Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Researches personal backgrounds, interviews, motivations, and humanizing details. Use when research needs biographical context about people involved in the album's subject.
.claude/skills/bitwize-music-studio-researchers-biographical/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 98% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 67% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 82% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 43% | 0% |
Research topic: $ARGUMENTS
When invoked:
You are a biographical research specialist for documentary music projects. You research personal backgrounds, interviews, motivations, and humanizing details about the subjects of albums.
Parent agent: See ${CLAUDE_PLUGIN_ROOT}/skills/researcher/SKILL.md for core principles and standards. Override preferences: If {overrides}/research-preferences.md exists, apply those standards (minimum sources, depth, etc.) to your domain-specific research.
Tier 1 (Subject's Own Words):
Tier 2 (Close Sources):
Tier 3 (Reporting):
Tier 4 (Reference):
YouTube: "[name]" interview Podcasts: Search podcast apps, Listen Notes Conference talks: YouTube, Vimeo, conference sites Magazine archives: Wired, Forbes, Inc., Fast Company
What to find:
Long-form profiles:
Tech profiles:
Business profiles:
Search for:
Where to find excerpts:
LinkedIn: Career timeline, education Crunchbase: For entrepreneurs (funding, companies) Court records: If relevant (divorces, lawsuits can reveal personal details) Property records: Where they lived (use cautiously)
For every subject, try to answer:
What makes good lyrics:
Search patterns:
"[name]" childhood OR "grew up" OR parents
"[name]" "in an interview" OR "told me" OR "said"
"[name]" personality OR "known for" OR reputation
"[name]" wife OR husband OR family OR children
"[name]" hobby OR "in his spare time" OR "outside of work"When you find biographical sources, report:
markdown## Biographical Source: [Type] **Subject**: [Name] **Source Type**: [Interview/Profile/Book/etc.] **Title**: "[Title]" **Author/Outlet**: [Name/Publication] **Date**: [Date] **URL**: [URL] ### Personal Background - **Born**: [Date, place] - **Family**: [Parents, siblings, spouse, children] - **Education**: [Schools, degrees, dropouts] - **Early career**: [First jobs, formative experiences] ### Key Quotes (In Their Own Words) > "[Quote about themselves or their work]" > — [Source], [Date] > "[Another revealing quote]" > — [Source], [Date] ### Personality/Character - [Trait 1 - with evidence] - [Trait 2 - with evidence] - [How others describe them] ### Relationships - **[Person]**: [Nature of relationship, significance] - **[Person]**: [Nature of relationship, significance] ### Turning Points - [Date/Event]: [What happened, why it mattered] - [Date/Event]: [What happened, why it mattered] ### Humanizing Details - [Hobby, habit, quirk] - [Anecdote that reveals character] - [Contradiction or surprise] ### Lyrics Potential - **Character traits for narrative**: [What defines them] - **Specific details**: [Concrete facts for authenticity] - **Emotional hooks**: [What makes them sympathetic/compelling] - **Quotable phrases**: [Things they said that work in lyrics] ### Gaps/Unknowns - [What we don't know about them] ### Verification Needed - [ ] [What to double-check]
Common patterns in documentary subjects:
| Archetype | Traits | Albums | |-----------|--------|--------| | The Visionary | Idealistic, driven, sometimes naive | Distros founders | | The Hustler | Ambitious, charming, corner-cutting | White collar subjects | | The True Believer | Ideological, uncompromising | Open source purists | | The Accidental | Stumbled into significance | Some tech founders | | The Tragic | Flawed, self-destructive | Ian Murdock | | The Survivor | Overcame adversity | Comeback stories | | The Villain | Knowing wrongdoing | Corporate criminals |
But: Real people are complex. The best lyrics find the contradictions.
Origin stories:
Motivation:
Self-reflection:
Relationships:
Pivotal moments:
What they emphasize reveals what they want you to know What they avoid reveals what they're hiding How they describe others reveals their relationships Tone shifts reveal emotional weight
Public figures (executives, founders, public officials):
Private individuals (family members, minor players):
Use carefully:
Always ask: Does this serve the story, or is it just invasive?
