“After an industrial DJ” → don’t go harder, build tension differently
“Bar, 50 people” → lower energy ceiling, more variety, deeper cuts
Use supported search_tracks filters such as BPM, genre, rating, key, date,
or playlist to build a local candidate set
Use score_transition on representative local pairs when you need the
scoring profile’s returned derived 0–1 energy values; search_tracks has no
energy filter, and resolve_tracks_data returns analyzer evidence rather
than the derived score
Use query_transition_candidates to identify tracks that work well
together within the pool
Present a curated pool (not a fixed sequence) — the DJ picks the order live
Optionally run build_set for a suggested sequence within the pool
The value is in the translation from natural language context to musical parameters — something a GUI tool can’t do.
Understand your library’s shape — and its blind spots.
Paste into your agent:
Analyze my collection for gaps and imbalances. I want to understand:
- Where am I deep vs. thin?
- What keys/tempos/genres am I missing?
- Am I overindexing on anything?
- What limits my flexibility as a DJ?
You’ll get: A practical map of strong and thin areas in your own library,
with concrete gaps to explore or practise.
How the assistant works (technical)
Exact operations:
Use read_library for overall stats (genre distribution, key distribution, track count)
Use search_tracks with supported filters to map local coverage, then use
resolve_tracks_data when cached audio evidence is needed:
BPM buckets (< 120, 120-125, 125-130, 130-135, 135+) — where are you thin?
Key coverage across the Camelot wheel — any dead ends where you have 1 track and nothing compatible?
Genre coverage — are you a techno DJ with 3 house tracks, or evenly spread?
Representative derived 0–1 energy from score_transition — all bangers
and no warmup material? Do not claim a full distribution without scoring
the local tracks being compared.
Rating distribution — are you only rating the tracks you already love?
Identify specific gaps:
Keys with < 3 tracks (harmonic dead ends)
BPM ranges with < 5 tracks (can’t sustain a set there)
Labels represented heavily or thinly in the collection
Present findings as actionable local-library insights, not just charts.
Open-ended catalog gap discovery is outside these tools; evaluate a concrete
user-supplied track or release only after the user provides one.
A knowledgeable collaborator for finding directions in your own collection and
evaluating concrete candidates you supply.
Paste into your agent:
I'm digging for new music today. Here's the direction:
[describe what you want — genre, mood, tempo, or reference tracks]
Use my collection to understand my taste and suggest directions. If I give you
a concrete track or release candidate, evaluate how it fits.
You’ll get: Collection-grounded directions and, when you supply a concrete
candidate, a focused fit assessment rather than invented catalog suggestions.
How the assistant works (technical)
Exact operations:
Analyze the local collection for label, artist, genre, era, tempo, and key.
Use resolve_tracks_data for analyzer evidence, then call
score_transition on representative local pairs before describing any
derived-energy pattern. Resolve responses do not contain derived scoring
values.
Suggest collection-grounded directions such as an underused genre, tempo
band, label already represented locally, or contrasting era. Do not claim
specific new tracks are available.
Ask the user for a concrete track or release candidate before provider
lookup. lookup_discogs and lookup_beatport match that specific candidate;
they do not search credits or explore a label’s catalog.
For a user-supplied candidate, report only the returned match fields and
compare its genre, BPM, key, and label/date with the local collection. Audio
evidence is available only if the candidate is already a local track with a
current cache entry.
Defer open-ended catalog and collaborator research. These tools do not
provide it, and this recipe does not add an external-search prerequisite.
Focus: [e.g., "learn my new tracks", "practice difficult transitions",
"explore a key I never use", "get comfortable below 124 BPM"]
Duration: [e.g., 30 min, 1 hour]
You’ll get: Ordered exercises matched to your focus and available time,
with varied transition challenges and a clear next-session feedback loop.
How the assistant works (technical)
Exact operations:
Based on the focus area, select appropriate tracks:
New tracks: find recently added tracks (by date or specific batch), pair them with familiar tracks for context
Difficult transitions: find pairs with challenging but rewarding compatibility — key jumps that work with the right timing, BPM gaps that need manual adjustment
Weak key areas: find tracks in keys the DJ rarely uses (from gap analysis), pair with comfortable keys to practice moving in and out
Tempo range: find tracks in the target BPM range, pair in sets of 3-4 for extended practice
Use score_transition to find pairs that are:
Achievable but not trivial based on the 0–1 composite and, more
importantly, its per-axis breakdown
Varied in challenge type (some harmonic, some tempo, some energy); select
qualitatively rather than inventing a rigid score band
Present as ordered exercises:
“Mix 1: Track A → Track B (compatible keys, practice the 4 BPM gap)”
“Mix 2: Track C → Track D (key jump from 6A to 8A — try mixing during the breakdown)”
“Mix 3: Track E → Track F → Track G (3-track chain, maintain energy while shifting keys)”
After practice, ask what worked and what didn’t — refine for next session
Choose a conversational recipe for gig prep, collection analysis, candidate evaluation, debriefing, harmonic planning, or practice.
