← all publishers

FradSer

@fradser source repo

Report this profile Claim this profile

• 132 skills
• 0 followers
• 580 repo stars
• 2 weeks ago last updated

1. ▌
   Commit 3 · fradser

   Creates atomic conventional git commits using git-agent. This skill should be used when the user requests "commit", "git commit", "create commit", or wants to commit changes using AI atomic commits.
   580 repo stars
2. ▌
   Commit And Push 3 · fradser

   Creates atomic conventional git commits using git-agent and pushes changes to the remote repository.
   580 repo stars
3. ▌
   Reflect Skills From Memory 2 · fradser

   This skill should be used when the user asks to "reflect on skills from memory", "audit marketplace skills against memory", "从记忆中检查 skills 的问题", "反思并修改 skill", "apply memory feedback to skills", or wants to turn accumulated memory feedback about this marketplace's skills into concrete skill fixes. Reads the project's persistent memory, re-verifies each known skill problem against current code, then fixes the skill or corrects the stale memory.
   580 repo stars
4. ▌
   Lark 2 · fradser bundle

   Lark/Feishu CLI router: query and operate Lark/Feishu via lark-cli. Use `lark-cli skills read subskill` (e.g. lark-doc, lark-base, lark-im) to load domain skills for docs, sheets, base, calendar, im, mail, tasks, okr, drive, wiki, slides, whiteboard, apps/miaoda, approval, attendance, contact, vc, minutes, note, events, etc.
   580 repo stars
5. ▌
   Commit 2 · fradser bundle

   Creates clean, conventional git commits using standard git. Use when the user asks to "commit", "git commit", "create commit", or wants to commit staged or unstaged changes.
   580 repo stars
6. ▌
   Tropes 2 · fradser bundle

   Detects and eliminates AI writing tropes that make text sound artificial or formulaic. Use as an explicit review/quality pass when asked to check writing style, eliminate AI cliches, audit documentation tone, or refine drafts. Do not trigger automatically for ordinary code generation or initial document creation. Supports four-tier JSON preferences (global/project x shared/local office.json) read via load-preferences.sh.
   580 repo stars
7. ▌
   Create Pr 2 · fradser bundle

   Creates a GitHub pull request after repository validation, then starts the standalone review-pr workflow for CI monitoring, comment triage, closeout, and merge. Use when asked to create or submit a pull request.
   580 repo stars
8. ▌
   Review Pr 2 · fradser bundle

   Reviews a pull request: runs an independent baseline review, monitors CI and incoming reviewer comments with Pi monitor_start, triages and applies verified fixes, then presents a closeout summary and waits for explicit user confirmation before merging and cleaning the worktree and branch. Use this skill when the user asks to "review a PR", "monitor PR review comments", "address reviewer feedback on #123", or "watch CI on a pull request".
   580 repo stars
9. ▌
   Create Prd 2 · fradser bundle

   This skill should be used when the user asks to "create PRD", "write product requirements document", or mentions "PRD", "product requirements document".
   580 repo stars
10. ▌
    Create Issues 2 · fradser bundle

    Creates GitHub issues following test-driven development principles and proper labeling conventions. This skill should be used when the user asks to "create an issue", "file a bug", or needs to document new requirements, epics, or PR-scoped tasks.
    580 repo stars
11. ▌
    Update Readme 2 · fradser bundle

    Updates ONLY the root-level README.md and README.zh-CN.md. NEVER update README files in subdirectories, packages, modules, or nested paths. Use this skill when the user specifically asks to "update the README", "sync the bilingual READMEs", or wants root English and Chinese READMEs to match the current project state. Do NOT use for PRDs, general documentation, or writing drafts.
    580 repo stars
12. ▌
    Resolve Issues 2 · fradser bundle

    Resolves GitHub issues using isolated worktrees and test-driven development, then delegates PR creation to create-pr so the quality gate and the review-pr loop always run. This skill should be used when the user asks to "resolve an issue", "fix issue", or wants to implement fixes or features linked to tracked GitHub issues.
    580 repo stars
13. ▌
    Commit And Push 2 · fradser bundle

    Creates clean conventional git commits using standard git and pushes changes to the remote repository. Use when the user asks to "commit and push", "push changes", or complete a commit followed by git push.
    580 repo stars
14. ▌
    Patent Architect 2 · fradser bundle

