End-to-end source processing -- seed, reduce, process all claims through reflect/reweave/verify, archive. The full pipeline in one command.
SkillScore45Maintained
Automatic
◆Knowledge Management pack
Last verified 8/12/2026
What it changes
Passed 5 of 12 test cases with the skill, and 2 of 12 without it.
Without skill18%
With skill45%
Checks it passed that the model alone missed
Captures the starting index for claim numbering
Lists created note titles in the report summary
Captures the source file basename as the batch identifier
and 7 more in the full report
8 fixed2 passed either way10 still failing2 broke
Pass-rate lift
+27 pp
Tokens
+110%
Agent turns
0%
Response time
-49%
Model gemini-3.6-flashMeasured 8/12/2026v110 of 22 cases passed with skill · 12 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 8
Prompt
When `--handoff` is passed for batch `dataset-analysis`, what queue status summary must be recorded in the handoff block after archiving?
What was checked, without and with the skill
Checked
Without skill
With skill
States that all tasks for the batch are marked done and archived
Missed
Passed
case-22 · gemini-3.6-flash · 8/12/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md302 linessingle file
EXECUTE NOW
Target: $ARGUMENTS
Parse immediately:
Source file path: the file to process (required)
--handoff: output RALPH HANDOFF block at end (for chaining)
If target is empty: list files in {DOMAIN:inbox}/ and ask which to process
Step 0: Read Vocabulary
Read ops/derivation-manifest.md (or fall back to ops/derivation.md) for domain vocabulary mapping. All output must use domain-native terms. If neither file exists, use universal terms.
START NOW. Run the full pipeline.
Pipeline Overview
The pipeline chains four phases. Each phase uses skill invocation or /ralph for subagent-based processing. State lives in the queue file — the pipeline is stateless orchestration on top of stateful queue entries.
Source file
|
v
Phase 1: /seed — create extract task, move source to archive
|
v
Phase 2: /reduce (via /ralph) — extract claims from source
|
v
Phase 3: /ralph (all claims) — create -> reflect -> reweave -> verify
|
v
Phase 4: /archive-batch — move task files, generate summary
|
v
Complete