Autoresearch Goal
This is a Hermes-native autoresearch-goal workflow skill.
Why This Exists
autoresearch-goal exists to keep research work explicit, evidence-backed, and inside the Hermes/executor boundary instead of relying on ad hoc chat narration.
Do Not Use When
- The request is casual chat, a status-only acknowledgement, or another workflow has stronger routing evidence.
- The user needs implementation, review, CI, merge, or external publishing evidence that has not been delegated or observed.
Examples
Good example:
- Prompt: autoresearch-goal: keep researching AI agent memory practices until the evidence gaps are closed or logged.
- Expected behavior: Run a durable research loop with critic checks, source gaps, and a stop or checkpoint condition.
- Why: The request is research that needs persistence and review, not a one-shot brief.
Bad example:
- Prompt: autoresearch-goal: treat casual chat or unaccepted work as if this workflow already produced verified results.
- Expected behavior: Ask a clarification question or route to a narrower workflow instead of forcing
autoresearch-goal.
- Why: The request lacks the required inputs or would overclaim work that Hermes did not observe.
Completion Checklist
- The research question, source boundaries, recency assumptions, and confidence level are named.
- Observed sources, inference, synthesis, and unresolved retrieval gaps are separated.
- Follow-up planning or handoff uses the research summary without calling it execution evidence.
Recovery Notes
- If sources cannot be accessed, state the retrieval gap and use only observed local context.
- If evidence is thin or one-sided, lower confidence and ask for a narrower source boundary.
Workflow Lane
- Current lane: Research and company ops (
product-docs, source-finder, web-research, research, best-practice-research, autoresearch-goal, model-optimization, inference-serving, +19 more) - research, signals, ops, and briefings.
- If intent belongs to another lane, hand back to
oh-my-hermes or name the adjacent workflow.
- Shared product, routing, compatibility, and evidence rules:
omh-routing/references/skill-common-rail.md.
Use When
Use for validator-gated research that needs durable artifacts.
Strong routing signals: `autoresearch-goal`, `research goal`, `durable research`, `critic research`
Catalog Metadata
Category: research
Phase: durable-research
Hermes role: researcher
Quality tier: validator-gated
Reasoning demand: standard
Quality bar:
- Define validator criteria before gathering evidence.
- Run each cycle as evidence-gap closure: name the open gaps the cycle targets, then stop at the validator criteria or the declared iteration budget, whichever comes first.
- Keep durable research artifacts separate from coding execution evidence.
- Stop with next questions or a source-backed synthesis when validation is incomplete.
Handoff policy:
Keep durable research in Hermes-managed artifacts; do not convert to executor handoff unless the research produces an accepted coding task.
Required inputs:
- research objective
- validator criteria
- source boundaries
Expected outputs:
- research artifact
- validator result
- next questions
Artifact expectations:
- durable research ledger or checklist
Safety rules:
- Do not imply hidden Hermes runtime behavior.
- Use the smallest verification that can prove the claim.
Runtime Evidence
Preferred harness for this skill: research.
omh runtime record --skill autoresearch-goal --harness research --status started
Record observed delegation results; otherwise return not_available or not_observed.
Prepared OMH routing is not execution, review, CI, merge-readiness, or merge evidence.
- Treat wrapper memory/context summaries as advisory local context, not proof of opaque Hermes memory reads or changes.
Preserve workflow intent and stop conditions; verify before claiming completion.
Use Hermes-native subagent/delegation features when available: native subagents -> Hermes delegation when available, otherwise sequential lanes.
Shared product, compatibility, topology, memory, harness, and execution rules: omh-routing/references/skill-common-rail.md. Load it when applicable; otherwise name an unavailable capability.
1---2name: omh-autoresearch-goal3description: [omh] Hermes adaptation for durable research-goal execution. Use when the user says: autoresearch-goal, research goal, durable research, critic research.4---5
6# Autoresearch Goal
7
8This is a Hermes-native `autoresearch-goal` workflow skill.
