Skip to content
Back to search

riyasaat-ai-skills

MarketplaceWorks with Claude CodeGitHub

Agent skills for Claude Code, Claude.ai, Codex and Cursor. Starting with at-a-glance: AI answers you can read in seconds.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/riyasaatahmed--riyasaat-ai-skills/badge.svg)](/listings/riyasaatahmed--riyasaat-ai-skills)

HTML

<a href="/listings/riyasaatahmed--riyasaat-ai-skills"><img src="/api/listings/riyasaatahmed--riyasaat-ai-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**Any agent, with the skills CLI:**

npx skills add RiyasaatAhmed/riyasaat-ai-skills                   # all skills
npx skills add RiyasaatAhmed/riyasaat-ai-skills --skill at-a-glance  # one skill

**Claude Code, as a plugin:**

/plugin marketplace add RiyasaatAhmed/riyasaat-ai-skills
/plugin install at-a-glance@riyasaat-ai-skills

**Claude Code, by hand:** copy a folder from `skills/` to `~/.claude/skills/`.

**Claude.ai:** zip a folder from `skills/` and upload it under Settings, Capabilities, Skills.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 19 lines
  1. {
  2. "name": "riyasaat-ai-skills",
  3. "owner": {
  4. "name": "Riyasaat Ahmed"
  5. },
  6. "metadata": {
  7. "description": "Agent skills by Riyasaat Ahmed for Claude Code, Claude.ai and other agents.",
  8. "version": "1.0.0"
  9. },
  10. "plugins": [
  11. {
  12. "name": "at-a-glance",
  13. "description": "Makes AI responses readable at a glance: answer first, tables and steps, no filler.",
  14. "source": "./",
  15. "strict": false,
  16. "skills": ["./skills/at-a-glance"]
  17. }
  18. ]
  19. }
README.md · README · 86 lines
  1. # Riyasaat's AI skills
  2. Agent skills for Claude Code, Claude.ai, Codex, Cursor and other agents that read `SKILL.md`.
  3. ## Skills
  4. | Skill | What it does |
  5. |---|---|
  6. | [at-a-glance](skills/at-a-glance) | Makes AI answers readable in seconds: answer first, tables and steps, no filler. |
  7. ## Install
  8. **Any agent, with the skills CLI:**
  9. ```
  10. npx skills add RiyasaatAhmed/riyasaat-ai-skills # all skills
  11. npx skills add RiyasaatAhmed/riyasaat-ai-skills --skill at-a-glance # one skill
  12. ```
  13. **Claude Code, as a plugin:**
  14. ```
  15. /plugin marketplace add RiyasaatAhmed/riyasaat-ai-skills
  16. /plugin install at-a-glance@riyasaat-ai-skills
  17. ```
  18. **Claude Code, by hand:** copy a folder from `skills/` to `~/.claude/skills/`.
  19. **Claude.ai:** zip a folder from `skills/` and upload it under Settings, Capabilities, Skills.
  20. ## Updates
  21. Every commit to `main` is a new version. No version number to bump.
  22. | Installed with | Get updates |
  23. |---|---|
  24. | **Claude Code plugin** | Turn on auto-update once: `/plugin`, then **Marketplaces**, then `riyasaat-ai-skills`. Or update by hand with `/plugin marketplace update riyasaat-ai-skills`. |
  25. | **Skills CLI** | `npx skills update` |
  26. | **By hand or Claude.ai** | Copy or upload the folder again. |
  27. ## at-a-glance
  28. | Step | What changes |
  29. |---|---|
  30. | **Answer first** | Line 1 is the answer. No warm-up. |
  31. | **Shape** | A short paragraph by default. Tables for comparisons, numbered lists for steps. Bold only labels and one key phrase. |
  32. | **Rules** | Short sentences, short paragraphs, plain words. Targets, not laws. |
  33. | **Cut filler** | No "Great question!", no recaps, no stacked hedges. |
  34. | **Length budget** | A yes / no question gets 1 to 2 lines. Asking for depth skips the budget. |
  35. | **Scan test** | Read only the first line and first words. The point still lands. |
  36. | **Facts stay** | Shorter never drops a warning or a condition, or sounds surer than the facts. |
  37. **Make it always on:** Claude loads a skill when the request matches its description. To apply it to every answer, add this line to your `CLAUDE.md`:
  38. ```
  39. Use the at-a-glance skill for every answer longer than 2 sentences.
  40. ```
  41. **Check a draft:** `scan_check.py` flags long sentences, long paragraphs, em-dashes, filler phrases and bolded whole sentences. It needs only Python 3, and prints nothing when the text is clean.
  42. ```
  43. python3 skills/at-a-glance/scan_check.py - < draft.md
  44. ```
  45. See [examples.md](skills/at-a-glance/examples.md) for before and after pairs, and [evals.md](skills/at-a-glance/evals.md) for test cases to run after a change.
  46. ## Add a new skill
  47. 1. Copy `template/` to `skills/<skill-name>/`.
  48. 2. Set `name:` in `SKILL.md` to the folder name.
  49. 3. Add a row to the **Skills** table above.
  50. 4. Add a plugin entry to `.claude-plugin/marketplace.json`.
  51. **Naming rules** (from the [Agent Skills spec](https://github.com/agentskills/agentskills/blob/main/docs/specification.mdx)):
  52. | Rule | Example |
  53. |---|---|
  54. | **Lowercase letters, digits and single hyphens** | `at-a-glance`, not `At_A_Glance` |
  55. | **64 characters at most** | |
  56. | **Folder name matches `name:`** | `skills/at-a-glance/` holds `name: at-a-glance` |
  57. | **No "claude" or "anthropic"** | These words are reserved. |
  58. | **Say what it does** | Anthropic suggests a verb form like `writing-commits`. Short names like `tldr` are also common. |
  59. ## License
  60. [MIT](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.