jwynia/underdog-unit
Generate stories about institutional outcasts given impossible mandates with minimal resources. Use when you want team dynamics in hostile institutions, David vs. Goliath within organizations, or narrative tension from constraint-driven creativity.
npx skills add https://github.com/jwynia/agent-skills --skill underdog-unitYou help writers create stories using the "Underdog Unit" formula: institutional outcasts given impossible mandates with minimal resources, creating pressure cookers for character development and creative problem-solving.
Outcasts + Impossible Mandate + Severe Constraints = Narrative Tension
The power lies in:
| Mandate Type | Enemy | Examples |
|--------------|-------|----------|
| Cold Cases | Time | Old evidence, faded memories, dead witnesses |
| Impossible/Unsolvable | Complexity | Cases that stumped the best |
| Cross-Jurisdictional | Bureaucracy | Navigating multiple systems |
| Internal Affairs | Institution | Investigating their own |
| Experimental/New Threats | The Unknown | Cyber, biotech, emerging crimes |
| PR Disasters | Perception | High-profile failures |
| Political Hot Potatoes | Politics | Cases no one wants |
| Reject Pile | Apathy | Cases deemed unimportant |
Physical Space: Basement storage, abandoned wings, trailers, repurposed areas
Budget: Shoestring, self-funded, borrowed, scavenged, barter economy
Personnel: Skeleton crew, part-time, borrowed, probationary, volunteers
Authority: Limited jurisdiction, advisory only, unofficial, no arrest powers
Time: Sunset clause, probationary period, case-by-case renewal
Technology: Outdated, no database access, analog only, DIY solutions
Political: No leadership support, active sabotage, scapegoat status
| Archetype | Description | Story Function |
|-----------|-------------|----------------|
| The Disgraced Expert | Former star with catastrophic failure | Seeking redemption |
| The Rule-Breaker | Gets results through unorthodox methods | Values justice over procedure |
| The Burnout | Lost faith in the system | Rediscovers purpose |
| The Rookie | Inexperienced but eager | Fresh perspective, hasn't learned "impossible" |
| The Outsider | Civilian/reformed criminal/foreign expert | Outside knowledge |
| The Has-Been | Past glory, current irrelevance | Institutional memory |
| The Whistleblower | Did the right thing at wrong time | Principled but isolated |
| The Misfit | Doesn't fit institutional culture | Competent but "difficult" |
| Leadership Type | Relationship to Unit |
|-----------------|---------------------|
| Hostile | Wants them to fail, actively undermines |
| Indifferent | Forgot they exist, benign neglect |
| Protective | One champion shields from bureaucracy |
| Conditional | Support contingent on results |
| Divided | Competing agendas, mixed messages |
What enemy drives your narrative?
Pick 3-4 for maximum friction:
Build complementary dysfunctions:
Define victory:
Plan increasing pressures:
Personal → Professional → Community → Systemic
Official Designations:
Unofficial Names:
| Pitfall | Solution |
|---------|----------|
| Too many constraints | Believability breaks if literally everything is against them |
| Unearned competence | Team needs to struggle before succeeding |
| Deus ex machina resources | Solutions should come from established elements |
| Perfect team harmony | Internal conflict drives development |
| Institutional conversion | System rarely admits it was wrong |
| Consequence-free rule breaking | Actions should have prices |
The constraint becomes the catalyst; the outcasts become the heroes; the impossible becomes the inevitable. The formula works because external struggles mirror internal ones—characters fighting personal demons also fight institutional ones.
context/output-config.md in the projectstories/units/ or explorations/stories/Pattern: {unit-name}-underdog-{date}.md
context/output-config.md{unit-name}-underdog-{date}.mdTrigger phrases: "design the complete unit", "plan the full series", "how does the institution work"
| Task | Agent Type | When to Spawn |
|------|------------|---------------|
| Institutional research | general-purpose | When modeling on real organizations |
| Character development | general-purpose | When deepening individual outcasts |
Pattern: Stacking every possible limitation—no budget, no space, no authority, hostile leadership, skeleton crew, outdated tech, AND a sunset clause.
Why it fails: Beyond 3-4 constraints, the situation becomes implausible. Why would any institution set up something designed to fail this completely? Readers lose suspension of disbelief.
Fix: Pick 3-4 constraints maximum. Make them feel organic to the institution's logic. One powerful constraint (active sabotage from leadership) often works better than five medium ones.
Pattern: The outcast team immediately gels and starts solving cases through brilliant unconventional methods.
Why it fails: The formula requires earning competence. If they're immediately effective, they're not really underdogs—they're just a team with branding problems. The struggle IS the story.
Fix: Build in early failures. Show methods that don't work before finding ones that do. Let team friction create real problems before forging bonds.
Pattern: By the end, the institution recognizes the unit's value, gives them resources, and admits it was wrong.
Why it fails: Real institutions rarely admit systemic error. Having the parent institution validate the outcasts undermines the thematic core about working in the margins.
Fix: Victories should be grudging acknowledgments at best. The unit might survive, but the institution's culture won't fundamentally change. Success comes despite the system, not because it evolves.
Pattern: Each outcast has exactly the skill the team needs, and their dysfunctions never actually impede the work.
Why it fails: The formula requires friction. If the Burnout's apathy never costs them a case, if the Rule-Breaker's methods never backfire, the character flaws are cosmetic.
Fix: Let dysfunctions have real consequences. The Has-Been's outdated methods should fail sometimes. The Whistleblower's principles should create genuine dilemmas, not just flavor.
Pattern: When the plot requires it, someone magically has a contact, favor, or skill that wasn't established.
Why it fails: The constraint-creativity dynamic only works if constraints are real. Pulling resources from nowhere violates the premise. The unit can't be scrappy AND have whatever they need.
Fix: Establish all key resources, contacts, and skills early. Solutions should emerge from previously established elements. If they need something new, acquiring it should be a story beat, not a convenience.
| Skill | What it provides |
|-------|------------------|
| character-arc | Individual transformation arcs for team members |
| positional-revelation | How mundane roles create unexpected access |
| worldbuilding | Institutional systems to work within and against |
| Skill | What this provides |
|-------|-------------|
| dialogue | Team dynamics and conflict for dialogue scenes |
| scene-sequencing | Escalating pressure structure for pacing |
| endings | Earned resolution through team development |
| Skill | Relationship |
|-------|--------------|
| moral-parallax | Underdog-unit creates institutional pressure; moral-parallax explores the ethical complexity of working within corrupt systems |
| story-sense | Use story-sense to diagnose team dynamics problems; underdog-unit provides the formula structure |
Take jwynia/underdog-unit from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.