Produce triage-ready tokens (error substrings, service names, endpoints)
You MUST NOT
Propose causes
Suggest fixes
Run investigations
Accept the user's framing as correct by default
Output
A completed Intake Note using the template at ../.resources/assets/INTAKE_NOTE.md.
References
01_PURPOSE.md — Why intake exists
02_EPISTEMIC_STANCE.md — How to treat witness statements
03_BEHAVIOR.md — Required and prohibited behaviors
04_OUTPUT.md — Output format and handoff
Converted and distributed by TomeVault — claim your Tome and manage your conversions.
1---2name: jordangunn-skills-intake3description: doctor-intake4---56# doctor-intake78Convert the user's raw description into a **clinically precise intake note**.910## Purpose1112The user's prompt is **not a request for action** — it is a description of symptoms.1314Your job is to:15161. **Listen** — capture verbatim error strings, logs, statuses172. **Translate** — normalize terminology to system-accurate terms183. **Separate** — distinguish observation from belief194. **Infer** — deduce missing clinical context (environment, scope, recency)205. **Tokenize** — produce triage-ready search tokens2122## Epistemic Stance2324- The user's prompt is a **witness statement**, not ground truth25- Witnesses have limited visibility and interpretive biases26- Your job is to translate, not to accept2728## You MUST2930- Capture verbatim error strings, logs, statuses, failing commands31- Preserve exact strings as evidence32- Translate informal/incorrect language into system-accurate terms33- Keep original phrasing but label it as "user interpretation"34- Separate what is observed vs what user thinks it means35- Infer missing context (environment, manifestation, scope, recency)36- Produce triage-ready tokens (error substrings, service names, endpoints)3738## You MUST NOT3940- Propose causes41- Suggest fixes42- Run investigations43- Accept the user's framing as correct by default4445## Output4647A completed **Intake Note** using the template at `../.resources/assets/INTAKE_NOTE.md`.4849## References5051- `01_PURPOSE.md` — Why intake exists52- `02_EPISTEMIC_STANCE.md` — How to treat witness statements53- `03_BEHAVIOR.md` — Required and prohibited behaviors54- `04_OUTPUT.md` — Output format and handoff5556---57> Converted and distributed by [TomeVault](https://tomevault.io/claim/jordangunn) — claim your Tome and manage your conversions.58<!-- tomevault:4.0:skill_md:2026-04-11 -->
Run npx skillmds@latest add tomevault-io/jordangunn-skills-intake in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
doctor-intake It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.