Hermes Agent
dc592e528a
deep-research: v2.4.0 — file-only delivery to ~/workspace/research/results/<date>-<slug>.md with YAML frontmatter
2026-07-06 16:51:40 -05:00
Hermes Agent
713c03a249
deep-research: v2.3.0 — raised clarifying question caps (5/10), added tool selection strategy, post-dispatch no-polling rule; ask-testing: v1.0.0 — new peer agent for testing profile
2026-07-06 16:47:52 -05:00
Hermes Agent
fd3a71308e
create-plan: v1.1.1 — fix tool names (web_extract/mcp__playwright__), echo metacharacter breakage, bash-wrapped tool calls, self-referential §6.2, add one-at-a-time rule
2026-07-06 16:05:07 -05:00
Hermes Agent
29556adb6f
deep-research v2.2.0, deep-web-research v2.1.0 — clarifying-question cap
...
Both skills now have a hard cap on clarifying questions / scope ambiguity:
- deep-research (general profile dispatcher): 3 questions default, 5 hard cap,
abort at 6+. If the operator's question is under-specified, push back
rather than fire 6+ questions.
- deep-web-research (research profile methodology): headless, no operator
to ask. Detects under-specified questions and aborts with a structured
report naming the plausible interpretations, instead of dispatching with
a guessed scope.
This addresses the workshopping rule: 'up to 10 clarifying questions at
start, with max clarity.' Consensus after peer review: 10 is too many,
tighter cap forces prioritization. Abort at 6+ is the signal that the
question itself is broken, not the agent's question-asking budget.
2026-07-06 15:43:03 -05:00
Hermes Agent
9ef60eda37
remove 65 unmodified built-in skills (60 byte-identical + 5 version-only)
...
Skills removed are byte-for-byte identical (or differ only in the version
field we added to satisfy the version policy) to the upstream hermes-agent
package. They are sourced directly from the installed package at
/home/n8n/.hermes/hermes-agent/skills/ — keeping them in Gitea is
redundant.
Gitea now carries only skills with real customizations or custom-built
content. Future use of upstream built-ins (maps, notion, etc.) requires
a one-shot pull from hermes-agent, not from Gitea.
146 → 81 skills.
2026-07-06 13:19:37 -05:00
Hermes Agent
1533a6e8c3
ask-claude v2.6.1, ask-hermes v4.2.0, ask-dev v1.1.0, create-plan v1.1.0
...
- ask-claude v2.4.0 -> v2.6.1: Added mandatory disagreement scan (Step 3.5) with web-reference demand + internal consistency check. Updated callouts for the paste-vs-path rule (now HARD RULE, not just example).
- ask-hermes v4.1.1 -> v4.2.0: Added mandatory disagreement scan mirroring ask-claude.
- ask-dev v1.0.0 -> v1.1.0: Added mandatory disagreement scan mirroring ask-claude.
- create-plan v1.1.0 (new): Multi-agent plan-build dispatcher. Trigger phrases, 10-Q brief script (min as needed, max 10), curator dispatch, capture/handoff format, all 6 failure modes. Companion references: curator-framing-prompt.md, deep-research-dispatch-template.md, ask-claude-validation-template.md, structured-brief-10q.md.
5 rounds of Claude validation on the design plan; final SHIP from ask-hermes peer review.
2026-07-06 12:51:02 -05:00
Hermes Agent
c6d6db699c
ascii-video, minecraft-modpack-server, obsidian, pokemon-player, powerpoint, songwriting-and-ai-music: add version 1.0.0 — gitea: sync v1.2.0
2026-07-05 17:42:06 -05:00
Hermes Agent
c6ca1d9a9b
truenas: v1.0.0 (new to repo) — workspace-context-organization, youtube-content: add version field — ecosystem-surveillance: v1.1.0 sync
2026-07-05 17:30:28 -05:00
Hermes Agent
d25b048a72
deep-research + deep-web-research: v2.0.0 — six-move flow, domain-aware tool selection, re-strategize checkpoints, tag-based saturation, 600-turn ceiling
2026-07-05 17:28:26 -05:00
Hermes Agent
7771212893
update: session persistence rule — same topic resume, new topic new session
2026-07-05 15:32:45 -05:00
Hermes Agent
f6bb79df52
Add deep-research v1.0.0 — deep web research delegation skill
2026-07-04 14:00:28 -05:00
Hermes Agent
528bc1e54f
Add ask-dev v1.0.0 — dev profile peer agent skill
2026-07-04 13:43:21 -05:00
Hermes Agent
133d3d8b07
gitea: v1.1.0 — add versioning policy, bump version in commit messages
2026-07-04 13:38:05 -05:00
Hermes Agent
046de9e502
Add deep-web-research skill: exhaustive five-move research flow with external ledger, mechanical saturation check, phase gate, disconfirmation
2026-07-04 13:37:09 -05:00
Hermes Agent
d07044fd61
Update save-q-memory to v1.1.0 — add _source field to match schema
2026-07-04 11:49:37 -05:00
Hermes Agent
a21fba4cae
Update jotty-notes-api to v1.1.0 — add all three instances (Rob, Zoe, Jennifer)
2026-07-04 11:46:14 -05:00
Hermes Agent
b0d790be34
Add all 104 active skills from all 16 Hermes profiles
...
12 unversioned skills now versioned at 1.0.0:
agent-communication, ascii-video, external-reasoning-augmentation,
jotty-notes-api, minecraft-modpack-server, obsidian, pokemon-player,
powerpoint, social-search, songwriting-and-ai-music,
workspace-context-organization, youtube-content
Total repo: 141 skills across all profile scopes
2026-07-04 11:44:04 -05:00
Hermes Agent
d1c8a76180
Add all custom Hermes skills from general profile (33 skills)
...
agent-workflows: workspace-context-organization
autonomous-ai-agents: hermes-agent
computer-use
devops: hermes-config-bulk-update, hermes-profile-management, holographic-memory, telegram-integration, webhook-subscriptions
email: himalaya
mcp: native-mcp, searxng-smart-search
media: voice-systems, youtube-content
mlops: local-vector-memory, qdrant-collection-management
productivity: maps, notion, ocr-and-documents
project-knowledge-base
research: arxiv, blogwatcher, ecosystem-surveillance
save-agents-md
social-media: social-media-scraping, xurl
software-development: agent-self-audit, simplify-code, spike, subagent-driven-development, systematic-debugging, test-driven-development, writing-plans
user-response-style
2026-07-04 11:39:25 -05:00
Hermes Agent
c3b3cfdd09
Add save-q-memory skill (v1.0.0) — manual Qdrant write enforcer with 10-type schema
2026-07-04 11:38:43 -05:00
Hermes Agent
ea1661aaa9
Add gitea skill (v1.0.0) — push Hermes skill updates to local Gitea
2026-07-04 11:36:41 -05:00
Hermes Agent
03ae162d86
Update ask-claude (v2.4.0) and ask-hermes (v4.1.0) with Critical Evaluation + Limitations sections
...
ask-claude v2.4.0:
- Add 'Critical Evaluation — You Are the Final Authority' (5 rules)
- Add 'Claude's Limitations' (file access, fabrication, environment)
- Add ask.sh fallback pitfall
ask-hermes v4.1.0:
- Add 'Critical Evaluation — You Are the Final Authority' (5 rules)
- Add 'Peer Limitations' (no memory, fabrication, environment, self-reports)
2026-07-04 11:34:58 -05:00
5ae463fb3d
Add ask-claude and ask-hermes skills
2026-07-02 13:49:45 -05:00
