New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Underdog Unit

by jwynia in jwynia/agent-skills

Generate stories about institutional outcasts given impossible mandates with minimal resources.

MITAuto-check passed

Install Underdog Unit

skills CLI
$ npx skills add jwynia/agent-skills --skill underdog-unit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jwynia/agent-skills underdog-unit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jwynia/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/creative/fiction/character/underdog-unit .claude/skills/underdog-unit && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
underdog-unit
GitHub stars
170
Token cost
~3.9k tokens
SKILL.md length
1,750 words
Files
1
Skills in repo
111
Repo updated
First seen
Licence
MIT

At a glance

Generate stories about institutional outcasts given impossible mandates with minimal resources.

  • Works in 12 steps: The Mandate (Mission Type) → The Constraints (Resource Limitations) → The Team Composition (Outcast Archetypes) → …
  • You want team dynamics in hostile institutions
  • SKILL.md covers Core Formula, The Four Core Elements, Team Formation Patterns and Formula Variations, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Underdog Unit is an agent skill from jwynia/agent-skills. 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.

Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The licence is MIT.

When your agent uses it

  • You want team dynamics in hostile institutions

Example prompts

  • “/underdog-unit”

Workflow steps

12 steps, taken from the step headings in SKILL.md.

  1. The Mandate (Mission Type)
  2. The Constraints (Resource Limitations)
  3. The Team Composition (Outcast Archetypes)
  4. The Institutional Dynamics
  5. Choose Core Conflict
  6. Layer Constraints
  7. Assemble Outcasts
  8. Design Success Conditions
  9. Build Escalation
  10. Constraint Overload
  11. Competence Without Struggle
  12. Institutional Conversion

What it can do on your machine

Read from SKILL.md and the folder at commit e02ec7e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Underdog Unit loads about 3.9k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 1,750 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~3.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jwynia/agent-skills at commit e02ec7e, republished under its MIT licence (© jwynia). 1,750 words, ~3,924 tokens.

Download SKILL.mdSave it as .claude/skills/underdog-unit/SKILL.md (or your agent's skills folder).
name
underdog-unit
description
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.
license
MIT
metadata.author
jwynia
metadata.version
1.0
metadata.type
generator
metadata.mode
generative
metadata.domain
fiction

Underdog Unit: Narrative Formula Skill

You 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.

Core Formula

Outcasts + Impossible Mandate + Severe Constraints = Narrative Tension

The power lies in:

  • Forcing creative solutions through limitation
  • Building team bonds through shared adversity
  • Creating David vs. Goliath dynamics within institutions

The Four Core Elements

1. The Mandate (Mission Type)
Mandate TypeEnemyExamples
Cold CasesTimeOld evidence, faded memories, dead witnesses
Impossible/UnsolvableComplexityCases that stumped the best
Cross-JurisdictionalBureaucracyNavigating multiple systems
Internal AffairsInstitutionInvestigating their own
Experimental/New ThreatsThe UnknownCyber, biotech, emerging crimes
PR DisastersPerceptionHigh-profile failures
Political Hot PotatoesPoliticsCases no one wants
Reject PileApathyCases deemed unimportant
2. The Constraints (Resource Limitations)

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

3. The Team Composition (Outcast Archetypes)
ArchetypeDescriptionStory Function
The Disgraced ExpertFormer star with catastrophic failureSeeking redemption
The Rule-BreakerGets results through unorthodox methodsValues justice over procedure
The BurnoutLost faith in the systemRediscovers purpose
The RookieInexperienced but eagerFresh perspective, hasn't learned "impossible"
The OutsiderCivilian/reformed criminal/foreign expertOutside knowledge
The Has-BeenPast glory, current irrelevanceInstitutional memory
The WhistleblowerDid the right thing at wrong timePrincipled but isolated
The MisfitDoesn't fit institutional cultureCompetent but "difficult"
4. The Institutional Dynamics
Leadership TypeRelationship to Unit
HostileWants them to fail, actively undermines
IndifferentForgot they exist, benign neglect
ProtectiveOne champion shields from bureaucracy
ConditionalSupport contingent on results
DividedCompeting agendas, mixed messages

Team Formation Patterns

  • Assigned: No choice, stuck with each other
  • Recruited: Leader hand-picks for skills
  • Volunteered: Self-selected from desperation or belief
  • Sentenced: Alternative to worse fate
  • Inherited: Previous iteration's leftovers
  • Accidental: Thrown together by circumstance