    Automatically searches prior art via SerpAPI and generates Chinese patent application forms. This skill should be used when the user wants to generate Chinese patent application forms, or mentions "patents", "inventions", or wants to protect technical innovations.
    580 repo stars
15. ▌
    Apple Notes · fradser bundle

    Use this skill whenever the user wants to manage their Apple Notes using the `note` CLI tool. It covers listing, reading, creating, editing, moving, searching, and deleting notes and folders, and end-to-end-encrypted syncing to a Cloudflare backend. Works on macOS (via AppleScript) and on Linux (via a local SQLite database synced from the Cloudflare backend). Complements the `apple-events` skill (Reminders/Calendar).
    580 repo stars
16. ▌
    Apple Events · fradser bundle

    Use this skill whenever the user wants to manage their Apple Reminders or Calendars using the `event` CLI tool. It covers creating, viewing, searching, updating, and deleting reminders and calendar events, and syncing them to a Cloudflare backend. Works on macOS (via EventKit) and on Linux (via a local SQLite database synced from the Cloudflare backend).
    580 repo stars
17. ▌
    NPM Package Release · fradser

    Release and publish npm packages with Trusted Publishing (GitHub OIDC) in a monorepo, covering both first-release bootstrap (interactive publish + npm trust setup) and subsequent CI-owned releases via Changesets. Use whenever releasing a new package for the first time, diagnosing release or publication failures (EOTP, PUT 404, 409 Conflict, EPUBLISHCONFLICT, E401), handing off releases to CI, or triaging GitHub Actions release workflow runs.
    580 repo stars
18. ▌
    Retest Reloaded Pi Package · fradser

    Re-run one concrete reproduction of the current Pi-package problem after the user reloads Pi. Use whenever the user says they reloaded/restarted Pi and asks to test, verify, or retry the current case. This is a user-visible reproduction retry, not a request to run unit tests, typechecks, or a test suite.
    580 repo stars
19. ▌
    Code Terrier · fradser bundle

    Route Code Terrier reviews to the GitHub pull-request flow or direct terminal flow. Use when the user asks to review a pull request, wait for Code Terrier, check findings, review local changes, or run a review without a pull request. This is the only Code Terrier skill the agent needs.
    580 repo stars
20. ▌
    Open Deskos Widget · fradser bundle

    Develop, style, verify, and deploy Open DeskOS CM5 widgets and visual plugins on the Linux Electron runtime. Use when creating or refactoring widgets, tuning layout density and typography, isolating plugin faults, managing git-agent shared worktrees, or staging releases on the CM5 hardware.
    580 repo stars
21. ▌
    Plan Mode · fradser

    Enter Plan Mode and return an executable plan when a user request cannot be directly satisfied by the current Skills, Tools, firmware configuration, hardware, network, storage, or known parameters.
    580 repo stars
22. ▌
    Verify · fradser

    Run the unit test suite with `make fast`. Use after implementing a feature or fixing a bug to confirm no regressions. Does not require Docker or a live database.
    580 repo stars
23. ▌
    Migrate · fradser

    Generate and apply an Alembic database migration. Use when domain models or ORM models have changed and the database schema needs updating.
    580 repo stars
24. ▌
    Using Agentbook · fradser bundle

    Use Agentbook from Codex through anonymous REST recall and, when explicitly requested, persistent authenticated identity registration, memory contributions, outcome reports, and verification with randomized pass@1 measurement. Trigger when a real build, test, runtime, or implementation error blocks progress, when the user asks to recall or write an Agentbook finding, or when the user asks to inspect the pilot. Do not use for expected TDD failures, deliberate negative tests, or transient tool errors.
    580 repo stars
25. ▌
    Use Railway · fradser bundle

    Operate Railway infrastructure: sign up for or sign in to a Railway account, create projects, provision services and databases, manage object storage buckets, deploy code, configure infrastructure as code, environments and variables, manage domains, troubleshoot failures, check status and metrics, manage feature flags, set up Railway agent tooling, and query Railway docs. Use this skill whenever the user mentions Railway, feature flags, flag rollout, targeting rules, signing up, creating an account, registering, logging in, deployments, services, environments, buckets, object storage, build failures, agent setup, MCP, or infrastructure operations, even if they don't say "Railway" explicitly. Also invoke this skill when the user asks to be signed up, registered, or onboarded to Railway: do not refuse — drive them through the unauthed `railway up` flow (deploys + signs up on the fly) or `railway login` (which creates new accounts on the fly).
    580 repo stars
26. ▌
    Agentbook Research · fradser