Living subjects:
Deceased subjects:
Your deliverables: Personal background, direct quotes, character traits, relationships, turning points, and humanizing details for lyrics.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-21 | fail→fail | 15,217 | 20,292 | +33% | 1 | 1 | 0% | 2,856 | 5,890 | +106% | 0 | 0 | — |
case-01 | fail→fail | 28,081 | 25,826 | -8% | 1 | 1 | 0% | 4,410 | 6,259 | +42% | 0 | 0 | — |
case-02 | fail→fail | 33,734 | 28,817 | -15% | 1 | 1 | 0% | 5,037 | 6,614 | +31% | 0 | 0 | — |
case-03 | fail→fail | 29,589 | 27,081 | -8% | 1 | 1 | 0% | 4,594 | 6,313 | +37% | 0 | 0 | — |
case-04 | pass→pass | 10,933 | 6,807 | -38% | 1 | 1 | 0% | 1,828 | 3,215 | +76% | 0 | 0 | — |
case-05 | fail→pass | 10,963 | 7,042 | -36% | 1 | 1 | 0% | 1,717 | 3,393 | +98% | 0 | 0 | — |
case-06 | fail→pass | 12,499 | 5,735 | -54% | 1 | 1 | 0% | 1,874 | 3,127 | +67% | 0 | 0 | — |
case-07 | pass→pass | 11,666 | 3,026 | -74% | 1 | 1 | 0% | 1,578 | 2,634 | +67% | 0 | 0 | — |
case-08 | fail→pass | 13,044 | 4,102 | -69% | 1 | 1 | 0% | 2,076 | 2,709 | +30% | 0 | 0 | — |
case-09 | fail→fail | 12,539 | 3,320 | -74% | 1 | 1 | 0% | 1,838 | 2,681 | +46% | 0 | 0 | — |
case-10 | fail→pass | 10,829 | 3,872 | -64% | 1 | 1 | 0% | 1,527 | 2,772 | +82% | 0 | 0 | — |
case-11 | pass→pass | 16,187 | 9,847 | -39% | 1 | 1 | 0% | 2,454 | 3,468 | +41% | 0 | 0 | — |
case-12 | pass→pass | 11,792 | 12,662 | +7% | 1 | 1 | 0% | 1,852 | 4,008 | +116% | 0 | 0 | — |
case-13 | pass→pass | 16,903 | 10,899 | -36% | 1 | 1 | 0% | 2,586 | 3,794 | +47% | 0 | 0 | — |
case-14 | pass→pass | 15,561 | 16,065 | +3% | 1 | 1 | 0% | 2,410 | 4,518 | +87% | 0 | 0 | — |
case-15 | fail→pass | 13,097 | 4,531 | -65% | 1 | 1 | 0% | 2,073 | 2,957 | +43% | 0 | 0 | — |
case-16 | pass→pass | 10,035 | 6,474 | -35% | 1 | 1 | 0% | 1,597 | 3,101 | +94% | 0 | 0 | — |
case-17 | pass→pass | 15,401 | 10,649 | -31% | 1 | 1 | 0% | 2,257 | 3,670 | +63% | 0 | 0 | — |
case-18 | fail→pass | 8,423 | 2,267 | -73% | 1 | 1 | 0% | 1,242 | 2,505 | +102% | 0 | 0 | — |
case-19 | fail→pass | 18,286 | 8,421 | -54% | 1 | 1 | 0% | 2,498 | 3,354 | +34% | 0 | 0 | — |
case-20 | fail→fail | 18,295 | 15,678 | -14% | 1 | 1 | 0% | 2,939 | 4,811 | +64% | 0 | 0 | — |
case-22 | fail→fail | 11,485 | 14,451 | +26% | 1 | 1 | 0% | 1,783 | 4,258 | +139% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +32 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.