Formula Variations

The Redemption Arc
  • Elements: Disgraced professionals + impossible cases + hostile institution
  • Theme: Personal redemption parallels unit validation
  • Climax: Often sacrificial victory
The Innovation Lab
  • Elements: Misfits + experimental mandate + indifferent institution
  • Theme: Innovation from the margins
  • Climax: Breakthrough validates unconventional methods
The Last Chance Saloon
  • Elements: Burnouts + cold cases + sunset clause
  • Theme: Finding purpose before it's too late
  • Climax: Each victory extends lifeline
The Expendables
  • Elements: Rule-breakers + dangerous cases + deniable operations
  • Theme: Sacrificial service
  • Climax: Success at personal cost
The Island of Misfit Toys
  • Elements: Misfits + reject cases + forgotten corner
  • Theme: Finding belonging in exile
  • Climax: Creating value from what others discarded

Systemic Tensions to Explore

Resource Creativity
  • Constraints force innovation
  • Informal networks vs. official channels
  • Personal investment compensating for support
  • Favor economy
Loyalty Dynamics
  • Team loyalty vs. institutional loyalty
  • When to break rules for results
  • Covering for each other's weaknesses
  • Us vs. them mentality
Success Paradoxes
  • Success attracts unwanted attention
  • Success threatens established departments
  • Success raises expectations without raising resources
  • Success makes them targets
Identity Questions
  • Professional identity vs. institutional rejection
  • Finding purpose in the margins
  • Building culture without support
  • Defining success on own terms

Implementation Guide

Step 1: Choose Core Conflict

What enemy drives your narrative?

  • Time (cold cases)
  • Complexity (impossible cases)
  • Bureaucracy (jurisdictional)
  • Institution itself (corruption)
  • Unknown (emerging threats)
Step 2: Layer Constraints

Pick 3-4 for maximum friction:

  • One physical (space/equipment)
  • One resource (budget/personnel)
  • One authority (power/jurisdiction)
  • One relationship (institutional dynamics)
Step 3: Assemble Outcasts

Build complementary dysfunctions:

  • Mix experience levels
  • Mix failure types
  • Mix backgrounds (insider/outsider)
  • Create interpersonal friction points
Step 4: Design Success Conditions

Define victory:

  • Short-term wins vs. long-term survival
  • Individual redemption vs. unit validation
  • System change vs. working within it
  • Public victory vs. private knowledge
Step 5: Build Escalation

Plan increasing pressures:

  • Skepticism → active opposition
  • Small wins → bigger challenges
  • Team friction → cohesion → new conflicts
  • Scarcity → solutions → new limitations

Stakes Escalation Pattern

Personal → Professional → Community → Systemic

  1. Job at risk, reputation threatened
  2. Industry/organization threatened
  3. Neighbors, family, local area impacted
  4. Entire social/political order at stake

Unit Naming Conventions

Official Designations:

  • Unfortunate acronyms (S.C.U.M., F.A.I.L.)
  • Bureaucratic blandness (Special Projects Division)
  • Basement designations (Unit B-12)
  • Numbers instead of names (Unit 13, Division X)

Unofficial Names:

  • Sardonic nicknames from other departments
  • Self-deprecating team adoptions
  • Gallows humor references

Common Pitfalls

PitfallSolution
Too many constraintsBelievability breaks if literally everything is against them
Unearned competenceTeam needs to struggle before succeeding
Deus ex machina resourcesSolutions should come from established elements
Perfect team harmonyInternal conflict drives development
Institutional conversionSystem rarely admits it was wrong
Consequence-free rule breakingActions should have prices

Quick-Start Templates

Template 1: The Innocent Professional
  • Pattern: Competence Trap
  • Team: Translator + support staff
  • Revelation: Translating coded criminal communications
  • Conflict: Criminals, law enforcement, victims all need them
Template 2: The Desperate Survivor
  • Pattern: Weakness Lever
  • Team: Night shift cleaners
  • Revelation: Cleaning up disguised crime scenes
  • Conflict: Blackmail, police pressure, moral obligation
Template 3: The Reluctant Heir
  • Pattern: Inherited Network
  • Team: Small shop staff (inherited)
  • Revelation: Shop is neutral ground for criminal negotiations
  • Conflict: Gang expectations, police, community safety

The Key Insight

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.

Output Persistence

Output Discovery
  1. Check for context/output-config.md in the project
  2. If found, look for this skill's entry
  3. If not found, ask user: "Where should I save underdog unit designs?"
  4. Suggest: stories/units/ or explorations/stories/
Primary Output
  • Mandate type - Mission and enemy
  • Constraints - 3-4 selected limitations
  • Team composition - Outcasts with archetypes
  • Institutional dynamics - Leadership relationship
  • Escalation plan - Stakes progression
File Naming

Pattern: {unit-name}-underdog-{date}.md

Verification (Oracle)

