Skip to complete skill
Free community skill@tomcrawshaw01

Agent-graph research workflow

Independently compiled by XSkills from public material by Tom Crawshaw.

Convert a research question into a dependency-aware agent graph with independent research branches, a separate skeptic, evidence-gated synthesis, and manual approval before delivery.

Skill brief

Is this the right skill?

Use it when

  • You have a research task with genuinely independent evidence streams.
  • You need a skeptical review that does not inherit the researchers' framing.
  • You can prove the workflow manually before making it scheduled or durable.

What you get

  • Dependency graph or honest fallback specification
  • Independent angle findings with sources and dates
  • Unsupported findings removed by the skeptic

Workflow

6 moves
  1. 01

    Choose a graph only when needed

  2. 02

    Remove false dependencies

  3. 03

    Run independent branches

  4. 04

    Challenge before synthesis

  5. 05

    Synthesize and approve

  6. 06

    Prove then schedule

Complete instruction set

Complete SKILL.md

Read every instruction below or copy the complete file directly into your agent.

Agent-graph research workflow

Source workflow

Draw the real dependencies

Use one agent when every step needs the full result of the previous step. Use a graph when independent research angles can run together and later work genuinely reads their outputs.

Draw every job and edge. Keep an edge only when output from the first job passes into the second. Remove false waits such as summarizing a file before an unrelated calendar check.

Separate research from checking

Give each independent angle to a delegated Hermes sub-agent. Add a separate skeptic sub-agent that did not produce the original findings. Give the skeptic a narrow checking question; a vague request to "review the report" is not enough.

Have the skeptic read the findings and drop anything it cannot support before the merge. This separation matters more than adding more agents or choosing a secret model.

Merge and retain the last human yes

Merge the surviving findings into one report. Put human approval where a mistake becomes expensive to undo, usually before work leaves the business or moves money. Do not insert approval at every intermediate step.

Account for graph cost

Use cheaper models for broad collection and reserve the expensive model for judgment or the final merge. Preserve the source's caveat: one developer measured fixed overhead at 73% of each API call on one older Hermes setup; it is not a universal benchmark.

Build the first graph by interviewing the operator

Before building, ask:

  • what question is being researched;
  • which angles are worth splitting;
  • what counts as a credible source;
  • where the result should land.

Create one parallel sub-agent per angle, a separate skeptic that tries to disprove every finding and drops unsupported material, and a merge that ranks survivors by confidence with a source and date. Save the graph as a reusable skill, but do not schedule it yet.

Run it by hand until the operator can inspect what the skeptic drops and what the merge keeps. Once reliable, schedule the source example for Monday at 9am and send the finished report to Telegram. Send nothing else without asking.

Hermes is the source's durable environment: cron starts the graph, Telegram or Discord receives the report, and its delivery ledger preserves completed responses across a gateway crash.

XSkills operational adaptations

Preflight Hermes delegation, shared context, skill saving, cron, the delivery channel, and durable delivery. If delegation is unavailable, return the graph specification and prompts instead of claiming parallel execution. If scheduling or delivery is unavailable, complete the manual proof run and return the exact schedule/delivery configuration still needed.

XSkills safety adaptations

Use only authorized source access. Require the operator's approval before any external delivery, schedule activation, spending increase, or irreversible action. A research report may be prepared before that gate; it must not be sent through an unapproved channel.

Return

Return the graph or graph specification, angle findings with sources and dates, skeptic removals, ranked merged report, manual proof result, and any unactivated schedule or delivery step.

Source attribution

Independently compiled by XSkills from Tom Crawshaw's X Article about graph engineering with Hermes. Crawshaw did not author or review this skill. Capability fallbacks and explicit access, delivery, schedule, spending, and irreversible-action boundaries are XSkills adaptations. Attribution does not imply endorsement.

Keep exploring

Related agent skills

Browse ai workflows skills

Turn an X workflow into your own skill.

Paste a public X post and get a free SKILL.md.

Build one free

Evidence and package

Source, changes, and version

Source

XSkills independently compiled this from public material by Tom Crawshaw. Attribution does not imply endorsement.

Open source evidence ↗

What XSkills changed

XSkills additions are labeled in the complete SKILL.md.

Limitations

  • Do not split a chain whose conclusions depend on the preceding step.
  • Use a checker that did not produce the original finding and give it a narrow question.
  • Do not schedule the graph before the manual run is reliable.

Version

Package version
Not assigned
Fingerprint
7131537d898e
Last reviewed
Not recorded
License
Not specified