likes/comments — upgrading a YouTube candidate's profile row from Estimated to Measured. Free YOUTUBE_API_KEY (10,000 units/day; one channel check ≈ 1–3 units). ToS boundary: vet a named shortlist, don't build a bulk creator database — quota extensions are refused for competitive harvesting. See scripts/connectors/README.md.
See CONNECTORS.md for the free/keyless recipe per category and the opt-in MCP layer. None are required — every step degrades to user-supplied inputs.
Instructions
Each step has a fill-in block in references/templates.md — copy the matching block. This skill does not compute a per-influencer score, STAR Suitability verdict, outreach priority, or action rank. It records evidence completeness and declared-filter results; fit-scorer owns typed comparison and ranking downstream.
- Define search criteria. Capture brand, goal, audience definition, budget/follower tier, platforms, engagement floor, location/language, exclusions, and the required/preferred parameter table. If any required criterion is missing, stop with
NEEDS_INPUT; offer audience-mapper only when the user wants help defining the audience. Step 1 template. - Conduct the search. Work hashtags, similar-accounts, competitor mentions, and platform-native discovery. Raw handles/profile URLs may appear only in Step 2's transient lookup block and must be removed before any save or handoff. Log the saved-safe batch with
creator_ref, identity status, opaquehandle_ref/source_refwhen resolvable, provider/tool, query purpose,observed_at, window, and evidence label. If no public handles/links, user export, roster records, or live search connector can supply candidate records, produce the exact query pack and collection template, returnNEEDS_INPUT, and stop before naming creators. Step 2 template. - Initial screening. Filter the pool on follower range, engagement, recency, relevance, and brand safety; tally red flags (suspected fake followers, controversy, competitor exclusivity, inactivity). These are discovery signals, not verified STAR failures or vetoes; unsupported applicable evidence remains Unknown for downstream scoring. Per-platform reading cues: references/platform-vetting.md. Step 3 template.
- Build influencer profiles. For each qualified creator, first reuse an explicitly carried opaque
creator_refor a creator-registry aggregate ID whose handle link is verified. If neither exists, generate one randomcreator-<UUIDv4>and reuse it unchanged throughout this report lineage. Never derive it from a handle or other identity data. Save an opaque handle/evidence ref only when an authorized artifact or verified registry link resolves it; otherwise keepidentity_status: unresolved, create no hidden locator map, and require the raw locator again in a later session. Then fill the profile (pseudonymous identity refs, field-level metrics and audience evidence, content, partnership history, contact-path refs, and evidence-completeness triage state). Preserve conflicts as parallel rows and merge provider identities only after a verified cross-link. Compare each volatile observation with the current campaign's STARevidence_window: within it iscurrent; outside it isstale; a missing window/date or absent STAR window isunknown. A stale or unknown required field stays visible, becomesrefresh_required, and forcestriage_state: NEEDS_REFRESH,ranking_status: NOT_RANKED, andNEEDS_INPUT; never invent a global TTL. Do not emit a score, recommendation
Truncated for display — read the full file on GitHub.
Related Skills
taste-skill
116.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
72.1kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
47.3kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
lobehub
85.6k🤯 LobeHub - Super-Agents on Your Team. Add super-agents to the chats your team already uses.They take on work by themselves and get better every week.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
