Skill rating
44 skills. The A–F grade combines safety (60%) and quality (40%); tests add a bonus. The rating refreshes automatically from open catalogs.
ManufacturingLogistics and warehouseProcurementQuality controlContact centreField serviceFinanceCustomer supportindustry shortcuts
| # | Grade | Skill | Score ▾ | Safety | Quality | Process | Tests | Popularity | Updated |
|---|---|---|---|---|---|---|---|---|---|
| 1 | A | Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, obje | 100 | 94 | D | — | ★ 39 599 | 5 d ago | |
| 2 | A | Clean Impeccable frontend design skill. Use when the user wants to design, redesign, critique, audit, polish, harden, optimize, adapt, clarify, colorize, animate, or otherwise improve a frontend inter | 100 | 89 | C | evals | ★ 39 599 | 5 d ago | |
| 3 | A | Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow. | 100 | 88 | C | — | ★ 39 599 | 5 d ago | |
| 4 | A | Turn a prompt, bug report, issue ID, or ticket URL into a repository-grounded implementation plan for human approval. Use when the user asks to plan a PR, prepare a ticket for implementation, work out | 100 | 88 | B | evals | ★ 39 599 | 5 d ago | |
| 5 | B | Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills. | 100 | 84 | C | — | ★ 39 599 | 5 d ago | |
| 6 | B | Turn technical conversations, bugs, CI failures, review comments, and repeated agent mistakes into durable project improvements. Use when the user asks what should be automated, documented, tested, ad | 95 | 92 | B | evals | ★ 39 599 | 5 d ago | |
| 7 | B | 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-n | 100 | 84 | C | — | ★ 39 599 | 5 d ago | |
| 8 | B | Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR. | 100 | 84 | C | — | ★ 39 599 | 5 d ago | |
| 9 | B | Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only for deterministic engineering: | 100 | 85 | B | — | ★ 39 599 | 5 d ago | |
| 10 | B | Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests. | 100 | 85 | C | — | ★ 39 599 | 5 d ago | |
| 11 | B | Ship PR: credit-aware autonomous pull request readiness workflow. Use when the user asks to ship work, prepare a branch for review, create or update a PR, make CI green, clean up a branch before PR, o | 95 | 89 | A | evals | ★ 39 599 | 5 d ago | |
| 12 | B | Invoke whenever writing, changing, reviewing, or sweeping tests. Authoring gate for new tests plus audit workflow for low-value, implementation-coupled, or duplicative tests and the test-only producti | 100 | 81 | C | — | ★ 39 599 | 5 d ago | |
| 13 | B | 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 | 100 | 80 | C | — | ★ 39 599 | 5 d ago | |
| 14 | B | 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. | 100 | 80 | C | — | ★ 39 599 | 5 d ago | |
| 15 | B | 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. | 100 | 81 | C | — | ★ 39 599 | 5 d ago | |
| 16 | B | Build and maintain documentation sites with Mintlify. Use when creating docs pages, configuring navigation, adding components, or setting up API references. | 100 | 80 | C | — | ★ 39 599 | 5 d ago | |
| 17 | B | 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-part | 100 | 80 | C | — | ★ 39 599 | 5 d ago | |
| 18 | B | Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md. | 100 | 77 | C | — | ★ 39 599 | 5 d ago | |
| 19 | B | Coordinating the Quivr V2 agent fleet. Use when designated coordinator, or asked to launch workers on tickets, merge green pull requests, keep Linear and the demo in sync, or resume the fleet in a new | 99 | 80 | C | — | ★ 39 599 | 5 d ago | |
| 20 | B | This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great. | 100 | 78 | C | — | ★ 39 599 | 5 d ago | |
| 21 | B | Polishes and improves the UI in your project. Covers concentric border radius, optical alignment, surface depth, contextual icons, hit areas and more. | 100 | 76 | C | — | ★ 39 599 | 5 d ago | |
