Write evidence backed profile
Skill jqaisystems/jqai-ai-skills/skills/write-evidence-backed-profile
Draft bios, applications, portfolio introductions, proposal introductions, cover notes, and professional profile copy from approved evidence without inventing experience or results. Use when a user wants personal or company positioning tailored to an audience, role, opportunity, directory, portfolio, proposal, or public profile and factual grounding matters.From its SKILL.md
npx -y skills add jqaisystems/jqai-ai-skills --skill write-evidence-backed-profileAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
3.0 KB, 513 tokens by cl100k_base, as published. Nobody here has run it
Write Evidence-Backed Profile
Create audience-specific profile writing from an approved evidence set. Prefer a smaller defensible story over a broad invented persona.
1. Define the writing task
- Confirm the audience, channel, prompt or field, word or character limit, desired action, and tone.
- Identify the claims the user expects the draft to communicate.
- Read references/channel-output-rules.md for the selected format.
- Preserve exact names, links, titles, dates, and wording supplied for the current task.
2. Build or inspect the evidence pack
- Use assets/evidence-pack-template.md when the user has not supplied a structured source set.
- Use public sources and user-approved facts only.
- Verify current pages when roles, availability, metrics, projects, credentials, services, or positioning may have changed.
- Treat inaccessible sources and unsupported user expectations as unverified.
- Do not embed a specific person's identity, CV, website, source registry, or voice guide in the skill.
3. Map evidence to the audience
For each important requested claim, record:
- the evidence that supports it
- whether it is direct experience, adjacent experience, interpretation, or unsupported
- why it matters to this audience
- the strongest wording the evidence permits
Do not infer job titles, customer relationships, years of experience, technical depth, revenue, performance, availability, awards, or credentials from weak signals.
4. Write the strongest honest version
- Lead with the most relevant supported overlap between the evidence and the audience's need.
- Present adjacent experience as adjacent, not direct expertise.
- Use concrete public work when it improves credibility.
- Omit unsupported claims instead of filling gaps with generic confidence.
- Avoid inflated certainty, unsupported superlatives, fabricated enthusiasm, and irrelevant capability lists.
- Match the requested format so the result is ready for human review and use.
5. Complete the evidence check
- Verify every name, title, date, link, metric, project description, and factual statement used.
- List requested claims that were qualified or omitted and explain the evidence gap briefly.
- Keep sensitive or user-approved non-public material out of reusable examples and public artifacts.
- Never submit a form, send a message, edit a public profile, or publish the draft.
Return the compact evidence map, finished draft, qualifications, omitted claims, sources checked, and any fact that still needs confirmation.
What ships with it: 3 files
2.7 KB alongside SKILL.md
agents/
- openai.yaml239 B
assets/
references/
- channel-output-rules.md1.4 KB