champion-identifier — Claude Code skill: find your internal champion
Reads LinkedIn profiles inside a target account and points to the person most likely to push your product from within. Useful before cold outreach into a large account.
npx skills add OneWave-AI/claude-skills --skill champion-identifier -a claude-codeWhat champion-identifier does
The skill takes a company, the solution you sell and any contacts you already know, then studies the department and leadership chain the solution touches. It gathers 5-10 candidates on LinkedIn and scores each one across six dimensions, 0 to 10 apiece, 60 total. Every score needs concrete evidence behind it, not a gut feeling.
Candidates are then ranked best to worst. Anyone who looks like a blocker or a coach rather than a champion gets flagged separately. For the top names the skill picks an outreach path, warm intro or direct message, and drafts the message with personalization hooks tied to that person.
Seven reference files ship with it: a scoring framework, an output template, outreach templates, meeting-prep questions, a multi-threading plan, a champion development plan and a playbook. The report comes out with every field filled from research, no placeholders. No LinkedIn access or gathered contacts means nothing to analyze — the inputs come first.
What it helps with
- find the person inside an account who wants your solution
- score candidates on one scale instead of guessing
- spot a blocker before the first meeting
- draft an outreach message with hooks for a specific person
- map the buying committee and plan coverage
Example prompts for the agent
- Analyze the LinkedIn profiles in this company's marketing department and find the champion
- Score these five people and tell me who is a blocker
- Build the DMU map and draft a warm-intro message
How to install champion-identifier
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill champion-identifier -a claude-code2Manually: put the files in place
~/.claude/skills/champion-identifier/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/champion-identifier/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill champion-identifier -a codex2Manually: put the files in place
.agents/skills/champion-identifier/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill champion-identifier -a cursor2Manually: put the files in place
.cursor/skills/champion-identifier/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install OneWave-AI/claude-skills champion-identifier2Manually: put the files in place
.github/skills/champion-identifier/SKILL.md1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill champion-identifier -a gemini-cli2Platform CLI
gemini skills install https://github.com/OneWave-AI/claude-skills --path champion-identifierManually: put the files in place
.devin/skills/champion-identifier/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill champion-identifier -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about champion-identifier
How do I install champion-identifier in Claude?
Run npx skills add OneWave-AI/claude-skills --skill champion-identifier -a claude-code. The skill file then sits at ~/.claude/skills/champion-identifier/SKILL.md.
What does champion-identifier do?
It analyzes LinkedIn profiles in a target account, scores candidates across six dimensions and suggests a personalization approach. You get a ranked report with draft messages.
Do I need LinkedIn access?
The skill works on the profiles and contacts you hand it. With no gathered data about people at the company there is nothing to analyze.
Source text
SKILL.md · MIT
--- name: champion-identifier description: Analyze LinkedIn profiles in target accounts to identify potential internal champions. Evaluates role, career path, mutual connections, interests, and suggests personalization approach. Use when you need to find who will champion your solution internally. --- # Champion Identifier Find the internal champion most likely to advocate for the solution at a target account, using structured LinkedIn and account analysis. ## Contents - references/scoring-framework.md - champion profile, six scoring dimensions, total-score bands, warning signs - references/output-template.md - the full Markdown report structure to produce - references/outreach-templates.md - warm-intro, forwardable, direct, and opening-line messages - references/meeting-prep.md - discovery and qualification questions, red flags - references/multi-threading.md - sequence, coverage map, DMU table, org-chart format - references/champion-development-plan.md - five-phase plan with success metrics - references/playbook.md - tips, best practices, trigger phrases, worked example ## Workflow 1. Gather inputs: the company, the solution being sold, and any known contacts or mutual connections. Ask for whatever is missing. 2. Research the company and the department the solution touches: stage, recent news, likely pain points, decision-making style, and hiring signals. 3. Identify 5-10 candidate individuals on LinkedIn within the relevant department and leadership chain. 4. Score each candidate across the six dimensions (0-10 each, 0-60 total) per references/scoring-framework.md, citing concrete evidence for every score. 5. Rank candidates best to worst, and flag anyone who is a blocker or coach rather than a champion using the warning signs. 6. For the top candidates, choose an outreach path (warm intro vs. direct) and draft the message from references/outreach-templates.md, plus personalization hooks and meeting prep from references/meeting-prep.md. 7. Build the multi-threading plan and account map (DMU table, org chart) per references/multi-threading.md. 8. Assemble the full report following references/output-template.md, filling every field with researched specifics and no placeholders. 9. Recommend next steps using the phased plan in references/champion-development-plan.md.
© OneWave-AI · MIT · OneWave-AI/claude-skills
