← Claus Argos Skill OSCONTENT HISTORY

Update to Claus Argos Skill OS

Snapshot Nov 21, 2026 · 00:11 UTC · version 1.16.1

Collection source: downloaded plugin package. These snapshots do not have a confirmed matching collection source. Differences in file lists alone do not establish changes to the package.

WHAT CHANGED

Instructions updated for turn-chaos-into-knowledge

Skill instructions — Now says: ## Legacy project-chat route When the source is one or more historical project chats, read...

Observed in instructions or declared skills. Runtime behavior has not been tested.

Save Claus Argos Skill OS and check future changes in Following.

Up to 3 plugins free · no card required.

All fields and original values.

Skill instructions

Before

Sep 30, 2026 · 23:14 UTC

No removed lines (ordering may have changed)

After

Nov 21, 2026 · 00:11 UTC

## Legacy project-chat route When the source is one or more historical project chats, read [references/legacy-chat-extraction.md](references/legacy-chat-extraction.md). Extract attributed candidate knowledge and continuity deltas; do n...

Supporting files

Before

Sep 30, 2026 · 23:14 UTC

[{"relative_path":"agents/openai.yaml","size_in_bytes":229}]

After

Nov 21, 2026 · 00:11 UTC

[{"relative_path":"agents/openai.yaml","size_in_bytes":229},{"relative_path":"references/legacy-chat-extraction.md","size_in_bytes":1847}]

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -9,3 +9,7 @@
 4. Design a shallow taxonomy around retrieval tasks; separate canonical records from commentary and archive.
 5. Resolve duplicates without erasing contradictions; label confidence, stale material, and missing sources.
 6. Return information architecture, canonical summaries, index, decision log, FAQs, gaps, maintenance rules, and migration plan.
+
+## Legacy project-chat route
+
+When the source is one or more historical project chats, read [references/legacy-chat-extraction.md](references/legacy-chat-extraction.md). Extract attributed candidate knowledge and continuity deltas; do not make the chat or its generated summary authoritative. Route ongoing orientation/checkpoints to `$maintain-project-continuity`, portable session transfer to `$handoff-work-between-chats`, and treat full organizational recovery and backup design as separate specialist work.
Full technical diff · 2 changed fields

changed /included_files

BEFORE
[
  {
    "relative_path": "agents/openai.yaml",
    "size_in_bytes": 229
  }
]
AFTER
[
  {
    "relative_path": "agents/openai.yaml",
    "size_in_bytes": 229
  },
  {
    "relative_path": "references/legacy-chat-extraction.md",
    "size_in_bytes": 1847
  }
]

changed /skill_md_contents

BEFORE
"---\nname: turn-chaos-into-knowledge\ndescription: Convert messy notes, chats, files, transcripts, links, and mixed sources into an organized knowledge system with taxonomy, summaries, entities, decisions, procedures, FAQs, provenance, contradictions, gaps, and retrieval paths. Use for knowledge bases, research organization, company wikis, or cleaning information overload.\n---\n# Turn Chaos Into Knowledge\n1. Define users, decisions supported, source scope, sensitivity, freshness, and target system.\n2. Inventory and deduplicate sources; preserve provenance, dates, ownership, and access constraints.\n3. Extract concepts, entities, claims, decisions, actions, processes, questions, and relationships.\n4. Design a shallow taxonomy around retrieval tasks; separate canonical records from commentary and archive.\n5. Resolve duplicates without erasing contradictions; label confidence, stale material, and missing sources.\n6. Return information architecture, canonical summaries, index, decision log, FAQs, gaps, maintenance rules, and migration plan.\n"
AFTER
"---\nname: turn-chaos-into-knowledge\ndescription: Convert messy notes, chats, files, transcripts, links, and mixed sources into an organized knowledge system with taxonomy, summaries, entities, decisions, procedures, FAQs, provenance, contradictions, gaps, and retrieval paths. Use for knowledge bases, research organization, company wikis, or cleaning information overload.\n---\n# Turn Chaos Into Knowledge\n1. Define users, decisions supported, source scope, sensitivity, freshness, and target system.\n2. Inventory and deduplicate sources; preserve provenance, dates, ownership, and access constraints.\n3. Extract concepts, entities, claims, decisions, actions, processes, questions, and relationships.\n4. Design a shallow taxonomy around retrieval tasks; separate canonical records from commentary and archive.\n5. Resolve duplicates without erasing contradictions; label confidence, stale material, and missing sources.\n6. Return information architecture, canonical summaries, index, decision log, FAQs, gaps, maintenance rules, and migration plan.\n\n## Legacy project-chat route\n\nWhen the source is one or more historical project chats, read [references/legacy-chat-extraction.md](references/legacy-chat-extraction.md). Extract attributed candidate knowledge and continuity deltas; do not make the chat or its generated summary authoritative. Route ongoing orientation/checkpoints to `$maintain-project-continuity`, portable session transfer to `$handoff-work-between-chats`, and treat full organizational recovery and backup design as separate specialist work.\n"
Full snapshot data
{
  "description": "Convert messy notes, chats, files, transcripts, links, and mixed sources into an organized knowledge system with taxonomy, summaries, entities, decisions, procedures, FAQs, provenance, contradictions, gaps, and retrieval paths. Use for knowledge bases, research organization, company wikis, or cleaning information overload.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 229
    },
    {
      "relative_path": "references/legacy-chat-extraction.md",
      "size_in_bytes": 1847
    }
  ],
  "name": "turn-chaos-into-knowledge",
  "skill_md_contents": "---\nname: turn-chaos-into-knowledge\ndescription: Convert messy notes, chats, files, transcripts, links, and mixed sources into an organized knowledge system with taxonomy, summaries, entities, decisions, procedures, FAQs, provenance, contradictions, gaps, and retrieval paths. Use for knowledge bases, research organization, company wikis, or cleaning information overload.\n---\n# Turn Chaos Into Knowledge\n1. Define users, decisions supported, source scope, sensitivity, freshness, and target system.\n2. Inventory and deduplicate sources; preserve provenance, dates, ownership, and access constraints.\n3. Extract concepts, entities, claims, decisions, actions, processes, questions, and relationships.\n4. Design a shallow taxonomy around retrieval tasks; separate canonical records from commentary and archive.\n5. Resolve duplicates without erasing contradictions; label confidence, stale material, and missing sources.\n6. Return information architecture, canonical summaries, index, decision log, FAQs, gaps, maintenance rules, and migration plan.\n\n## Legacy project-chat route\n\nWhen the source is one or more historical project chats, read [references/legacy-chat-extraction.md](references/legacy-chat-extraction.md). Extract attributed candidate knowledge and continuity deltas; do not make the chat or its generated summary authoritative. Route ongoing orientation/checkpoints to `$maintain-project-continuity`, portable session transfer to `$handoff-work-between-chats`, and treat full organizational recovery and backup design as separate specialist work.\n"
}

SHA-256 of public snapshot: 55ba2bb5ec5b242eababe8279be2ebcb8be14df122171b9c7de09420ac716c8f