What This Skill Can Verify
  • Constraint count - 3-4 constraints, not more? (High confidence)
  • Team dysfunction - Do outcasts have real flaws? (Medium confidence)
  • Formula structure - Core elements present? (High confidence)
What Requires Human Judgment
  • Plausibility - Would institution actually create this unit?
  • Team chemistry - Will these outcasts generate interesting conflict?
  • Stakes calibration - Is escalation appropriate for story length?
Oracle Limitations
  • Cannot assess whether team dynamics will be compelling
  • Cannot predict reader sympathy for outcast characters

Feedback Loop

Session Persistence
  • Output location: See context/output-config.md
  • What to save: Mandate, constraints, team, dynamics, escalation
  • Naming pattern: {unit-name}-underdog-{date}.md
Show full SKILL.md (702 more words)Show less
Cross-Session Learning
  • Check for prior unit designs in this setting
  • Ensure institutional consistency
  • Failed unit dynamics inform anti-patterns

Design Constraints

This Skill Assumes
  • Institution exists to work within/against
  • Resources are genuinely limited
  • Team members are genuinely flawed
This Skill Does Not Handle
  • Individual character arcs - Route to: character-arc
  • Institutional worldbuilding - Route to: governance-systems
  • Scene pacing - Route to: scene-sequencing
Degradation Signals
  • More than 4 constraints (implausible)
  • Team immediately competent (no struggle)
  • Institution converts at end (validates outcasts too easily)

Reasoning Requirements

Standard Reasoning
  • Single constraint selection
  • Individual outcast design
  • Basic team assembly
Extended Reasoning (ultrathink)
  • Full unit design - [Why: all elements must balance]
  • Multi-season escalation - [Why: long-term stakes progression]
  • Institutional integration - [Why: unit must fit larger system]

Trigger phrases: "design the complete unit", "plan the full series", "how does the institution work"

Execution Strategy

Sequential (Default)
  • Mandate before constraints
  • Constraints before team
  • Team before dynamics
Parallelizable
  • Designing multiple team members
  • Research into different institutional models
Subagent Candidates
TaskAgent TypeWhen to Spawn
Institutional researchgeneral-purposeWhen modeling on real organizations
Character developmentgeneral-purposeWhen deepening individual outcasts

Context Management

Approximate Token Footprint
  • Skill base: ~3k tokens (formula + elements + variations)
  • With templates: ~4k tokens
  • With full pitfalls: ~4.5k tokens
Context Optimization
  • Focus on relevant formula variation
  • Templates are starting points, not required
  • Naming conventions are optional flavor
When Context Gets Tight
  • Prioritize: Core formula, current constraint set
  • Defer: Full archetype list, all variations
  • Drop: Quick-start templates, naming conventions

Anti-Patterns

1. Constraint Overload

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.

2. Competence Without Struggle

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.

3. Institutional Conversion

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.

4. Perfect Team Complementarity

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.

5. Deus Ex Resources

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.

Integration

Inbound (feeds into this skill)
SkillWhat it provides
character-arcIndividual transformation arcs for team members
positional-revelationHow mundane roles create unexpected access
worldbuildingInstitutional systems to work within and against
Outbound (this skill enables)
SkillWhat this provides
dialogueTeam dynamics and conflict for dialogue scenes
scene-sequencingEscalating pressure structure for pacing
endingsEarned resolution through team development
Complementary
SkillRelationship
moral-parallaxUnderdog-unit creates institutional pressure; moral-parallax explores the ethical complexity of working within corrupt systems
story-senseUse story-sense to diagnose team dynamics problems; underdog-unit provides the formula structure

© jwynia, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/creative/fiction/character/underdog-unit of jwynia/agent-skills.

Open the folder on GitHubat commit e02ec7e

Compare with similar skills

Underdog Unit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Underdog Unit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Underdog Unit this skilljwynia/agent-skills170—~3.9kAutomated safety check: PassMIT
Unit Teststhedaviddias/Front-End-Checklist74k—~382Automated safety check: PassMIT
Warp Rust Unit Testswarpdotdev/warp65k1 repos~3.4kAutomated safety check: PassAGPL-3.0
Story ReadinessDonchitos/Claude-Code-Game-Studios26k—~6.9kAutomated safety check: PassMIT
Job Storiesphuryn/pm-skills27k—~743Automated safety check: PassMIT
User Storiesphuryn/pm-skills27k—~748Automated safety check: PassMIT

Similar skills

  • Unit Tests

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing CI coverage, automated checks, or test strategy related to Write unit tests.

    74k GitHub stars~382 tokensUpdated 4 days ago
    Testing & QAAuto-check passed

  • Warp Rust Unit Tests

    warpdotdev/warp

    Guides writing, improving and running crate-level Rust unit tests in the Warp codebase, and says when a unit test is the wrong level.