    Harvest problems (from ~/.Codex project memories or your own reflection on a codebase), create them on agentbook, and run parallel autoresearch. Trigger on "harvest", "scan problems", "agentbook research".
    580 repo stars
27. ▌
    Loop · fradser

    Run a prompt or skill in the current session on a recurring or variable interval (for example, /loop 5m /foo).
    580 repo stars
28. ▌
    Storm · fradser bundle

    Generates Wikipedia-style long-form articles grounded in multi-perspective research and retrieval, porting Stanford STORM's four-phase pipeline (research, outline, write, polish). Each phase is independently runnable and resumable; runtime-neutral by design. Use when the user asks for a "storm article", a "wikipedia-style article", or to "research and write a long-form piece".
    580 repo stars
29. ▌
    Missav · fradser bundle

    Browse missav.ws AV listings with agent-browser, extract title/duration/url from listing cards, enrich detail-page plot descriptions for genre analysis, and rank recommendations against user preferences stored in ~/.missav/ (genres/types, performers, labels/studios, keywords, duration). Learns from user feedback each session. Use when finding AV on missav, searching /cn/search/{query}, analyzing plot descriptions, or getting personalized recommendations.
    580 repo stars
30. ▌
    Gitflow · fradser bundle

    Manages local Git-flow branch lifecycles: start or finish feature, hotfix, and release branches with automated changelog generation, version bumping, and cleanup. Use for repositories configured for local Git-flow finishing when the user explicitly mentions git-flow branch operations (e.g. 'gitflow start feature', 'gitflow finish release'). For standard GitHub PR-based reviews and merges, use create-pr.
    580 repo stars
31. ▌
    Swiftui · fradser bundle

    Build, refactor, or review modern SwiftUI. Prioritize macOS 26 and iOS 26 Liquid Glass, while covering architecture, state, concurrency, navigation, accessibility, performance, and code quality. Use for any SwiftUI implementation, migration, or review.
    580 repo stars
32. ▌
    Skill Creator · fradser bundle

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
    580 repo stars
33. ▌
    Resolving Merge Conflicts · fradser bundle

    Use when you need to resolve an in-progress git merge/rebase conflict.
    580 repo stars
34. ▌
    Improve Codebase Architecture · fradser bundle

    Scans a codebase for deepening opportunities, presents them as a visual HTML report, then grills through the chosen one. Use when the user wants to improve codebase architecture or find refactoring opportunities.
    580 repo stars
35. ▌
    Finish Feature · fradser

    Finalizes and merges a feature branch into develop using git-flow, then prunes stale branches and worktrees. This skill should be used when the user asks to "finish a feature", "merge feature branch", "complete feature", "git flow feature finish", or wants to finalize a feature branch.
    580 repo stars
36. ▌
    Finish Release · fradser

    Finalizes a release and merges it into main and develop with a tag using git-flow, then prunes stale branches and worktrees. This skill should be used when the user asks to "finish a release", "merge release branch", "complete release", "git flow release finish", or wants to finalize a release.
    580 repo stars
37. ▌
    Consolidate · fradser bundle

    Consolidates project memory across harness and .memory/ with theme clustering, practical-expiry prune, ground-truth verify, and an adversarial second pass. Use when the user runs /memory:consolidate, asks to tidy/dedupe/prune memory, or reports redundant or stale memories. Also covers active writing during work.
    580 repo stars
38. ▌
    Commit And Push · fradser

    Creates clean conventional git commits using standard git and pushes changes to the remote repository. Use when the user asks to "commit and push", "push changes", or complete a commit followed by git push.
    580 repo stars
39. ▌
    Update Readme · fradser bundle

    Updates README.md and README.zh-CN.md to reflect the project's current state. Use this skill whenever the user asks to "update the README", "sync the docs", "update documentation", "reflect latest changes in README", or wants both the English and Chinese READMEs to match the current project.
    580 repo stars
40. ▌
    Research · fradser

    Runs a deep-research query on Google Gemini's deep-research managed agent and returns a cited report. This skill should be used when the user asks to "deep research with Gemini", "run Gemini deep research", "have Antigravity research X", or wants a thorough, multi-source web research report produced by a remote Gemini agent. Invoked via "/antigravity:research". Supports a higher-effort max mode via "--max".
    580 repo stars
41. ▌
    Create Issues · fradser bundle

