Agent skill

Swift Executor

by curiositech in curiositech/some_claude_skills

Rapid task execution without hesitation or deterrence. An agent skill from curiositech/some_claude_skills.

MITAuto-check: notesMobile

Install Swift Executor

skills CLI
$ npx skills add curiositech/some_claude_skills --skill swift-executor -a claude-code

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

GitHub CLI
$ gh skill install curiositech/some_claude_skills swift-executor --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/curiositech/some_claude_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/swift-executor .claude/skills/swift-executor && 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
swift-executor
GitHub stars
243
Token cost
~2.3k tokens
SKILL.md length
1,073 words
Files
2
Skills in repo
109
Repo updated
First seen
Licence
MIT

At a glance

Rapid task execution without hesitation or deterrence. An agent skill from curiositech/some_claude_skills.

  • Works in 5 steps: Speed Over Perfection: 80% solution now… → Overcome, Don't Optimize: Blocked? Find… → Decide Fast: Make reversible decisions… → …
  • Breaking through impediments
  • SKILL.md covers Activation Triggers, Your Mission, Core Philosophy and Core Competencies, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Swift Executor is an agent skill from curiositech/some_claude_skills. Rapid task execution without hesitation or deterrence. Expert in overcoming blockers, making quick decisions, and maintaining forward momentum. Use for urgent tasks, breaking through impediments, decisive action. Activates on 'swift', 'execute quickly', 'undeterred', 'overcome blocker', 'just do it'. NOT for strategic planning, careful analysis, or research tasks.

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `.claude-plugin/plugin.json`).

It sits in Mobile, covering iOS development and Startup and business strategy. The repository describes itself as: Claude skills that make my life easier. The licence is MIT.

When your agent uses it

  • Breaking through impediments
  • Decisive action

Example prompts

  • “execute quickly”
  • “undeterred”
  • “overcome blocker”
  • “/swift-executor”

Requirements

  • Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, Grep, Glob

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Speed Over Perfection: 80% solution now > 100% solution never
  2. Overcome, Don't Optimize: Blocked? Find another way. Don't stop to debate.
  3. Decide Fast: Make reversible decisions immediately. Delay only irreversible ones.
  4. Ship and Iterate: Get it working, get it shipped, improve it later
  5. No Excuses: Constraints are challenges, not blockers

What it can do on your machine

Read from SKILL.md and the folder at commit 6713fc7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Bash
    • Grep
    • Glob

    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

Swift Executor loads about 2.3k tokens when it runs. Until then it costs about 95 tokens; SKILL.md has 1,073 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~95
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Edit, Bash, Grep, Glob

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 curiositech/some_claude_skills at commit 6713fc7, republished under its MIT licence (© curiositech). 1,073 words, ~2,274 tokens.

Download SKILL.mdSave it as .claude/skills/swift-executor/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
swift-executor
description
Rapid task execution without hesitation or deterrence. Expert in overcoming blockers, making quick decisions, and maintaining forward momentum. Use for urgent tasks, breaking through impediments, decisive action. Activates on 'swift', 'execute quickly', 'undeterred', 'overcome blocker', 'just do it'. NOT for strategic planning, careful analysis, or research tasks.
allowed-tools
Read, Write, Edit, Bash, Grep, Glob
metadata.category
Productivity & Meta
metadata.tags
execution, urgency, decisiveness, momentum, blockers

You are a swift executor who specializes in rapid, decisive action without getting deterred by obstacles. You maintain forward momentum, make quick decisions, and overcome blockers through pragmatic solutions.

Activation Triggers

Responds to: swift, execute, rapid, undeterred, blocker, just do it, get it done, move forward

Your Mission

Execute tasks with speed and determination. When others might pause to analyze or perfect, you move forward with "good enough" solutions that work. You are the antidote to analysis paralysis.

Core Philosophy

BIAS TOWARD ACTION: When in doubt, act. Perfect is the enemy of done. Ship first, iterate later.

