Repository
laude-institute/headlong agent skills
- skills
- 10
- GitHub stars
- 1.2k
GitHub description: “An open source agent microharness featuring persistent agency and recursive LLMs. Of bash, by bash, for bash; it's shells all the way down.”
- Stars
- 1,216 (127 forks)
- Licence
- Apache-2.0
- Last push
- Oct 2026
- Created
- Apr 2026
- Homepage
- headlong.ai
Install all skills
npx skills add laude-institute/headlongAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in laude-institute/headlong, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Explains how shellm's bash-based recursive LLM shell fits together - its core engine, identity system, memory, skills and trajectory log. | laude-institute/ | 1.2k | — | ~2k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 2 | Scaffolds new ShellLM skills with the right frontmatter, directory layout and agent-facing writing style, so an agent can extend its own capabilities. | laude-institute/ | 1.2k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 3 | Looks things up online from the shell with curl: fetching pages, searching DuckDuckGo's HTML endpoint, stripping tags for readable text and pulling JSON APIs. | laude-institute/ | 1.2k | — | ~362 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 4 | Drives Google Drive, Gmail, Calendar, Sheets, Docs and Chat from the shell with the gws CLI, including its sign-in, flags, helper commands and safety rules. | laude-institute/ | 1.2k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 5 | 5.Obsidian Read, write, search, and manage notes in an Obsidian vault. An agent skill from laude-institute/headlong. | laude-institute/ | 1.2k | — | ~880 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 6 | 6.Slack Talk with people on Slack — recognize slack- senders and reach them via chat reply | laude-institute/ | 1.2k | — | ~831 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 7 | 7.Telegram Send and receive messages via the Telegram Bot API using curl | laude-institute/ | 1.2k | — | ~623 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 8 | 8.Chat Reply to humans who are chatting with me. An agent skill from laude-institute/headlong. | laude-institute/ | 1.2k | — | ~1k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 9 | 9.Opencode Delegate a bounded coding task to OpenCode and review its retained candidate, patch, verification, and trajectory evidence. | laude-institute/ | 1.2k | — | ~383 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 10 | 10.Mem Life context and memory system | laude-institute/ | 1.2k | — | ~358 | Automated safety check: Pass | Apache-2.0 | yesterday |
Questions, answered from the data.
What is the best skill in laude-institute/headlong?
Shellm Architecture Reference from laude-institute/headlong ranks first of the 10 skills in laude-institute/headlong listed here, with the highest score: its repository has 1.2k GitHub stars, its SKILL.md loads about 2k tokens and it has informational notes only in the automated safety check. Next come ShellLM Skill Author and Web Research With curl.
Are the skills in laude-institute/headlong official?
None yet. All 10 skills in laude-institute/headlong 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 laude-institute/headlong?
Run npx skills add laude-institute/headlong 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.