Agent Skills

Jira Context

fkdarven

How to call Jira Cloud's API and how the plugin resolves user-specific project/workflow IDs

Envato R2

therealityreport

Use when the user asks to search Envato, download licensed Envato assets with their own login, capture an Envato browser session, or upload Envato downloads and license metadata to Cloudflare R2.

SEO Firecrawl

RaDeleon

Full-site crawling, scraping, and site mapping via Firecrawl MCP. Use when user says "crawl site", "map site", "full crawl", "find all pages", "broken links", "site structure", "discover pages", "JS rendering", or needs site-wide analysis.

Refresh Miatrix Token

joestump

Refresh the Miatrix indexer API token in Prowlarr by logging into Miatrix via browser automation and extracting the current API key. Use this skill whenever Miatrix keeps re-downloading the same episodes or shows, when Prowlarr reports Miatrix indexer errors or failures, or when a Miatrix API key rotation is suspected. The skill handles the full workflow automatically: gathers credentials, logs in

Swiftui Modernize

yigitkonur

Modernize existing macOS SwiftUI code by replacing deprecated APIs with verified current production patterns.

Github

simpleapps-com

GitHub conventions for SimpleApps. Covers org structure, git safety, issue creation, PR workflows, and gh CLI usage. Use when creating issues, PRs, or working with GitHub repos.

Litertlm Prompting

kurtvalcorza

How to prompt a small on-device model so it performs. Load this before composing a prompt for the local model — habits that work on frontier models actively hurt here.

Citing Bonez Sources

bonez-io

Cite and dereference bonez results correctly. Use when presenting findings that came from bonez tools, when a result carries a ~hex handle or vendor URL, when the user asks where a claim came from, or when you need the full record behind a search snippet.

Finding Prior Art

bonez-io

Find what the org already knows before building or deciding. Use when starting non-trivial implementation or design work, when asked "have we done this before", "why is X like this", or "has anyone hit this error", when a decision smells like it was already made once, or before proposing an approach someone may have already rejected.

Impact Analysis

bonez-io

Assess blast radius before changing code. Use when asked "what breaks if", "who calls this", "is it safe to change or delete this", "what tests cover this", before refactoring a shared symbol or changing a public contract, or when judging how risky a diff is.

Querying The Graph

bonez-io

Traverse the org graph with BGQ via bonez:query. Use when a question is about relationships or structure — what calls, imports, tests, or depends on X, what is connected to a ticket or PR, which code touches a table — or when search has found a seed and you need its neighborhood.

Reviewing With Org Rules

bonez-io

Review code against the org's standing rules. Use when reviewing a PR, diff, or change in a bonez-connected org, when asked whether code follows the org's conventions, or before approving, merging, or signing off on anything non-trivial.

Who Owns What

bonez-io

Find people — owners, experts, reviewers — through the org graph. Use when asked who owns, maintains, or knows a system, who to ask, assign, or request review from, who wrote or decided something, or when routing work to a human.

Ponytail

michaelheichler

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, a

Athena Carry On Engineering Plan

Athena-Git-Group

逐步執行工程計畫，搭配 human-in-the-loop 審查。 每個 Phase 由對應 skill 連續執行所有內部步驟，完成後展示交付物進入 feedback loop。 使用者審查通過後才推進至下一個 Phase。 支援資料夾結構（plan.md + todo/doing/done/）與 Dependency Graph， 允許多個 AI 平行執行互不依賴的 Phase。 當使用者說「carry on engineering plan」「carry on」「繼續工程計畫」 「執行工程計畫」，或想恢復執行先前擬定的工程計畫時觸發。

Retrospective

Agentic-Engineering-Agency

Facilitate a sprint or iteration retrospective that surfaces real learnings and produces owned, dated action items. Invoke when a sprint or iteration has closed and the team needs a structured inspect-and-adapt session.

Verification Before Completion

aki25101998

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Lazy

JustasMonkev

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, addi

Dependabot Babysit Cycle

pPrecel

One iteration of the dependabot-babysit loop. Reads session state, runs verify → main health check → review/update → fix → stop-condition evaluation. Not intended to be invoked directly — use /dependabot-babysit instead. Invoke with: /dependabot-babysit-cycle [scope]

Outline Runbook Curator

joestump

Curate, consolidate, and restyle the StumpCloud Runbooks wiki in Outline (outline.stump.rocks) against the repo as source of truth. Use this skill whenever the user wants to review/clean up the wiki, consolidate or reorganize runbooks, fix stale or duplicated docs, reconcile Outline against the repo (ADRs, inventory, docs/), restructure the doc tree into hierarchy-native nodes, or apply the domain

Openspec Explore

ethanhinson

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

Decision Advisor

fivebucksventures

Structure a hard business decision — frame the choice, score options against weighted criteria, run a pre-mortem and stress-test, and produce a recommendation + decision record for any active brand

Audit Tech Stack

soreavis

Tech stack compliance audit. Checks code quality conventions — inline styles vs CSS framework, type safety, component architecture, linting, framework best practices. Adapts to detected stack.

Algorithmic Thinking

michaelheichler

Guide for solving competitive programming and algorithmic problems using techniques from Daniel Zingaro's 'Algorithmic Thinking' (2nd Ed, 2024). Covers hash tables, trees, recursion, memoization, dynamic programming, graphs, BFS, Dijkstra's algorithm, binary search, heaps, segment trees, union-find, and randomized algorithms. Use this skill whenever the user needs help with: algorithmic problem so