This page is a recipe catalog. Network use, local state, prerequisites, duration, and result vary by recipe; compare the six contracts below.
Best for
DJs who want a guided conversation rather than one fixed operational workflow.
Network
Network when neededOnly recipes evaluating a concrete track or release candidate supplied by the user use provider lookups; local planning recipes do not browse catalogs or discover releases.
Scope
One selected recipe and the collection subset or session context supplied to it.
Time
Scope-dependent and set by the chosen recipe and conversation depth.
Resuming
Recipes do not maintain a durable workflow cursor. Reuse the prompt and prior constraints after a restart.
Result
A conversation result that varies by recipe; no file or Rekordbox change is made.
What can change
Staged metadata
This workflow does not create staged metadata.
Direct user files
None.
Local state
Enrichment cacheWhen needed — Collection Gap Analysis or Dig Session Partner evaluates a concrete user-supplied candidate whose lookup is not cached.
Provider sessionWhen needed — That supplied-candidate lookup needs Discogs authentication.
Files created
None.
Before you start
reklawdbox connected to a library with the collection or history data needed by the chosen recipe.
Recipe-specific context such as gig constraints, a practice focus, or a session date.
Approval checkpoints
The user chooses the recipe, constraints, and whether to act on any recommendation.
Recovery
Narrow the request, correct the context, or rerun the recipe with different constraints.
Rekordbox handoff
None. This workflow produces recommendations only.
Choose a recipe
Gig Prep
Translate venue, slot, duration, and vibe into a curated performance pool or suggested sequence.
Network
No networkTrack search and transition scoring use local library data and cached analysis.
Local state
None.
Needs
Gig context and enough local candidate tracks for the requested constraints.
Time
Scope-dependent; driven by pool size and refinement.
Result
A curated pool and, optionally, a suggested local sequence.
Collection Gap Analysis
Map thin and deep areas in the local library, then frame digging directions or evaluate a concrete candidate supplied by the user.
Network
Network when neededThe user supplies a specific track or release candidate that needs an uncached Discogs lookup.
Local state
Enrichment cacheWhen needed — The supplied candidate’s Discogs lookup is not already cached.
Provider sessionWhen needed — Discogs authentication is required for the supplied candidate lookup.
Needs
A library large enough for meaningful genre, key, BPM, energy, or rating distributions; a concrete candidate is required before provider lookup.
Time
Scope-dependent; local analysis can be followed by evaluation of a supplied candidate.
Result
An actionable description of local collection strengths, blind spots, and broad digging directions, plus evaluation of any supplied candidate.
Dig Session Partner
Use the local collection as taste context to frame directions and evaluate concrete candidates supplied by the user.
Network
Network when neededA user-supplied track or release candidate needs a Discogs or Beatport lookup that is not already cached.
Local state
Enrichment cacheWhen needed — The supplied candidate’s Discogs or Beatport lookup is not already cached.
Provider sessionWhen needed — Discogs authentication is required for the supplied candidate lookup.
Needs
A desired direction and enough collection context to infer taste; a concrete candidate is required before provider lookup.
Time
Scope-dependent; driven by local analysis, supplied candidates, and follow-up conversation.
Result
Collection-grounded directions and evaluation of supplied candidates; reklawdbox does not browse label catalogs or discover releases.
Post-Gig Debrief
Review a recorded Rekordbox session for energy, tempo, harmonic movement, and rotation patterns.
Network
No networkSession history and track data are read from the local Rekordbox library.
Local state
None.
Needs
A Rekordbox session or history entry for the gig being reviewed.
Time
Scope-dependent; driven by session length and comparison depth.
Result
A structured debrief with observations to apply to future preparation.
Harmonic Journey Planning
Plan an extended Camelot-key path and identify track choices or gaps along it.
Network
No networkKey mapping, track search, and transition scoring use local data and cached analysis.
Local state
None.
Needs
A starting point, journey style, duration, and candidate scope with usable key/BPM evidence.
Time
Scope-dependent; driven by journey length and library coverage.
Result
A harmonic path with candidate tracks and explicit gaps or difficult transitions.
Practice Session Design
Turn a practice focus and time limit into ordered exercises using tracks from the local library.
Network
No networkTrack selection and pair scoring use local data and cached analysis.
Local state
None.
Needs
A practice focus, duration, and enough local tracks for the requested exercises.
Time
User-defined practice duration plus scope-dependent preparation.