    65k GitHub starsUsed in 1 repo~3.4k tokens
    Testing & QAAuto-check passed

  • Story Readiness

    Donchitos/Claude-Code-Game-Studios

    Is a story implementation-ready?. An agent skill from Donchitos/Claude-Code-Game-Studios.

    26k GitHub stars~6.9k tokensUpdated 2 days ago
    Product & Project ManagementAuto-check passed

  • Job Stories

    phuryn/pm-skills

    Turns a feature into job stories in the When, I want to, so I can format, each with six to eight acceptance criteria tied to the user's situation and outcome.

    27k GitHub stars~743 tokensUpdated yesterday
    Product & Project ManagementAuto-check passed

  • User Stories

    phuryn/pm-skills

    Create user stories following the 3 C's (Card, Conversation, Confirmation) and INVEST criteria with descriptions, design links, and acceptance criteria.

    27k GitHub stars~748 tokensUpdated yesterday
    Product & Project ManagementAuto-check passed

  • Create Stories

    Donchitos/Claude-Code-Game-Studios

    Break one epic into implementable stories embedding TR-ID, ADR guidance, acceptance criteria.

    26k GitHub stars~7.3k tokensUpdated 2 days ago
    Product & Project ManagementAuto-check passed

More from jwynia/agent-skills

All 111 skills in this repo

  • Devcontainer

    jwynia/agent-skills

    Diagnose devcontainer configuration problems and guide development environment setup.

    170 GitHub stars~1.2k tokensUpdated 7 mo ago
    Auto-check: notes

  • Frontend Design

    jwynia/agent-skills

    Create distinctive, production-grade frontend interfaces with high design quality.

    170 GitHub stars~3.2k tokensUpdated 7 mo ago
    Auto-check passed

  • Gitea Workflow

    jwynia/agent-skills

    Orchestrate agile development workflows for Gitea repositories using the tea CLI.

    170 GitHub stars~3.8k tokensUpdated 7 mo ago
    Auto-check passed

  • Godot Asset Generator

    jwynia/agent-skills

    Generate game assets using AI image generation APIs (DALL-E, Replicate, fal.ai) and prepare them for Godot.

    170 GitHub stars~3.8k tokensUpdated 7 mo ago
    Auto-check passed

  • Mastra Hono

    jwynia/agent-skills

    Develop AI agents, tools, and workflows with Mastra v1 Beta and Hono servers.

    170 GitHub stars~2.9k tokensUpdated 7 mo ago
    Auto-check passed

  • PPTX Generator

    jwynia/agent-skills

    Create and manipulate PowerPoint PPTX files programmatically.

    170 GitHub stars~3.1k tokensUpdated 7 mo ago
    Auto-check passed

Questions about Underdog Unit

What does Underdog Unit do?

Generate stories about institutional outcasts given impossible mandates with minimal resources. Underdog Unit is an agent skill from jwynia/agent-skills. Generate stories about institutional outcasts given impossible mandates with minimal resources.

When should I use Underdog Unit?

Underdog Unit fits situations like: you want team dynamics in hostile institutions.

How do I install Underdog Unit in Claude Code?

Run `npx skills add jwynia/agent-skills --skill underdog-unit -a claude-code`. Or copy the skill folder (skills/creative/fiction/character/underdog-unit in jwynia/agent-skills) into .claude/skills/underdog-unit in your project. Claude Code loads it when a task matches its description.

How do I install Underdog Unit in Codex?

Run `npx skills add jwynia/agent-skills --skill underdog-unit -a codex`. Or copy the skill folder (skills/creative/fiction/character/underdog-unit in jwynia/agent-skills) into .agents/skills/underdog-unit in your project. Codex loads it when a task matches its description.

Can I use Underdog Unit in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jwynia/agent-skills --skill underdog-unit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/underdog-unit, .gemini/skills/underdog-unit, .github/skills/underdog-unit and .opencode/skills/underdog-unit in your project.

What does Underdog Unit need to run?

SKILL.md names no scripts, command-line tools or credentials: Underdog Unit is instructions for the agent only.

Does Underdog Unit access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Underdog Unit safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Underdog Unit use?

Underdog Unit is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Underdog Unit use?

About 3.9k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Underdog Unit?

Skills that share tags, products or a category with Underdog Unit: Unit Tests (thedaviddias/Front-End-Checklist, 74k stars), Warp Rust Unit Tests (warpdotdev/warp, 65k stars), Story Readiness (Donchitos/Claude-Code-Game-Studios, 26k stars) and Job Stories (phuryn/pm-skills, 27k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Underdog Unit?

jwynia (a GitHub user) maintains it in jwynia/agent-skills, which has 170 GitHub stars. The repository holds 111 skills in this directory. The repository was last updated on February 24, 2026.

Source: jwynia/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.