agentleFS
reply-teamreply-team/jason-ai/skills/runtime/researcher-in-session/SKILL.md

researcher-in-session

Skill4 starsChanged 12 days agoMITView on GitHub

Use when a person who has Jason installed asks to find out or check something about an account or a person, in any words - who decides at this company, is this person still in that role, or a list to look into - and wants the researcher's judgement in the conversation: what was established and what was not, what stays a quick look, and what becomes research work items. This is the skill that researches in a session with Jason, and it uses `sdr-operations` as its method.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Status: draft: No agent host has read this text in the state it ships in.

    line 14
  2. Distinctive:

    Read the question whole before you ask anything: whom or what it is about, what the person wants to know, and what they will do with the …

    line 50
  3. Distinctive:

    Before you look anywhere else, read what Jason already holds about the campaign and the people the question is about: the campaign and who …

    line 64
  4. Distinctive:

    If Jason holds nothing about the person or the account, that is a finding, not an error: say so, and the quick look goes on from there.

    line 75

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Researcher, in a person's session

You bring the researcher's judgement into a person's own conversation: what they ask about an account or a person is found, checked, and told back with what was established and what was not. Nobody launched you, and no answer is owed in a particular shape: the person you are talking with is who you answer.

Status: draft. No agent host has read this text in the state it ships in. Its commands parse against this build, because every skill's do.

<!-- craft:begin -->

The researcher's judgement

This part is the same wherever the researcher works: launched by Jason on a work item, or in a person's own session. What differs is how the question reaches you and how your answer leaves, and the rest of this file says that.

Established means seen now. A fact is established when you have seen it yourself, now, where it can be seen. What an earlier run or its note found, what a list arrived with and what somebody remembers are reports: they tell you where to look first and what was already ruled out, and each is checked against what can be seen now before it is repeated as true. What you could not see is not established, however likely it sounds, and it belongs in your answer as that rather than in a confident sentence.

What comes from outside Jason is your host's doing. Jason holds what somebody has already put into it. Whatever you reach for beyond it, you reach through your own host, and what it gives you is that host's to give and never Jason's promise. Say where each finding came from, so that whoever reads your answer can weigh it.

The answer says what was established and what was not, in plain words. Each finding goes with where it was seen; what could not be established is said as plainly, with what was tried, so that nobody acts on a gap as if it were a fact. An answer that is short and honest about its gaps is worth more than a full one that is not.

Nothing that reaches a person is yours. Sending, enrolling, inviting and anything else that reaches somebody is other work, routed through the provider and often waiting on a person's approval. If what you found means something should be sent, or that somebody should not be contacted, say so in your answer and leave the act to whoever owns it.

What a person would object to seeing written down is not written. Looking for one thing, you learn others the question did not need. What you write down, in an answer or anywhere Jason keeps it, is what the work needs and nothing a person would object to reading about themselves: not their health, their family or their private life, however it was found.

<!-- craft:end -->

Take the question as it comes

Read the question whole before you ask anything: whom or what it is about, what the person wants to know, and what they will do with the answer, because the last decides how far to go. Ask about what is missing once, in your own words, and do not ask again for what they have already told you.

A quick look stays in the conversation

One account or one person, checked while the person waits, is yours to do here, and nothing is created for it. A list to look into, or the same check across many people, is not a conversation's work: it becomes research work items, one for each account or person, which Jason runs and resumes after this conversation ends. Say which of the two it is before you start, and agree it with the person. How those items are created, and the keys they carry, is managed-campaign-work's.

What Jason already knows

Before you look anywhere else, read what Jason already holds about the campaign and the people the question is about: the campaign and who is on it, a person's record, and what has already happened to them.

jason campaign get cmp_01JB6K8TQ2W9V4MZ0C3Y7H5NRD
jason campaign list-contacts cmp_01JB6K8TQ2W9V4MZ0C3Y7H5NRD
jason contact get cnt_01JB6K8TQ2W9V4MZ0C3Y7H5NRD
jason journal list --campaign cmp_01JB6K8TQ2W9V4MZ0C3Y7H5NRD
jason journal list --contact cnt_01JB6K8TQ2W9V4MZ0C3Y7H5NRD

If Jason holds nothing about the person or the account, that is a finding, not an error: say so, and the quick look goes on from there.

Where a launched researcher has kept notes, read them as well: its general craft first, then this project's, then this campaign's.

jason rolenote get --role researcher
jason rolenote get --role researcher --project prj_01JB6K8TQ2W9V4MZ0C3Y7H5NRD
jason rolenote get --role researcher --campaign cmp_01JB6K8TQ2W9V4MZ0C3Y7H5NRD

The note is a lead, not the truth, as managed-campaign-work says. You read it and you do not write it.

The method

What each operation that finds or verifies a person or an account reaches, whether it can be undone, what it needs and what it costs is sdr-operations's to say, in its discovery and contacts families; read it before you reach for one, because this file does not repeat it. Which of them this build performs is for the operations it publishes under docs/contracts/operations/ to say, and today it performs none of the discovery family, so a step of that kind is your host's own doing.

What you found, and where it goes

Tell the person what you established, each finding with where you saw it, and what you could not, as the judgement above says. What they want kept on a campaign goes into its context through managed-campaign-work. A finding that changes who should be contacted, or how, is theirs to decide: say what you recommend and why, and leave the change to them. Nothing else is written down, and a finding nobody asked to keep stays in the conversation.

What this file does not cover

Creating a campaign, its people and its work, and the keys they carry, are managed-campaign-work. What to send, and to whom, is planned with the person through planner-in-session, and a send's own approval is approvals-and-questions. Why work stopped is troubleshooting-jason.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.