Skip to content
Back to search

techne

Forcing-function skills for AI agents — validated to improve behavior, not just change it.

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/lynxlangya--techne/badge.svg)](/listings/lynxlangya--techne)

HTML

<a href="/listings/lynxlangya--techne"><img src="/api/listings/lynxlangya--techne/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

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

**Recommended: ask your AI agent.** Paste this into Claude Code or Codex:

Install techne for my current agent by following https://github.com/lynxlangya/techne/blob/main/INSTALL.md, then verify the techne skills are available.

The agent reads [INSTALL.md](INSTALL.md), detects your harness (Claude / Codex / Cursor / Gemini / Kimi), runs the right install path, and confirms the skill works.

**Manual:** per-harness commands and the universal `npx skills` fallback are in [INSTALL.md](INSTALL.md).

For Claude Code:

/plugin marketplace add lynxlangya/techne
/plugin install techne@techne-dev
/reload-plugins

For Codex:

npx skills add lynxlangya/techne -a codex -g -y

See [WORKFLOW.md](WORKFLOW.md) for the delivery process and [ROADMAP.md](ROADMAP.md) for the product map.

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 · 20 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "techne-dev",
  3. "description": "Development marketplace for the techne skills plugin.",
  4. "owner": {
  5. "name": "lynxlangya",
  6. "email": "lynxlangya@gmail.com"
  7. },
  8. "plugins": [
  9. {
  10. "name": "techne",
  11. "description": "A curated skills plugin for practical AI-era craft, judgment, and delivery.",
  12. "version": "0.1.0",
  13. "source": "./",
  14. "author": {
  15. "name": "lynxlangya",
  16. "email": "lynxlangya@gmail.com"
  17. }
  18. }
  19. ]
  20. }
README.md · README · 90 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # techne
  2. > **τέχνη** · /ˈtɛk.niː/ · "TEK-nee"
  3. Ancient Greek for **craft · skill · art**: the practical know-how of *making*
  4. and *doing*, and the shared root of both **technique** and **technology**.
  5. Aristotle placed *technē* (knowing **how**) beside *epistēmē* (knowing
  6. **that**).
  7. Skills and agents for the AI era.
  8. Website: [techne.wangyun.fan](https://techne.wangyun.fan).
  9. Chinese version: [README-CN.md](README-CN.md).
  10. ## What This Is
  11. techne is a curated library of skills and agent assets for practical AI-era
  12. work. A techne skill is not a prompt snippet. It is a forced cognitive move: a
  13. small procedure that makes an AI collaborator investigate, judge, write, code,
  14. or ship in a way it often skips under pressure.
  15. The project keeps one shared source of truth in `skills/`. Host-specific files
  16. stay thin: Claude Code plugin metadata, Cursor and Gemini manifests, and install
  17. instructions for Codex, Kimi, and other Agent Skills hosts all point back to the
  18. same skill bodies.
  19. ## Skills
  20. The current seeded skills use the `anchor-*` prefix because each one anchors AI
  21. work to evidence it cannot self-report or fake: a source tree, run ledger, git
  22. diff, or written brief.
  23. - `anchor-viz` — investigate a real codebase by diagramming it. It routes one user
  24. request across architecture, interaction, data-model, state-model, and
  25. type-structure diagrams, then validates and builds a local viewer. See
  26. [skills/anchor-viz/README.md](skills/anchor-viz/README.md) for detailed usage.
  27. - `anchor-repro` — force bug fixes through a failing reproduction first, then verify
  28. with the same probe after the fix. See
  29. [skills/anchor-repro/README.md](skills/anchor-repro/README.md) for detailed usage.
  30. - `anchor-vet` — force code review through computed scope, accounted blast radius,
  31. verified claims/findings, and admissible verdicts before approving or
  32. requesting changes. See [skills/anchor-vet/README.md](skills/anchor-vet/README.md) for
  33. detailed usage.
  34. - `anchor-intake` — interrogate a written engineering implementation brief before work
  35. starts, accounting the fixed rubric, surfacing gaps/traps/questions, and
  36. emitting an intent-level plan. See
  37. [skills/anchor-intake/README.md](skills/anchor-intake/README.md) for detailed usage.
  38. ## Install
  39. **Recommended: ask your AI agent.** Paste this into Claude Code or Codex:
  40. ```text
  41. Install techne for my current agent by following https://github.com/lynxlangya/techne/blob/main/INSTALL.md, then verify the techne skills are available.
  42. ```
  43. The agent reads [INSTALL.md](INSTALL.md), detects your harness (Claude / Codex /
  44. Cursor / Gemini / Kimi), runs the right install path, and confirms the skill
  45. works.
  46. **Manual:** per-harness commands and the universal `npx skills` fallback are in
  47. [INSTALL.md](INSTALL.md).
  48. For Claude Code:
  49. ```text
  50. /plugin marketplace add lynxlangya/techne
  51. /plugin install techne@techne-dev
  52. /reload-plugins
  53. ```
  54. For Codex:
  55. ```bash
  56. npx skills add lynxlangya/techne -a codex -g -y
  57. ```
  58. See [WORKFLOW.md](WORKFLOW.md) for the delivery process and
  59. [ROADMAP.md](ROADMAP.md) for the product map.
  60. ## Documentation
  61. Public-facing documentation is split by language:
  62. - `README.md` is the default English document.
  63. - `README-CN.md` is the Chinese companion document.
  64. The same convention applies to skill usage guides when a Chinese version is
  65. needed, for example `skills/anchor-viz/README.md` and `skills/anchor-viz/README-CN.md`.

Ratings and comments

Sign in to rate this skill.

Sign in

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