claude-skills-journalism
jamditis
Claude Code skills for journalism, media, and academia - verification, FOIA, data journalism, academic writing, and more
GITHUB TOPIC
15projects include this topic
The "verification" topic on GitHub groups 15 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by claude-skills-journalism with 393 GitHub stars. claude-skills-journalism — Claude Code skills for journalism, media, and academia - verification, FOIA, data journalism, academic writing, and more. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
{count} projects
Exact GitHub Topic match
jamditis
Claude Code skills for journalism, media, and academia - verification, FOIA, data journalism, academic writing, and more
Apageoflove
ChangeProof — DeepSeek Harness plugin: after a code change, confirm the changed lines are really covered by tests
unknowbug
Code verification protocol for vibe coding — every claim must have a verifiable practice anchor.
030611
Privacy-minimal heuristic per-turn verification summaries for DeepSeek Harness
263311487-ux
The quality gate for agent-built web apps. Real-browser acceptance checks — CLI, MCP (Claude Code / Cursor / Copilot), GitHub Action. Agents self-test and pass; real browsers tell the truth.
AmethystLuna
Claim verification for AI coding agents — logic-primitive verification for state machines, data models, and concurrency risk in design docs & refactoring plans. Cross-platform Agent Skills + DSH native. | AI coding agent claim verification plugin: logic-primitive verification of design docs and refactoring plans, covering state machines, data models and concurrency risk, with before-and-after regression. Cross-platform Agent Skills + DSH native.
245678000000
Acceptance-driven autonomous completion for DeepSeek Harness. Done means verified.
863683348
Verification toolkit for DeepSeek Harness agents: evidence-based claim checking with line citations, config validation (JSON/YAML), HTTP URL, npm and GitHub submission-readiness probes.
bpc-oss
This repository does not yet provide a project description.
Foshowithit
RCOS operator control plane for DeepSeek Harness — GoalRunner, authority gates with explicit approval, three-truth verification (execution / capability / objective satisfaction), trust ladder and next-action, task identity rebuilt from Archon runs. Side-loaded, no fork.
7starsseeker
Fact-checking skill for DeepSeek Harness: multi-source verification against the open web, domestic and international ecosystems, optional TypeSafe Jev (System One) judgements.
Dely0
A DSH skill: fresh-context code review with a replayable evidence gate
jmche
LLM-as-a-Verifier plugin for DeepSeek Harness — fine-grained reward tools (verify_compare / verify_select / verify_track) with Probabilistic Pivot Tournament, plus a Best-of-N conversation mode with a Web settings panel.
zouyuanqing
Three-plane probabilistic verifier for DeepSeek Harness: tiered logprob/sample/template judges, seeded tournament best-of-N, layered context reflux.
zriyox
AI says "done"? Make it show evidence first: force tests before the goal is sealed, and check once more before wrapping up — DeepSeek Harness plugin / Make your dsh agent prove it's done: gated goal completion + turn-end verification