InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

137 results with any of your words Clear search and filters
  1. fulcra-tools

    Skills

    Long-running AI agents coordinating over their human's own Fulcra account — shared bus, cross-model reviews, session continuity, load balancing. Unofficial, MIT.

    Stale GitHub, ashfulcra 10 ★MITUpdated 9 days ago

    git clone https://github.com/ashfulcra/fulcra-tools.git
  2. socialforge

    Skills

    An open-source social media production system that turns a content calendar into on-brand copy, images, video, and client-ready delivery - with compliance and human approval built in.

    Stale GitHub, indranilbanerjee 43 ★MITUpdated 10 days ago

    git clone https://github.com/indranilbanerjee/socialforge.git
  3. Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

    Stale Agent skill collections on GitHub, obra MIT1 note

  4. Graduate-application planning workspace for AI agents — the LLM does the judgement, deterministic validators keep it honest. Sourced program evaluations, evidence-grounded CVs and statement drafts, nothing final without human review.

    Stale GitHub, TianCZeng 5 ★MITUpdated 19 days ago

    git clone https://github.com/TianCZeng/admissions-ops.git
  5. pixellab-pip

    Skills

    Meet PixelLab Pip: a tiny pup who fetches the right PixelLab workflow. He follows human commands to create, edit, and animate pixel assets, then sniffs out a bigger prompt, scouts for a useful tool, and carries back what happened.

    Indexed GitHub, Shilo 47 ★MITUpdated yesterday

    git clone https://github.com/Shilo/pixellab-pip.git
  6. Turns issues into merged PRs/MRs with zero human intervention — supports GitHub and GitLab, and Claude Code, Codex CLI, Kiro CLI, Antigravitiy CLI, opencode, and other agent CLIs.

    Stale GitHub, zxkane 40 ★Updated 6 days ago

    git clone https://github.com/zxkane/autonomous-dev-team.git
  7. Australian tax and accounting agent skills for Claude Code and Codex: BAS, FBT, Division 7A, trusts, payroll and practice compliance, with primary sources and human review.

    Indexed GitHub, ryanduguid 10 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/ryanduguid/australian-accounting-skills.git
  8. Markdown + git methodology for human and AI software teams: planning, Definition of Done, coordination, handoffs, and verification. Fourteen docs and templates. CC BY 4.0.

    Stale GitHub, Korner83 5 ★CC-BY-4.0Updated 30 days ago

    git clone https://github.com/Korner83/ai-development-methodology.git
  9. Agent skill to clean up AI-generated code: audit, refactor and guard vibe-coded codebases with Claude Code, Cursor or Codex. A human approves every decision.

    Indexed GitHub, fictormarcel2 5 ★MITUpdated 6 days ago

    git clone https://github.com/fictormarcel2/untangle-everything.git
  10. charm-os

    Skills

    CharmOS / C(H+A)RM — open-source framework to manage humans AND AI agents as first-class relationships, on a personal second brain, driven by the RDR loop (Recall to Deep Research). Manifest-first, Apache-2.0.

    Indexed GitHub, tonydzi 6 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/tonydzi/charm-os.git
  11. kluris

    Skills

    Kluris gives AI coding agents shared, human-curated team knowledge: git-backed brains of markdown that agents search and update through per-brain skills and a native CLI.

    Stale GitHub, ngvoicu 7 ★MITUpdated 10 days ago

    git clone https://github.com/ngvoicu/kluris.git
  12. A gated 25-step pipeline for validating and launching a business idea with Claude Code. Evidence over assumption, a fresh-context critic and a human signature at every step, three gates that can kill the idea. 23 skills, 4 subagents, 2 workflows, an approval hook, evals and CI. MIT.

    Indexed GitHub, marian-kamenistak 10 ★Custom licence (see repository)Updated 3 days ago

    git clone https://github.com/marian-kamenistak/founder-pipeline.git
  13. Human-gated perspective-panel research: one question, several seats, one judge. Solo, native panel, or per-seat MoA/Fusion fanout.

    Stale GitHub, bmtrnavsky 5 ★MITUpdated 26 days ago

    git clone https://github.com/bmtrnavsky/storm-fusion-research-pipeline.git
  14. wizard

    Skills

    Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.

    Indexed Agent skill collections on GitHub, mattpocock MIT1 note

  15. Carefully human hand written llm jailbreaks for the latest models that are available on the market. GPT-6 Astra, GPT-6.1 SoL, Opus 4.7, Opus 4.6, Sonnet 4.6, Haiku 4.5, Deepseek V4, Deepseek Flash, DeepSeek V4.1 Pro / Flash, Qwen 3.8 MAX, Qwen 3.8 Omni-Flash, Qwen 3.7 etc

    Stale GitHub, motan1337 16 ★MITUpdated 20 days ago

    git clone https://github.com/motan1337/universal-bypass-for-claude-chatgpt-qwen-deepseek-llm-claude-code-codex.git
  16. Claude Code skills for rewriting AI-drafted prose to pass AI detectors: a measured three-step pipeline (structural rewrite, tell removal, cross-model diction) scored against Pangram, plus reference management and citation auditing.

    Stale Archived GitHub, petar-djukic 5 ★MITUpdated 10 days ago 1 note

    git clone https://github.com/petar-djukic/writing-skills.git
  17. Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.

    Stale Agent skill collections on GitHub, obra MIT1 note

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.