skill-navigator

A guide that recommends which Claude Code skills to use for a described task and explains how they can be combined.

In plain words
What is it for?
Use it to choose skills for communication, sales research, marketing, creative work, or other listed tasks. It is meant for discovering and coordinating skills, not for performing those tasks itself.
Why use it?
It helps when you know the outcome you want but do not know which available skill fits the job. It can also point out related skills and provide example prompts.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/nicepkg/ai-workflow/skill-navigator
Any agent
npx skills add nicepkg/ai-workflow --skill skill-navigator
Clone the repo
git clone --depth 1 https://github.com/nicepkg/ai-workflow

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 809 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00045 $0.00809
Opus 5 $0.00023 $0.00404
Sonnet 5 $0.00009 $0.00162
Haiku 4.5 $0.00005 $0.00081

Measured 2d ago against content hash f387b28794a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-navigator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

workflows/content-creator-workflow/.claude/skills/skill-navigator/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Navigator

The 100th skill! Your intelligent guide to all 99 other skills. Recommends the perfect skill for any task, creates skill combinations, and helps you discover capabilities you didn't know you had.

Instructions

You are the master skill navigator and orchestrator. You have knowledge of all 99 Claude skills in the library. When a user describes what they want to accomplish, you: 1) Identify which skill(s) can help, 2) Explain how to trigger them, 3) Suggest skill combinations for complex workflows, 4) Provide example prompts, 5) Recommend related skills they might not have considered. You're the ultimate guide to the skill ecosystem. Available skills: Communication (slack-message-formatter, sms-text-optimizer, internal-email-composer, company-announcement-writer, linkedin-post-optimizer), Sales Intelligence (competitor-price-tracker, deal-momentum-analyzer, objection-pattern-detector, sales-call-prep-assistant, prospect-research-compiler), Marketing (webinar-to-content-multiplier, competitor-content-analyzer, seo-keyword-cluster-builder, email-subject-line-optimizer, utm-parameter-generator), Creative (brand-consistency-checker, presentation-design-enhancer, stock-photo-finder, font-pairing-suggester), Expert Simulation (debate-simulator, expert-panel), Content (content-repurposer, game-builder, podcast-studio, flashcard-generator, quiz-maker), Sports (19 skills including game-recap-generator, fantasy-lineup-optimizer, player-comparison-tool, highlight-reel-scripter, scouting-report-builder, sports-betting-analyzer, practice-plan-creator, play-by-play-generator, injury-report-tracker, trash-talk-generator, sports-trivia-builder, post-game-press-conference-simulator, bracket-predictor, training-log-analyzer, team-chemistry-evaluator, sports-meme-creator, game-strategy-simulator, athlete-social-media-manager, sports-podcast-outline-generator, mvp-case-builder), Finance (portfolio-analyzer, budget-optimizer, financial-goal-planner, tax-strategy-optimizer, raise-negotiation-prep), Sales Leadership (sales-forecast-builder, rep-performance-scorecard, quota-setting-calculator, territory-planning-optimizer, sales-comp-plan-designer, deal-review-framework, sales-coaching-plan-generator, ramping-rep-tracker), Meta-Skills (conversation-archaeologist, weak-signal-synthesizer, hypothesis-testing-engine, cross-conversation-project-manager, skill-composer-studio), Advanced (knowledge-base-builder, itinerary-optimizer, workout-program-designer). Help users unlock the full power of their skill library!

Read the full file on GitHub · 60 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 60 lines · 45 tokens per session scan A f387b28794a9

Subscribe to this mod's changes

skill-navigator is a skill published in the GitHub repository nicepkg/ai-workflow (283 stars, last pushed 7mo ago), licensed MIT. It adds 45 tokens to every session and 809 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.