| 22 | B | Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading le | 100 | 76 | C | — | ★ 39 599 | 5 d ago | |
| 23 | C | Runtime guide for running Armada workers as local subagents of a Claude Code coordinator. Use when an Armada coordinator running in Claude Code must launch a worker on a ticket with the Agent tool, se | 100 | 73 | D | — | ★ 39 599 | 5 d ago | |
| 24 | C | Use when you need to resolve an in-progress git merge/rebase conflict. | 100 | 73 | D | — | ★ 39 599 | 5 d ago | |
| 25 | C | Runtime guide for running Armada workers on Conductor Cloud. Use when an Armada coordinator must launch a worker on a ticket, send it a message, check whether a silent worker is still alive, or stop a | 100 | 73 | D | — | ★ 39 599 | 5 d ago | |
| 26 | C | Coordinating an Armada fleet of coding agents on one project. Use when designated coordinator, or asked to launch workers on ready tickets, answer their questions, merge their green pull requests, or | 100 | 73 | D | — | ★ 39 599 | 5 d ago | |
| 27 | C | Working one ticket as an Armada worker agent. Use when you were launched on a ticket by an Armada coordinator, or asked to claim, plan, implement and ship one ticket of a project that has an armada.to | 100 | 73 | D | — | ★ 39 599 | 5 d ago | |
| 28 | C | Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs. | 100 | 72 | C | — | ★ 39 599 | 5 d ago | |
| 29 | C | Diátaxis Documentation Expert. An expert technical writer specializing in creating high-quality software documentation, guided by the principles and structure of the Diátaxis technical documentation a | 100 | 69 | C | — | ★ 39 599 | 5 d ago | |
| 30 | C | Rewrite AI-sounding text so it reads like the writer without changing what it says.
Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line
closers, staged openers, forced tr | 100 | 71 | C | — | ★ 39 599 | 5 d ago | |
| 31 | C | improve-codebase-architectureProcedureSoftware developmentData and analyticsQuivrHQ/quivrClaude Code Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick. | 100 | 68 | C | — | ★ 39 599 | 5 d ago | |
| 32 | C | Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locall | 100 | 68 | C | — | ★ 39 599 | 5 d ago | |
| 33 | C | Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed. | 100 | 68 | D | — | ★ 39 599 | 5 d ago | |
| 34 | C | Turn a decision you can't fully answer into a questionnaire for someone else to fill in. | 100 | 65 | C | — | ★ 39 599 | 5 d ago | |
| 35 | C | Ask which skill or flow fits your situation. A router over the skills in this repo. | 100 | 65 | C | — | ★ 39 599 | 5 d ago | |
| 36 | C | Teach the user a new skill or concept, within this workspace. | 100 | 65 | C | — | ★ 39 599 | 5 d ago | |
| 37 | C | Runtime guide for persistent Armada workers on this machine through herdr. Four sections cover launch, message, status, and stop with safe worktree archival. | 100 | 61 | D | — | ★ 39 599 | 5 d ago | |
| 38 | C | Implement a piece of work based on a spec or set of tickets. | 100 | 58 | D | — | ★ 39 599 | 5 d ago | |
| 39 | C | Compact the current conversation into a handoff document for another agent to pick up. | 100 | 58 | D | — | ★ 39 599 | 5 d ago | |
| 40 | B | Writing Quivr's public documentation site. Use when adding or editing a docs page, documenting a new feature, plugin type, API or CLI change, or reviewing documentation. | 100 | 78 | D missing files | — | ★ 39 599 | 5 d ago | |
| 41 | D | A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go. | 100 | 43 | D | — | ★ 39 599 | 5 d ago | |
| 42 | D | Stop. That last message did not land: re-pitch it. | 100 | 43 | D | — | ★ 39 599 | 5 d ago | |
| 43 | D | A relentless interview to sharpen a plan or design. | 100 | 43 | D | — | ★ 39 599 | 5 d ago | |
| 44 | C | Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear. | 100 | 66 | C missing files | — | ★ 39 599 | 5 d ago |