Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →agenticnotetaking/next
Surface the most valuable next action by combining task stack, queue state, inbox pressure, health, and goals. Recommends one specific action with rationale.
Passed 15 of 20 test cases with the skill, and 3 of 20 without it.
and 17 more in the full report
13 fixed4 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
There are 7 unread article markdowns in inbox/ (oldest is 10 days old, including inbox/learning-techniques.md which directly aligns with active research in ops/goals.md), and no open tasks in ops/tasks.md. What specific action should be recommended?
| Checked | Without skill | With skill |
|---|---|---|
| Recommends processing the concrete file inbox/learning-techniques.md. | Passed | Passed |
| Uses the domain reduce command in the recommendation. | Missed | Passed |
The instructions your model reads when the skill loads.
Read these files to configure domain-specific behavior:
ops/derivation-manifest.md — vocabulary mapping, domain context
vocabulary.notes for the notes folder namevocabulary.inbox for the inbox folder namevocabulary.note for the note type name in outputvocabulary.topic_map for MOC referencesvocabulary.cmd_reduce for process/extract commandvocabulary.cmd_reflect for connection-finding commandvocabulary.cmd_reweave for backward-pass commandvocabulary.rethink for rethink command nameops/config.yaml — thresholds, processing preferences
self_evolution.observation_threshold (default: 10)self_evolution.tension_threshold (default: 5)If these files don't exist, use universal defaults and generic command names.
INVARIANT: /next recommends, it does not execute. Present one recommendation with rationale. The user decides what to do. This prevents cognitive outsourcing where the system makes all work decisions and the user becomes a rubber stamp.
Execute these steps IN ORDER:
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 (notes, inbox, topic map, etc).
Before collecting state, evaluate all maintenance conditions and reconcile the queue. This ensures maintenance tasks are current before the recommendation engine runs.
Read queue file (ops/queue/queue.json or ops/queue.yaml). If schema_version < 3, migrate:
maintenance_conditions section with default thresholdstest cases passed, vs 3 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.