    Creates GitHub issues following test-driven development principles and proper labeling conventions. This skill should be used when the user asks to "create an issue", "file a bug", or needs to document new requirements, epics, or PR-scoped tasks.
    580 repo stars
42. ▌
    Resolve Issues · fradser bundle

    Resolves GitHub issues using isolated worktrees and test-driven development, then delegates PR creation to /github:create-pr so the quality gate and the /github:review-pr loop always run. This skill should be used when the user asks to "resolve an issue", "fix issue
    580 repo stars
43. ▌
    Use Openscad · fradser bundle

    Writes OpenSCAD code and drives the `openscad` command-line compiler to produce STL/3MF/AMF/DXF/SVG/PNG outputs from parametric `.scad` models. This skill should be used when the user asks to design a 3D-printable part, generate a laser-cut 2D plate, render a preview image of a CAD model, export STL for 3D printing, batch-render parametric variants, or convert between mesh formats. Invoked via "/hardware:use-openscad".
    580 repo stars
44. ▌
    Generate Video · fradser bundle

    Generate short videos from a text prompt or from still images using ByteDance Seedance on Volcengine Ark. Use this skill whenever the user wants to create, generate, render, or animate a video, clip, animation, motion graphic, or product demo — including text-to-video ("a drone shot over a forest at sunrise") and image-to-video, where a still becomes the first frame, or two stills are morphed start-to-end. Prefer this skill over describing a video in text.
    580 repo stars
45. ▌
    Use Kicad CLI · fradser bundle

    Drives the KiCad command-line interface (`kicad-cli`, version 9.0) to export schematics and PCBs, produce fabrication outputs, and run design checks. This skill should be used when the user asks to export gerbers, drill, or pick-and-place files, generate a BOM or netlist, run ERC or DRC (including in CI), export a STEP/3D model or PDF/SVG, upgrade KiCad symbol/footprint libraries, or run a KiCad job set. Invoked via "/hardware:use-kicad-cli".
    580 repo stars
46. ▌
    Swiftui Review · fradser bundle

    Reviews SwiftUI code for best practices on modern APIs, maintainability, and performance. This skill should be used when the user asks to review SwiftUI code, check for deprecated iOS/macOS APIs, validate data flow patterns, or audit accessibility compliance in Swift projects.
    580 repo stars
47. ▌
    Update Changelog · fradser bundle

    Creates or updates CHANGELOG.md following the Keep a Changelog 1.1.0 format. Use this skill when the user asks to "update the changelog", "generate changelog", "add changelog entry", "create CHANGELOG.md", "sync changelog with tags", or wants to document project changes based on git tags and commit history.
    580 repo stars
48. ▌
    Patent Architect · fradser bundle

    Automatically searches prior art via SerpAPI and generates Chinese patent application forms. This skill should be used when the user wants to generate Chinese patent application forms, or mentions "patents", "inventions", or wants to protect technical innovations.
    580 repo stars
49. ▌
    Best Practices · fradser bundle

    Language-specific best practices, code quality standards, and framework detection rules. Use when executing refactoring workflows, applying code quality rules, detecting frameworks, or checking language-specific patterns for TypeScript, Python, Go, Swift, or React.
    580 repo stars
50. ▌
    Get Context · fradser

    Execute this when the user requests code context for a repository, library, or any natural-language code/technology question using DeepWiki, Context7, Exa, git clone, and/or web search+fetch.
    580 repo stars
51. ▌
    QA · fradser

    Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".
    580 repo stars
52. ▌
    Code Context · fradser

    This skill should be used when the user asks to "understand a codebase", "get code context", "research a library", "explore a repository", "find code examples", "look up documentation", asks a natural-language code/technology question (e.g. "how does X work", "X vs Y", "best practice for Z"), or wants to understand how a specific project, library, or concept works before making changes.
    580 repo stars
53. ▌
    Refactor Project · fradser bundle

    Executes automated project-wide refactoring with a focus on cross-file optimization. This skill should be used when the user asks for project-wide refactoring, cross-file simplification, consistency standardization across the codebase, duplication reduction, or invokes "/refactor-project".
    580 repo stars
54. ▌
    Brainstorming · fradser bundle

    Designs new software features and multi-component changes for the current repo into implementation-ready BDD specs via autonomous codebase research, then commits the design for review (runs to completion without mid-design questions). Scope covers new features, greenfield design, and multi-component changes. Not for hardware/physical-system design, out-of-repo questions, single-file refactors, or known-root-cause bugs (those go to direct edits or systematic-debugging).
    580 repo stars
55. ▌
    Retrospective · fradser bundle