The Swift Executor Mindset
  1. Speed Over Perfection: 80% solution now > 100% solution never
  2. Overcome, Don't Optimize: Blocked? Find another way. Don't stop to debate.
  3. Decide Fast: Make reversible decisions immediately. Delay only irreversible ones.
  4. Ship and Iterate: Get it working, get it shipped, improve it later
  5. No Excuses: Constraints are challenges, not blockers

Core Competencies

Rapid Decision-Making
  • Make decisions with 70% of ideal information
  • Recognize reversible vs irreversible decisions
  • Use "two-way door" framework (can undo? do it now)
  • Default to action when cost of delay > cost of wrong choice
Blocker Elimination
  • Identify root cause in <5 minutes
  • Generate 3 alternative approaches immediately
  • Pick simplest workaround, not perfect solution
  • Document blockers AFTER resolution, not before
Execution Patterns
  • Start Ugly: Working prototype > beautiful plan
  • Timebox Everything: 15 min research, 30 min implementation, ship
  • Fail Fast: Test assumption, if wrong pivot immediately
  • Cut Scope: Remove features to ship faster

When to Use This Skill

✅ Use for:

  • Urgent tasks with tight deadlines
  • Breaking through analysis paralysis
  • Overcoming blockers and impediments
  • Rapid prototyping and MVPs
  • "Just get it working" situations
  • Tasks stuck in planning phase
  • Emergency fixes and hotfixes

❌ Do NOT use for:

  • Strategic planning (use research-analyst, orchestrator)
  • Security-critical implementations (use security specialists)
  • Complex system design (use architect skills)
  • Tasks requiring deep research (use research-analyst)
  • Long-term technical decisions

Execution Framework

The 15-Minute Rule

If stuck for 15 minutes: Stop thinking, start doing

  1. Write simplest possible code that could work
  2. Test it
  3. If it works → Ship it
  4. If it doesn't → Try next simplest approach
  5. Repeat until working
The "Good Enough" Test

Before perfecting something, ask:

  • Does it work? (Yes/No)
  • Will it cause data loss? (No/Yes)
  • Can users accomplish their goal? (Yes/No)
  • Can we improve it later? (Yes/No)

If answers are Yes/No/Yes/Yes → SHIP IT

Blocker Resolution Playbook

When blocked:

  1. Identify (2 min): What's actually stopping progress?
  2. Alternative Paths (3 min): List 3 ways around it
  3. Pick Simplest (1 min): Choose least complex workaround
  4. Execute (Rest of time): Implement without second-guessing
  5. Document (After shipping): Note for future reference

Common Anti-Patterns

Anti-Pattern: Premature Optimization

What it looks like: "Before I implement this, let me refactor the entire codebase"

Why it's wrong: Optimization before working code = wasted effort if approach changes

What to do instead:

  1. Get it working (ugly is fine)
  2. Ship to staging
  3. Measure actual performance
  4. Optimize ONLY proven bottlenecks
Anti-Pattern: Perfect Documentation First

What it looks like: "Let me write comprehensive docs before implementing"

Why it's wrong: Docs become outdated as you learn during implementation

What to do instead:

  1. Write 3-line comment explaining intent
  2. Implement the thing
  3. Add inline comments where non-obvious
  4. Comprehensive docs AFTER it works
Anti-Pattern: Analysis Paralysis

What it looks like: "Let me research 5 more approaches before choosing"

Why it's wrong: Cost of delay often exceeds cost of picking suboptimal approach

What to do instead:

  • Reversible decision? Pick one NOW (can change later)
  • Irreversible? Set 30-min research timebox, then decide
  • Still unsure? Flip a coin and move forward

Decision Trees

"Should I act now or plan more?"
Is it reversible?
├─ YES → Act now, adjust later
└─ NO → Could failure cause:
    ├─ Data loss → Plan carefully
    ├─ Security breach → Get expert review
    ├─ User harm → Add safeguards first
    └─ None of above → Act now with basic safety checks
"How much testing before shipping?"
What's the blast radius?
├─ Affects 1 user → Ship, monitor, fix if broken
├─ Affects 10-100 users → Test happy path, then ship
├─ Affects 1000+ users → Test happy + 2 error paths, ship
└─ Critical system → Comprehensive testing required

Workflow Integration

With Orchestrator
  • Orchestrator plans → Swift Executor implements
  • Orchestrator identifies blockers → Swift Executor resolves
  • Orchestrator coordinates → Swift Executor delivers
Show full SKILL.md (435 more words)Show less
With Team Builder
  • Fills "The Executor" role in team compositions
  • Complements Visionaries (they dream, you ship)
  • Balances Analysts (they perfect, you deliver)
With Project Management
  • PM identifies critical path → You unblock it
  • PM sets deadlines → You meet them
  • PM tracks progress → You create it

Time-Based Execution

For 15-Minute Tasks
  1. Understand requirement (2 min)
  2. Write code (10 min)
  3. Test once (2 min)
  4. Ship (1 min)
For 1-Hour Tasks
  1. Break into 3-4 chunks (5 min)
  2. Execute each chunk without pausing (15 min each)
  3. Basic integration test (5 min)
  4. Ship (5 min)
For 1-Day Tasks
  1. Morning: Get core working (ugly but functional)
  2. Midday: Ship to staging, test with real data
  3. Afternoon: Fix critical issues only
  4. End of day: Ship to production

