Recently added

Sep 5, 2026

1. pr-review0stars

   Context-aware pull request review across all MotifPath repos, sharing durable guidelines with the team as it finds them.

   Claude Code1 skill
2. plan-writer0stars

   Write structured technical implementation plans for MotifPath features, services, and infrastructure changes.

   Claude Code1 skill
3. git0stars

   Enforce MotifPath git conventions: Conventional Commits, branch naming with task codes, dev/main flow, PR structure.

   Claude Code
4. ai-consultant0stars

   Senior AI consultant perspective — flags AI anti-patterns, missed opportunities, and model/prompt design issues.

   Claude Code1 skill
5. adr-writer0stars

   Write, review, and update Architecture Decision Records for the MotifPath project.

   Claude Code1 skill
6. dr-19-acquisition-target-scout0stars

   Screens a market for acquisition targets against a stated thesis, ranks the survivors on a visible weighted model, and builds the screening workbook and the target dossiers. A screen is defined by what it excludes, and the exclusion log records a certainty the data does not have: the reason it records is whichever criterion ran first, a company that failed one criterion and one that failed six produce the same row, and a hard gate applied to an estimated figure states as a measurement something nobody measured. So it applies every criterion to every candidate without short-circuiting, names the companies that failed exactly one, and re-runs the whole screen at both ends of every estimate's own error band. It also reports which gates would change the shortlist if they were weights. The workbook's scores are live formulas over a visible weights row, recalculated and read back out. Contacts no target, adviser, employee or customer.

   Claude Code
7. blend0stars

   Sören's workflow skills — blends superpowers, simpleviz, and review loops

   CodexClaude Code3 skills
8. workstreams0stars

   Parallel workstreams over herdr worktrees. An orchestrator provisions isolated streams; an implementer runs in each. Both read per-repo specs, so the plugin carries no project knowledge.

   Claude Code1 skill
9. sci-paper5stars

   Scientific paper writing, source-traced review, and de-AI rewriting for top-tier journals (ApJ/MNRAS/PRD/JCAP-class) and NSF/NIH proposals. Ships 12 skills and 40 tools under one typed standard: scientific-integrity blockers that cannot be waived as style preferences, a zero-target L0 lexicon, ranked advisories, explicit measurement states so missing calibration never reads as clean, claim-first rewriting gated on hard scientific-fidelity eligibility, a mechanical length budget with a machine-built removal map and a required-shrink gate, corpus-calibrated salience-hierarchy, domain-register (with an exhaustive zero-hit vocabulary audit), collocation, and discourse-texture (given/new cohesion, epistemic hedging) axes, each judged against the field's own per-section distribution at the unit it was calibrated at, a residue axis that gates the trace an edit leaves, A-R review with narrative-spine and adversarial-escalation dimensions, registry-verified bibliographies (CrossRef, DataCite, arXiv), pixel-measured figure review, and isolated multi-reviewer orchestration. Learned scores are field-similarity triage, never an authorship verdict. See CHANGELOG.md for per-version history.

   Claude Code2 skills
10. codex-workers0stars

    Use Codex as persistent steerable workers from Claude Code.

    Claude Code1 skill1 MCP server
11. ace1stars

    AI Connect Engine — orchestrates the ACE lifecycle from idea through app building, Connect setup, LLO management, and closeout

    Claude Code50 skills6 MCP servers
12. agentic-engineering-workflow0stars

    The portable half of a solo agentic engineering harness: the skills pipeline, the verification checklist, the AI-failure-mode code review checklist, and the catch-log schema. Mechanical wiring (CI, hooks, lint) is installed per-project by bootstrap, not by this plugin.

    Claude Code
13. tuff9stars

    Drive the Tuff capability lifecycle manager from a Claude Code session: install, version, diff, and validate the skills, tools, hooks, workflows, and MCP servers a repository gives its agents. Requires the tuff CLI on PATH.