    Analyzes evaluation patterns across completed plans and evolves the superpowers checklists accordingly.
    580 repo stars
56. ▌
    Writing Plans · fradser bundle

    Creates executable implementation plans that break down a brainstorming design into detailed, unambiguous per-batch tasks for execution.
    580 repo stars
57. ▌
    Bdd · fradser bundle

    Behavior-driven development: Discovery → Formulation → Automation. Use when the user wants to build features or fix bugs via Gherkin scenarios and the BDD lifecycle, or mentions BDD/Gherkin/Executable Specifications. Delegates test implementation to /mattpocock:tdd.
    580 repo stars
58. ▌
    Tdd · fradser bundle

    BDD-driven test implementation: red-green loop mechanics, seams, mocking, and test quality under BDD Automation. Use when the user wants to write or improve tests during BDD implementation, needs guidance on test structure, or asks about test seams, mocking, or anti-patterns.
    580 repo stars
59. ▌
    Better Interface · fradser bundle

    User-invoked, cross-discipline interface review that coordinates six domain references: accessibility, layout, writing, typography, colors, and ui. Use when explicitly invoked for a holistic review of a screen, flow, feature, or product interface. Supports quick and full review modes. Triggers on better-interface, full interface review, holistic UI audit, cross-discipline design review, review the whole interface.
    580 repo stars
60. ▌
    Executing Plans · fradser bundle

    Executes a written implementation plan via per-batch sub-agent coordinators with verification and commits between batches.
    580 repo stars
61. ▌
    Generate Image · fradser bundle

    Generate Image (gemini / openai backends)
    580 repo stars
62. ▌
    Triage · fradser bundle

    Moves issues and external PRs through a state machine of triage roles — categorise, verify, grill, and write agent-ready briefs. Use when the user says "triage this issue" or wants agent-ready issue briefs.
    580 repo stars
63. ▌
    Wizard · fradser bundle

    Generates 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, running a one-off migration or cutover, or the user says "build a wizard" or wants a scripted step-by-step setup. Don't invoke this for steps the agent can perform itself.
    580 repo stars
64. ▌
    Teach · fradser bundle

    Teaches the user a new skill or concept within the workspace. Use when the user says "teach me X", wants to learn a topic over sessions, or needs a structured learning plan.
    580 repo stars
65. ▌
    To Spec · fradser bundle

    Turns the current conversation into a spec and publishes it to the project issue tracker, with no interview. Use when the user says "write a spec", "create a PRD", or wants the discussion captured as a spec.
    580 repo stars
66. ▌
    Loop Me · fradser bundle

    Runs a stateful grilling session that produces workflow specs for workflows the user wants to build. Use when the user says "loop me" or wants workflow specs drawn out of them.
    580 repo stars
67. ▌
    Ask Matt · fradser bundle

    Recommends the skill or flow that fits the user's situation. A router over the skills in this repo. Use when the user asks which skill to use, is unsure what fits, or needs a pointer to the right workflow.
    580 repo stars
68. ▌
    Handoff · fradser bundle

    Compacts the current conversation into a handoff document for another agent to pick up. Use when the user says "hand this off" or wants the work continued by a fresh session.
    580 repo stars
69. ▌
    Implement · fradser bundle

    Implements a piece of work from a spec or ticket set. Use when the user says "implement this spec", "work the tickets", or wants code written from an existing plan.
    580 repo stars
70. ▌
    Prototype · fradser bundle

    Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
    580 repo stars
71. ▌
    Wayfinder · fradser bundle

    Plans a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on the issue tracker, resolved one at a time. Use when the user has a large ambiguous goal and wants the route charted.
    580 repo stars
72. ▌
    Setup Pre Commit · fradser bundle

    Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
    580 repo stars
73. ▌
    Edit Article · fradser

    Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.
    580 repo stars
74. ▌
    Grill Me · fradser bundle

    Runs a relentless interview that sharpens a plan or design. Use when the user wants to be grilled on an idea, pressure-test a plan, or refine a design through questioning.
    580 repo stars
75. ▌
    Grilling · fradser bundle

    Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
    580 repo stars
76. ▌
    Optimize Plugin · fradser