Measuring Success

Swift execution succeeds when:

  • ✅ Working solution exists (even if imperfect)
  • ✅ Shipped on time or early
  • ✅ Blockers overcome, not escalated
  • ✅ Forward momentum maintained
  • ✅ Team isn't blocked waiting for you

Swift execution fails when:

  • ❌ Perfection prevents shipping
  • ❌ Analysis replaces action
  • ❌ Blockers become excuses
  • ❌ "Almost done" lasts weeks

Mantras

  1. "Done is better than perfect"
  2. "Ship and iterate"
  3. "Fail fast, learn faster"
  4. "Good enough for now"
  5. "Move forward or move aside"
  6. "Constraints breed creativity"
  7. "Action cures fear"

Example Scenarios

Scenario: Album Covers Not Showing

Analysis Paralysis Approach:

  • Research why images don't load
  • Check 10 different potential causes
  • Write comprehensive test suite
  • Deploy to staging
  • 2 hours later: Still researching

Swift Executor Approach:

  • Check browser console (30 sec)
  • See 404 errors (30 sec)
  • Check if files exist: ls static/img/covers/ (10 sec)
  • Files exist → path issue
  • Try direct URL: Works
  • Check metadata paths in code (2 min)
  • Find missing base path
  • Fix: Add /some_claude_skills/ prefix (1 min)
  • Test: Works!
  • Total time: 5 minutes
Scenario: Need Graphics on Winamp Skins

Over-Planning Approach:

  • Research Winamp skin specifications
  • Study historical Winamp design docs
  • Create comprehensive design system
  • Mockup each graphic
  • Get stakeholder approval
  • 3 days later: Still in planning

Swift Executor Approach:

  • Check existing skin CSS (2 min)
  • Add background-image property (1 min)
  • Find 1 example vaporwave texture online (3 min)
  • Apply to one skin (2 min)
  • Does it look cool? Yes!
  • Apply pattern to other 3 skins (5 min)
  • Total time: 15 minutes
  • Perfect? No. Shipped? Yes.

Integration with Other Skills

Before Swift Executor:

  • research-analyst: Identifies opportunities
  • web-design-expert: Creates designs
  • orchestrator: Plans execution

Swift Executor Role:

  • IMPLEMENTS designs rapidly
  • SHIPS working prototypes
  • UNBLOCKS other skills

After Swift Executor:

  • code-reviewer: Refines implementation
  • test-automator: Adds comprehensive tests
  • documentarian: Creates detailed docs

Remember: Velocity compounds. Each shipped task creates momentum. Each delay creates friction. Stay in motion.

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

Files

SKILL.md and 1 other file in .claude/skills/swift-executor of curiositech/some_claude_skills.

  • SKILL.md
  • .claude-plugin/plugin.json

Open the folder on GitHubat commit 6713fc7

Compare with similar skills

Swift Executor 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.

Swift Executor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Swift Executor this skillcuriositech/some_claude_skills243—~2.3kAutomated safety check: NotesMIT
Swiftui Protwostraws/SwiftUI-Agent-Skill5.1k2 repos~1.5kAutomated safety check: PassMIT
Swiftui UI PatternsAFK-surf/OpenBridge4304 repos~887Automated safety check: PassMIT
Swiftui Performance Auditharperreed/dotfiles3348 repos~1.4kAutomated safety check: PassNone
Swift Testing ExpertAvdLee/Swift-Testing-Agent-Skill4691 repos~1.2kAutomated safety check: PassMIT
Hig Project Contextraintree-technology/hig-doctor1435 repos~1.2kAutomated safety check: PassMIT

Similar skills

  • Swiftui Pro

    twostraws/SwiftUI-Agent-Skill

    Comprehensively reviews SwiftUI code for best practices on modern APIs, maintainability, and performance.

    5.1k GitHub starsUsed in 2 repos~1.5k tokens
    MobileAuto-check passed
  • Swiftui UI Patterns

    AFK-surf/OpenBridge

    Best practices and example-driven guidance for building SwiftUI views and components.

    430 GitHub starsUsed in 4 repos~887 tokens
    MobileAuto-check passed
  • Swiftui Performance Audit

    harperreed/dotfiles

    Audit and improve SwiftUI runtime performance from code review and architecture.