    Claude Code1 skill
14. verify-cloud-account0stars

    Bash 実行前にクラウド CLI (gh / firebase / aws / gcloud / kubectl) のアクティブアカウントをプロジェクト想定値と照合し、不一致なら deny する PreToolUse hook。Agent Skill 3 本 (init / show / migrate) 同梱

    Claude Code3 skills
15. session-facts0stars

    セッション開始時にリポジトリを分析し、スタック/スクリプト/env キー/ドメイン型のファクトバンドルを Markdown で生成する Codex plugin。SessionStart で発火

    CodexClaude Code1 skill
16. sensitive-files-guardrail0stars

    機密ファイル (.env, *.secret, 秘密鍵, クレデンシャル) を Vibe Coding から守る多段 hook。Read/Bash/Edit/Write で機密パスを保護し、Stop で .gitignore 未登録を検出。うっかり露出の予防が目的で、敵対的バイパス対策ではない

    Claude Code
17. llms-docs0stars

    Progressive document loaders for Claude, AI SDK, and Firebase official docs via llms.txt

    Claude Code3 skills
18. file-split-advisor0stars

    Write/Edit 後に行数 tier と責務混在シグナル (import 多様性・命名の抽象度・定義数・制御フロー密度) を組み合わせて分割検討メモを additionalContext で返す非 block hook。言語/役割 (テスト/宣言的コード) で閾値を調整する

    Claude Code
19. external-ai-assist0stars

    Cursor / Codex などの外部 AI CLI を並走・クロスレビューに使う hook 集。Explore の Cursor 並走、ExitPlanMode の Cursor+Codex クロスレビュー、Stop 時の Cursor 差分レビューを提供する

    Claude Code
20. writing-artifacts5stars

    Positive writing system for durable written artifacts — READMEs, ADRs, PR descriptions, docs, runbooks. Reader-expectation prose, Diátaxis document jobs, plain-language structure.

    Claude Code1 skill
21. ship-gate5stars

    Stop-hook gate against trail-off: detects unpushed commits at turn end and injects an agent-directed nudge to review and finish the branch.

    Claude Code
22. session-retro5stars

    Interactive session retrospectives — deterministic activity triggers, one end-of-day offer, batch-scoped diff- and event-log-driven interview, native memory entries. No external services.

    Claude Code1 skill
23. nightshift5stars

    Plan by day, land by night, triage in the morning. `plan` turns an idea into a plan the loop can land unattended (self-contained `# Task N` sections, empty Open Questions, one Codex pass, opened as a PR). `init` scaffolds the overnight landing loop into the current repo — loop/land.sh, a quiet verifier, two PreToolUse guards the generator cannot loosen, a merge script that waits for CI and re-reads the kill switch — and proves it with a preflight and a dry run. `morning` reads the journal and the land:blocked PRs and says what needs a human. The loop itself is committed in your repo, not in this plugin: it runs `claude -p --setting-sources project`, where installed plugins never load.

    Claude Code3 skills
24. handoff5stars

    Manual /handoff skill — writes a structured resume doc on demand, auto-loads it on next session.

    Claude Code1 skill
25. gates5stars

    Four stateless PreToolUse gates, a PostToolUse JSON-config guard, and a docs-consolidation trigger. Denies a git commit that changes code without staging its covering docs (per-plugin README/CLAUDE.md pairs, or the nearest README/CLAUDE/AGENTS walking up); asks before a new-project scaffold command (npm create vite, cargo new, rails new, …) runs ahead of an approved design; denies a high-fan-out Workflow script with no per-agent model: override and asks before a denylisted built-in named workflow; denies an ad-hoc Agent dispatch that omits model unless the agent type pins one in frontmatter. Separately, a never-blocking trigger counts commits since the .docs-sync record and nudges toward /docs-consolidate. Every gate has an ack marker. Separately, a PostToolUse hook re-parses settings.json/.mcp.json after an edit and reports a syntax error, which Claude Code otherwise swallows by silently dropping the config it cannot parse.

    Claude Code1 skill
26. frontend-design5stars

    Frontend/UI design guidance, gated by scope: a light or surgical change gets inline principles; a wide-sweeping or highly-detailed design gets routed to Claude Design in the browser with a paste-ready design brief.

    Claude Code1 skill
27. domain-modeling5stars

    Actively build and sharpen a project's ubiquitous language — an opinionated CONTEXT.md glossary — by challenging terms, disambiguating overloaded words, and stress-testing domain relationships. Cross-references the adr skill for decision records. Adapted from mattpocock/skills (MIT).

    Claude Code1 skill
28. codex-review5stars

    Cross-provider adversarial plan/design-doc review via OpenAI Codex (GPT-5.6 Terra): verdict-loop protocol, atomic chain guard, cross-repo decision-gate log.

    Claude Code1 skill
29. adr5stars

    Turns an intent into a grounded, cited, build-ready ADR (docs/adr/YYYY-MM-DD-<slug>.md) — every claim cited, load-bearing decisions surfaced to the human — then hands it to nightshift:plan's landing step. Front-end for adr → nightshift.

    Claude Code1 skill
30. agoragentic35stars

    Connect Claude Code to Triptych OS through generated focused skills. Automatic MCP launch is disabled pending qualified host enforcement.