    This skill should be used when the user asks to "validate a plugin", "optimize plugin", "check plugin quality", "review plugin structure", or "run plugin optimizer".
    580 repo stars
77. ▌
    Systematic Debugging · fradser bundle

    Diagnoses a reported bug, error, test failure, or unexpected behavior through a 4-phase root-cause analysis before any code changes.
    580 repo stars
78. ▌
    To Tickets · fradser bundle

    Breaks a plan, spec, or conversation into tracer-bullet tickets that declare their blocking edges, published to the configured tracker. Use when the user says "break this into tickets" or wants a plan decomposed into vertical slices.
    580 repo stars
79. ▌
    Wait What · fradser bundle

    Stop. That last message did not land — re-pitch it. Use when the user says "wait what", "I don't follow", "explain that again", or similar confusion signals.
    580 repo stars
80. ▌
    Receiving Code Review · fradser

    Use when the superpowers-evaluator returned REWORK on a batch, when fixing rework items from an evaluation report, or when receiving any code review feedback on superpowers output. Requires technical rigor and verification instead of performative agreement or blind implementation.
    580 repo stars
81. ▌
    Reflect Skills From Memory · fradser

    This skill should be used when the user asks to "reflect on skills from memory", "audit marketplace skills against memory", "从记忆中检查 skills 的问题", "反思并修改 skill", "apply memory feedback to skills", or wants to turn accumulated memory feedback about this marketplace's skills into concrete skill fixes. Reads the project's persistent memory, re-verifies each known skill problem against current code, then fixes the skill or corrects the stale memory.
    580 repo stars
82. ▌
    Code Review · fradser bundle

    Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
    580 repo stars
83. ▌
    Scaffold Exercises · fradser bundle

    Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
    580 repo stars
84. ▌
    Obsidian Vault · fradser

    Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.
    580 repo stars
85. ▌
    Migrate To Shoehorn · fradser bundle

    Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.
    580 repo stars
86. ▌
    Writing Beats · fradser bundle

    Exploit-phase writing — assembles raw material into a journey of beats, grounding each term before a beat leans on it. Use when the user has raw material and wants it turned into an article.
    580 repo stars
87. ▌
    Writing Shape · fradser bundle

    Exploit-phase writing — shapes raw material into an article paragraph by paragraph. Use when the user has a raw-material pile and wants the final article written.
    580 repo stars
88. ▌
    Batch Grill Me · fradser

    Runs a relentless interview that asks every frontier question at once, round by round. Use when the user wants to be grilled on a design or map a design tree.
    580 repo stars
89. ▌
    Claude Handoff · fradser bundle

    Hands the current conversation to a fresh background agent that picks up the work immediately. Use when the user wants the work continued by a background agent.
    580 repo stars
90. ▌
    Codebase Design · fradser bundle

    Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
    580 repo stars
91. ▌
    Diagnosing Bugs · fradser bundle

    Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
    580 repo stars
92. ▌
    Domain Modeling · fradser bundle

    Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
    580 repo stars
93. ▌
    Grill With Docs · fradser bundle

    Runs a relentless interview that sharpens a plan or design and creates docs (ADRs and glossary) along the way. Use when the user wants to stress-test a plan or design, or produce decision records.
    580 repo stars
94. ▌
    Plugin Best Practices · fradser bundle

    This skill should be used when the user asks to "validate plugin structure", "review manifest files", "check frontmatter compliance", "verify tool invocation patterns", "explain plugin component types", or needs Claude Code plugin architectural guidance.
    580 repo stars
95. ▌
    Behavior Driven Development · fradser bundle

    Applies behavior-driven development principles including Gherkin scenarios and test-driven development. This skill should be used when the user asks to implement features, fix bugs, or when writing executable specifications and tests before writing production code.
    580 repo stars
96. ▌
    Writing Fragments · fradser bundle

    Explore-phase writing — mines raw fragments without committing to structure. Use when the user wants to brainstorm material or gather fragments for a later article.
    580 repo stars
97. ▌
    To Questionnaire · fradser bundle

    Turns a decision the user can't fully answer into a questionnaire for someone else to fill in. Use when the user says "turn this into a questionnaire" or needs knowledge pulled out of an expert.
    580 repo stars
98. ▌
    Design An Interface · fradser

    Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
    580 repo stars
99. ▌
    Ubiquitous Language · fradser

    Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".
    580 repo stars
100. ▌
     Git Guardrails Claude Code · fradser bundle

     Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
     580 repo stars