{ "markdown": "
\n\n\"techne\n\n# techne\n\n*Opinionated Claude Code skills for repo hygiene: audit builds, tame CI noise, hunt doc/code drift, keep linked repos in lockstep.*\n\n[![Validate](https://github.com/ajbarea/techne/actions/workflows/validate.yml/badge.svg)](https://github.com/ajbarea/techne/actions/workflows/validate.yml)\n[![Docs](https://github.com/ajbarea/techne/actions/workflows/docs.yml/badge.svg)](https://github.com/ajbarea/techne/actions/workflows/docs.yml)\n[![Python](https://img.shields.io/badge/Python-3.12+-3776AB?style=flat-square&logo=python&logoColor=white)](https://python.org)\n[![uv](https://img.shields.io/badge/uv-package_manager-DE5FE9?style=flat-square)](https://docs.astral.sh/uv/)\n[![Claude Code](https://img.shields.io/badge/Claude_Code-plugin-D97757?style=flat-square)](https://code.claude.com/docs)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg?style=flat-square)](LICENSE)\n\n
\n\n---\n\nInstallable as a single `/plugin`:\n\n```bash\n/plugin marketplace add ajbarea/techne\n/plugin install techne@techne\n```\n\n## What's in the box\n\n| Skill | What it does |\n| --- | --- |\n| `techne:audit` | Runs the repo's `make` targets in dependency order and reconciles terminal output against `logs/dev-*.log` archives. |\n| `techne:auto-commit` | Groups working-tree changes into a structured `COMMITS.md` plan for staged review before anything lands. |\n| `techne:catchup` | Reads every comment, review, and state change on a repo's issues and PRs since you last participated, then reports who is blocked on whom. |\n| `techne:ci-audit` | Audits GitHub Actions runs on the current branch/PR: surfaces warnings, failures, and noise; fixes what's fixable in-repo. |\n| `techne:deslop` | Scans comments and docstrings for AI-generated slop and proposes tightened rewrites. |\n| `techne:docs-site` | Maintains the Zensical-powered docs site: config, deploy pipeline, theming, link integrity. |\n| `techne:docsync` | Verifies documentation claims (CLI commands, paths, config keys, signatures) against the actual code. |\n| `techne:elenchus` | Adversarial pre-merge review: drives `/code-review`, then reproduces the load-bearing claim, traces every consumer across the whole repo, and walks a bug-class rubric for reachable destructive ops, unmirrored parallel-path guards, migration crashes, and dead-but-green features. |\n| `techne:paper` | Scaffolds a new paper dir (LaTeX + results-harvest + shared bib + portfolio row) in a papers-style monorepo so it builds on day one. |\n| `techne:paper-review` | Pre-submission novelty + reviewer pass for a draft paper: grounds every novelty/claim verdict in retrieved prior work, flags related-work gaps, and surfaces lab-overlap for disclosure. |\n| `techne:research-grounded` | Flags design decisions in IMPL/ROADMAP that lack `# research(YYYY-MM):` provenance, then web-searches to ground them. |\n| `techne:reslop` | Rewrites docstrings grounded in the implementation rather than deleting them outright. |\n| `techne:sisters` | Cross-repo drift audit across the sister repos listed in `~/.claude/techne.toml`. |\n| `techne:theoros` | Starts an observed live dev session: Claude drives the REPL in a named `tmux` session; you spectate read-only via `tmux attach -r`. |\n\n## Install\n\nAdd the marketplace and install the plugin from inside Claude Code:\n\n```bash\n/plugin marketplace add ajbarea/techne\n/plugin install techne@techne\n```\n\nSkills become available as `techne:` and can be invoked the same way as any other Claude Code skill.\n\n> **First-time setup:** techne is opinionated about a few conventions (Makefile pattern, dev-runner archive, `.claude/skill-context.md`). See [Conventions](docs/conventions.md) for the minimum each skill needs.\n\n## Configuration\n\n`techne:sisters` reads `~/.claude/techne.toml` at runtime (user-controlled config that lists the active sister repos to compare against).\n\n```toml\ngithub_user = \"your-github-username\"\nworkspace_root = \"/path/to/your/workspace\"\n\n[[sisters]]\nname = \"repo-one\"\nstatus = \"active\"\n\n[[sisters]]\nname = \"repo-two\"\nstatus = \"active\"\n\n[[sisters]]\nname = \"repo-three\"\nstatus = \"active\"\n```\n\nSet `status = \"backburner\"` to skip a repo without removing it.\n\n## How it fits together\n\n```\n~/.claude/techne.toml ← user-controlled sister-repo registry\n │\n ▼\ntechne (plugin)\n├── audit ── verifies build targets vs. logs/\n├── auto-commit ── groups diffs into COMMITS.md\n├── catchup ── who is blocked on whom since you last looked\n├── ci-audit ── reads gh runs, fixes warnings in-repo\n├── deslop ── flags AI-slop prose\n├── docs-site ── manages Zensical site + deploy\n├── docsync ── doc claims ↔ implementation\n├── elenchus ── adversarial pre-merge review (reproduce + trace + rubric)\n├── paper ── scaffolds a new paper dir (LaTeX + harvest)\n├── paper-review ── grounded novelty + reviewer pass for a draft\n├── research-grounded ── flags un-grounded design decisions\n├── reslop ── rewrites docstrings from code\n├── sisters ── cross-repo drift across sisters\n└── theoros ── observed tmux REPL session\n```\n\nEach skill is self-contained. Invoke one without pulling in the others. They share a convention of writing intermediate artifacts (plans, audit reports) to disk for human review before mutating the repo.\n\n## Why \"techne\"\n\nGreek τέχνη: craft, the practical knowledge of how to make a thing well. That's what these skills are for — the craft of keeping a repo honest: audits, drift checks, clean commits, clean prose.\n\n## License\n\nMIT.\n\n---\n\n
\n\n\n \n \"\"\n  2026 AJ Barea\n\n
\n", "bytes": 5939, "sha": "1f298753fdd619b738fae34f70af02f00595dbf6951c5f13493992a5108b0089", "repo_slug": "ajbarea/techne", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/plg_ajbarea_techne_techne_171c0656/readme" }