    Claude Code8 skills
31. zenn2stars

    Write Zenn tech-blog articles: the house style guide and Zenn-flavoured Markdown syntax. Install at user scope to make it available across all projects.

    Claude Code2 skills
32. workhub2stars

    Task-board, schedule and vault knowledge-base skills and hooks for the workhub vault (task-list, task-start, task-report, project-start, shared-space, schedule-edit, mindmap-edit, vault-init, vault-setup, vault-migrate, kb-ingest, kb-query, kb-lint, kb-index, memory-setup, memory-recall, strategist), the setup skills for the files those harness hooks read (setup-project-context, setup-rules-ex) plus capture-rule, the secretary agent that fields the owner's decisions, the harness hooks that carry the app's registered projects and their rules into a session, plus the workhub app's own release procedure (release-app).

    Claude Code21 skills
33. visuals2stars

    Produce visual deliverables as self-contained HTML and hand them over as PDF: fixed 16:9 slide decks, inline-SVG diagrams on an editorial grammar, readable HTML documents and dashboards, and publication-quality PDF export for all of them — rendered entirely inside Claude Code. Install at user scope; optional.

    Claude Code4 skills
34. team-ops2stars

    Team operations on a shared folder as the single source of truth: team knowledge base, file-based product backlog, sprint ceremonies, multi-repo progress tracking, and daily burndown/spec reporting.

    Claude Code13 skills
35. strategy2stars

    Turn a strategy handed down from above into your own organization's target states: decompose it into aspects and states (strategy-decompose), audit it for necessity, sufficiency and overlap (strategy-auditor), and ship it as a spreadsheet.

    Claude Code1 skill
36. stack-react-router2stars

    Helpers for React Router and Remix applications.

    Claude Code1 skill
37. stack-opencode2stars

    Helpers for working with OpenCode configuration and extensions.

    Claude Code1 skill
38. stack-dnd-kit2stars

    Helpers for building drag-and-drop UIs with dnd kit.

    Claude Code1 skill
39. stack-cloudflare2stars

    Helpers for developing on Cloudflare (Workers, Pages, R2, D1, etc.).

    Claude Code1 skill
40. persona2stars

    Switchable response personas with a shared token-reduction engine: bundled characters (holmes, genshijin, noctis, lunafreya, ignis), user-defined characters that survive plugin updates, three compression levels persisted across sessions, a persona-switch CLI other skills can call, character-agnostic commit/review/compress/stats/crew helpers, and an MCP description-shrinking proxy. Derived from genshijin (MIT).

    Claude Code8 skills
41. obsidian2stars

    Generic Obsidian format helpers: Obsidian Flavored Markdown, Bases, JSON Canvas, Obsidian CLI, and Defuddle web clipping.

    Claude Code5 skills
42. engineering2stars

    Engineering utilities and helpers for software development tasks.

    Claude Code16 skills
43. claude-tooling2stars

    Extend and maintain Claude Code itself: slash commands, skill authoring and installation, Desktop routines, plan grilling, plus the SessionStart plugin-update notice. Install at user scope to make it available across all projects.

    Claude Code4 skills
44. authoring2stars

    Author text deliverables and deliver them: README / CLAUDE.md / release notes / work logs, and posting the result to Slack. Visual deliverables — slide decks, HTML documents and PDF export — live in the visuals plugin. Install at user scope to make it available across all projects.

    Claude Code5 skills
45. agent-ops2stars

    Run agents in a terminal multiplexer: herdr and Zellij setup, handoff between agents, role-based teams, persistent sidekicks, and the WSL/VS Code launch doctor. Install at user scope to make it available across all projects.

    Claude Code8 skills
46. relay1stars

    Delegate work packets from a lead Claude Code session to executor sessions in their own iTerm tabs, with session reuse instead of always spawning fresh.

    Claude Code17 skills
47. durable-threads0stars

    Coordinate durable worker threads across Codex, Claude, Grok, and Cursor with provider-specific session controls.

    Codex1 skill
48. cfnsync0stars

    Skill for driving and interpreting the cfnsync CLI (sync raw CloudFormation templates to stacks) safely from Codex.

    CodexClaude Code1 skill1 MCP server
49. aify-project-graph0stars

    Lean MCP project graph surface for Codex: graph_packet, pull, consequences, change_plan, and health.

    CodexClaude Code1 MCP server
50. route171stars

    Route the accumulated session context to the core protocol whose deficit it shows — /route (a per-prompt hook directive triggers it)

    CodexClaude Code1 skill