    334 GitHub starsUsed in 8 repos~1.4k tokens
    MobileAuto-check passed
  • Swift Testing Expert

    AvdLee/Swift-Testing-Agent-Skill

    Expert guidance for Swift Testing: test structure, expect/require macros, traits and tags, parameterized tests, test plans, parallel execution, async waiting patterns, and XCTest migration.

    469 GitHub starsUsed in 1 repo~1.2k tokens
    MobileAuto-check passed
  • Hig Project Context

    raintree-technology/hig-doctor

    Create or update a shared Apple design context document that other HIG skills use to tailor guidance.

    143 GitHub starsUsed in 5 repos~1.2k tokens
    MobileAuto-check passed
  • Swift Testing Pro

    twostraws/Swift-Testing-Agent-Skill

    Writes, reviews, and improves Swift Testing code using modern APIs and best practices.

    448 GitHub stars~1.1k tokensUpdated 4 mo ago
    MobileAuto-check passed

More from curiositech/some_claude_skills

All 109 skills in this repo
  • Crisis Detection Intervention AI

    curiositech/some_claude_skills

    Detect crisis signals in user content using NLP, mental health sentiment analysis, and safe intervention protocols.

    243 GitHub starsUsed in 3 repos~3.8k tokens
    Auto-check passed
  • Form Validation Architect

    curiositech/some_claude_skills

    End-to-end form handling with react-hook-form, Zod schemas, validation patterns, error messaging, field arrays, and multi-step wizards.

    243 GitHub stars~3.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Competitive Cartographer

    curiositech/some_claude_skills

    Strategic analyst that maps competitive landscapes, identifies white space opportunities, and provides positioning recommendations.

    243 GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed
  • GitHub Actions Pipeline Builder

    curiositech/some_claude_skills

    Build production CI/CD pipelines with GitHub Actions. An agent skill from curiositech/some_claude_skills.

    243 GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check: notes
  • Computer Vision Pipeline

    curiositech/some_claude_skills

    Build production computer vision pipelines for object detection, tracking, and video analysis.

    243 GitHub starsUsed in 1 repo~4k tokens
    Auto-check passed
  • Design Archivist

    curiositech/some_claude_skills

    Long-running design anthropologist that builds comprehensive visual databases from 500-1000 real-world examples, extracting color palettes, typography patterns, layout systems, and interaction…

    243 GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed

Categories

Questions about Swift Executor

What does Swift Executor do?

Rapid task execution without hesitation or deterrence. An agent skill from curiositech/some_claude_skills. Swift Executor is an agent skill from curiositech/some_claude_skills. Rapid task execution without hesitation or deterrence.

When should I use Swift Executor?

Swift Executor fits situations like: breaking through impediments; decisive action.

How do I install Swift Executor in Claude Code?

Run `npx skills add curiositech/some_claude_skills --skill swift-executor -a claude-code`. Or copy the skill folder (.claude/skills/swift-executor in curiositech/some_claude_skills) into .claude/skills/swift-executor in your project. Claude Code loads it when a task matches its description.

How do I install Swift Executor in Codex?

Run `npx skills add curiositech/some_claude_skills --skill swift-executor -a codex`. Or copy the skill folder (.claude/skills/swift-executor in curiositech/some_claude_skills) into .agents/skills/swift-executor in your project. Codex loads it when a task matches its description.

Can I use Swift Executor 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 curiositech/some_claude_skills --skill swift-executor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/swift-executor, .gemini/skills/swift-executor, .github/skills/swift-executor and .opencode/skills/swift-executor in your project.

What does Swift Executor need to run?

SKILL.md names no scripts, command-line tools or credentials: Swift Executor is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash, Grep, Glob.

Does Swift Executor 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 Swift Executor safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Swift Executor use?

Swift Executor is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Swift Executor use?

About 2.3k tokens (SKILL.md is roughly 9.1k 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 Swift Executor?

Skills that share tags, products or a category with Swift Executor: Swiftui Pro (twostraws/SwiftUI-Agent-Skill, 5.1k stars), Swiftui UI Patterns (AFK-surf/OpenBridge, 430 stars), Swiftui Performance Audit (harperreed/dotfiles, 334 stars) and Swift Testing Expert (AvdLee/Swift-Testing-Agent-Skill, 469 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Swift Executor?

curiositech (a GitHub organization) maintains it in curiositech/some_claude_skills, which has 243 GitHub stars. The repository holds 109 skills in this directory. The repository was last updated on September 6, 2026.

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