Skill collection
instructa/agent-skills agent skills
- skills
- 17
- GitHub stars
- 139
GitHub description: “A curated collection of agent-skills”
- Stars
- 139 (16 forks)
- Licence
- No licence
- Last push
- Sep 2026
- Created
- Dec 2025
Install all skills
npx skills add instructa/agent-skillsAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in instructa/agent-skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | A skill your agent uses when the user wants to turn an application, product, startup idea, SaaS, mobile app, web app, API, AI product, or internal tool into a production-ready Markdown specification… | instructa/ | 139 | — | ~1.5k | Automated safety check: Pass | No licence | 9 days ago |
| 2 | Have Codex review a feature or change from Claude Code, then let Claude address the findings and request verification. | instructa/ | 139 | — | ~1.6k | Automated safety check: Pass | No licence | 9 days ago |
| 3 | Find, clone, inspect, and summarize high-quality GitHub reference repositories for coding agents. | instructa/ | 139 | — | ~2.1k | Automated safety check: Pass | MIT | 9 days ago |
| 4 | Run or install repo security leak checks with BetterLeaks and Trivy. | instructa/ | 139 | — | ~557 | Automated safety check: Pass | No licence | 9 days ago |
| 5 | Delegate a bounded task from a Codex session to a Fable-powered Cursor Agent in the same Herdr workspace, then wait for and collect the result. | instructa/ | 139 | — | ~925 | Automated safety check: Pass | No licence | 9 days ago |
| 6 | Delegate a bounded task from a Codex session to Grok 4.6 with xhigh reasoning in the same Herdr workspace, then wait for and collect the result. | instructa/ | 139 | — | ~951 | Automated safety check: Pass | No licence | 9 days ago |
| 7 | Delegate a bounded task from a Codex session to GPT-5.6 Sol in the same Herdr workspace, then wait for and collect the result. | instructa/ | 139 | — | ~1.2k | Automated safety check: Pass | No licence | 9 days ago |
| 8 | Run local Go health checks (tests, coverage, lint) in Go repositories that contain go.mod/go.sum. | instructa/ | 139 | — | ~732 | Automated safety check: Pass | No licence | 9 days ago |
| 9 | Build, critique, and iterate high-converting marketing or product landing pages using React + Vite + TypeScript + Tailwind and shadcn/ui components, with all icons sourced from Iconify. | instructa/ | 139 | — | ~1.8k | Automated safety check: Pass | No licence | 9 days ago |
| 10 | Determine runtime owner, first-fix layer, and canonical long-term module or package owner in layered codebases. | instructa/ | 139 | — | ~1.3k | Automated safety check: Pass | No licence | 9 days ago |
| 11 | Live-test any Electron desktop app with native-devtools-mcp, Chrome DevTools Protocol, screenshots, OCR, and accessibility tools. | instructa/ | 139 | — | ~1.3k | Automated safety check: Pass | No licence | 9 days ago |
| 12 | 12.Shellck Run shellcheck on shell scripts after editing scripts or when debugging shell errors. | instructa/ | 139 | — | ~302 | Automated safety check: Pass | No licence | 9 days ago |
| 13 | 13.Clarify Turn complex, technical, ambiguous, or verbose material into clear language without losing important detail. | instructa/ | 139 | — | ~532 | Automated safety check: Pass | MIT | 9 days ago |
| 14 | Run a reusable JavaScript supply-chain security baseline with pnpm-first hardening, release-age gating, lifecycle-script controls, exotic dependency checks, CI install checks, and optional incident… | instructa/ | 139 | — | ~1.8k | Automated safety check: Pass | No licence | 9 days ago |
| 15 | Use Claude Code directly from Astra's current task to design or implement UI/UX and frontend work, with Astra owning sequencing, review, and integration. | instructa/ | 139 | — | ~966 | Automated safety check: Pass | No licence | 9 days ago |
| 16 | Find duplicate ownership, hidden second sources of truth, and contract drift in layered codebases. | instructa/ | 139 | — | ~1.3k | Automated safety check: Pass | No licence | 9 days ago |
| 17 | Publish CLIs/TUIs to Homebrew via a personal tap. An agent skill from instructa/agent-skills. | instructa/ | 139 | — | ~605 | Automated safety check: Pass | No licence | 9 days ago |
Questions, answered from the data.
What is the best skill in instructa/agent-skills?
App Spec Packager from instructa/agent-skills ranks first of the 17 skills in instructa/agent-skills listed here, with the highest score: its repository has 139 GitHub stars, its SKILL.md loads about 1.5k tokens and it passes the automated safety check with no findings. Next come Codex Reviewer and Search Context.
Are the skills in instructa/agent-skills official?
None yet. All 17 skills in instructa/agent-skills listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from instructa/agent-skills?
Run npx skills add instructa/agent-skills in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.