9
10## Why This Exists
11
12`autoresearch-goal` exists to keep `research` work explicit, evidence-backed, and inside the Hermes/executor boundary instead of relying on ad hoc chat narration.
13
14## Do Not Use When
15
16- The request is casual chat, a status-only acknowledgement, or another workflow has stronger routing evidence.
17- The user needs implementation, review, CI, merge, or external publishing evidence that has not been delegated or observed.
18
19## Examples
20
21Good example:
22
23- Prompt: autoresearch-goal: keep researching AI agent memory practices until the evidence gaps are closed or logged.
24- Expected behavior: Run a durable research loop with critic checks, source gaps, and a stop or checkpoint condition.
25- Why: The request is research that needs persistence and review, not a one-shot brief.
26
27Bad example:
28
29- Prompt: autoresearch-goal: treat casual chat or unaccepted work as if this workflow already produced verified results.
30- Expected behavior: Ask a clarification question or route to a narrower workflow instead of forcing `autoresearch-goal`.
31- Why: The request lacks the required inputs or would overclaim work that Hermes did not observe.
32
33## Completion Checklist
34
35- The research question, source boundaries, recency assumptions, and confidence level are named.
36- Observed sources, inference, synthesis, and unresolved retrieval gaps are separated.
37- Follow-up planning or handoff uses the research summary without calling it execution evidence.
38
39## Recovery Notes
40
41- If sources cannot be accessed, state the retrieval gap and use only observed local context.
42- If evidence is thin or one-sided, lower confidence and ask for a narrower source boundary.
43
44## Workflow Lane
45
46- Current lane: **Research and company ops** (`product-docs`, `source-finder`, `web-research`, `research`, `best-practice-research`, `autoresearch-goal`, `model-optimization`, `inference-serving`, `+19 more`) - research, signals, ops, and briefings.
47- If intent belongs to another lane, hand back to `oh-my-hermes` or name the adjacent workflow.
48- Shared product, routing, compatibility, and evidence rules: `omh-routing/references/skill-common-rail.md`.
49
50## Use When
51
52Use for validator-gated research that needs durable artifacts.
53
54 Strong routing signals: `autoresearch-goal`, `research goal`, `durable research`, `critic research`
55
56## Catalog Metadata
57
58Category: `research`
59Phase: `durable-research`
60Hermes role: `researcher`
61Quality tier: `validator-gated`
62Reasoning demand: `standard`
63
64Quality bar:
65
66- Define validator criteria before gathering evidence.
67- Run each cycle as evidence-gap closure: name the open gaps the cycle targets, then stop at the validator criteria or the declared iteration budget, whichever comes first.
68- Keep durable research artifacts separate from coding execution evidence.
69- Stop with next questions or a source-backed synthesis when validation is incomplete.
70
71Handoff policy:
72
73Keep durable research in Hermes-managed artifacts; do not convert to executor handoff unless the research produces an accepted coding task.
74
75Required inputs:
76
77- research objective
78- validator criteria
79- source boundaries
80
81Expected outputs:
82
83- research artifact
84- validator result
85- next questions
86
87Artifact expectations:
88
89- durable research ledger or checklist
90
91Safety rules:
92
93- Do not imply hidden Hermes runtime behavior.
94- Use the smallest verification that can prove the claim.
95
96## Runtime Evidence
97
98Preferred harness for this skill: `research`.
99
100```sh
101omh runtime record --skill autoresearch-goal --harness research --status started
102```
103
104Record observed delegation results; otherwise return `not_available` or `not_observed`.
105Prepared OMH routing is not execution, review, CI, merge-readiness, or merge evidence.
106- Treat wrapper memory/context summaries as advisory local context, not proof of opaque Hermes memory reads or changes.
107Preserve workflow intent and stop conditions; verify before claiming completion.
108
109Use Hermes-native subagent/delegation features when available: native subagents -> Hermes delegation when available, otherwise sequential lanes.
110
111Shared product, compatibility, topology, memory, harness, and execution rules: `omh-routing/references/skill-common-rail.md`. Load it when applicable; otherwise name an unavailable capability.
rlaope