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.
npx skills add bestdeejay-design/agent-skills --skill skill-suggestergit clone --depth 1 https://github.com/bestdeejay-design/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bestdeejay-design/agent-skills/skill-suggester)<a href="https://agentmods.dev/skills/bestdeejay-design/agent-skills/skill-suggester"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/skill-suggester/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bestdeejay-design/agent-skills/skill-suggester"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/skill-suggester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00142 | $0.01711 |
| Opus 5 | $0.00071 | $0.00856 |
| Sonnet 5 | $0.00028 | $0.00342 |
| Haiku 4.5 | $0.00014 | $0.00171 |
Grade A, and why
skill-suggester 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Suggester — подбор скиллов по задаче
Помощник, который по свободному описанию задачи/намерения пользователя подсказывает,
какой скилл из библиотеки agent-skills использовать и как их комбинировать.
When to use
Загружай этот скилл, когда пользователь не знает, какой скилл применить:
- «какой скилл использовать для …», «какой skill подойдёт», «что выбрать»
- «подбери инструмент / команду / навык под задачу»
- «рекомендуй скилл», «suggest skill», «skill suggestion»
- задача сформулирована свободным текстом, но без явного указания скилла
- нужно понять, какие скиллы можно объединить в цепочку для многоэтапной работы
Do NOT use
- Когда задача уже явно называет скилл («сделай презентацию» →
presentation-maker, «сгенерируй тестовые картинки» →test-graphics) — загружай его напрямую. - Когда пользователь просит выполнить работу, а не выбрать инструмент.
- Для подбора инструментов вне библиотеки (это не каталог внешних утилит).
What this skill does
Вход: описание задачи свободным текстом (одна строка или фраза).
Выход:
- Список подходящих скиллов с релевантностью (score) и кратким «почему использовать».
- Не больше 3 комбо — последовательностей скиллов для многоэтапной задачи
(например,
code-review → commit-message-writer → github-repo-hygiene).
How to work
- Спросить задачу. Если пользователь не дал описание — уточни, что он хочет сделать (одним вопросом). Если описание есть — переходи к шагу 2.
- Прочитать базу. Открой
index.jsonв корне репозитория и прочитай у каждого скилла поляname,triggers,description,category. При необходимости загляни вskills/<name>/SKILL.mdдля деталей. - Сопоставить. Сравни запрос с триггерами и описаниями скиллов. Учти синонимы и перефразировки (RU/EN). Определи категорию задачи (repository / media / social / code / data) и отметь скиллы этой категории.
- Выдать рекомендацию. Отсортируй по релевантности, выведи топ-3–5:
rank. skill-name (score) — почему использовать. Если задача многоэтапная — предложи до 3 комбо-цепочек.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 119 lines · 142 tokens per session scan A 1bff526ce402
skill-suggester is a skill published in the GitHub repository bestdeejay-design/agent-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 142 tokens to every session and 1,711 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
workflow
Use when a task is too large for turn-by-turn orchestration and should run through the big-task workflow lane: system-wide changes, large migrations, repo-wide audits, high-confidence verification, or tasks explicitly asking to run a workflow. Claude Code uses native dynamic workflows; Codex, OpenCode, and Grok use…
skill-compiler
Automatic solved-to-skill compiler — detects novel task completions and autonomously drafts new SKILL.md files. Stolen from Hermes Agent's learning loop (NousResearch, 2026-05-11).
context-compactor
9-section context compression with analysis scratchpad. Adapted from Claude Code's /compact system (2026-03-31).
daemon-loop
Autonomous recurring agent tasks — converts workflows into persistent background daemons that run on intervals. Stolen from Boris Cherny's Claude Code /loop pattern (2026-03-31).
trade-journal-analyzer
Unified post-trade analytics: journal pattern extraction + drawdown classification. Absorbs: drawdown-classifier.
Deep Research Loop
Multi-step web research, compilation, and synthesis workflow. Scrapes multiple sources, cross-references claims, and produces a structured research brief.