Product & Project Management · For developers

Handles Linear issues for the team: reading details and images, checking sub-issues, marking progress, labeling AI-created issues and writing completion comments.

lobehub/lobehub

Audit and improve repository code milestone by milestone for correctness, clarity, local reasoning, DRY design, explicit state modeling, panic resistance, and trustworthy TypeScript boundaries.

pmndrs/glyph

Researches the codebase and relevant docs, asks clarifying questions, then writes a spec sheet in specs/ for a significant feature or complex fix.

cashew-labs/libretto

Coordinate multiple agents by splitting work into research, synthesis, implementation, and verification, assigning ownership, and keeping the coordinator focused on integration rather than raw…

LearnPrompt/cc-harness-skills

Write a practical Business Requirements Document (BRD) from a product idea, feature concept, customer request, business problem, or rough product opportunity.

digoal/blog

A skill your agent uses when drafting, reviewing, or improving Gherkin, Cucumber scenarios, BDD acceptance criteria, feature examples, Scenario Outlines, Backgrounds, Rules, Doc Strings, Data…

intent-driven-dev/intent-driven-template

A skill your agent uses when designing, drafting, refining, or stress-testing an RFC for an approved PRD, including requests for a design doc, solution design, or how to build it.

mirumee/nimara-ecommerce

Sets the rules for finding, writing and updating Shift GitHub issues: search for duplicates first, use outcome-focused titles and testable acceptance criteria.

shift-editor/shift

Evaluates and carries out non-trivial software changes from first principles: ground the problem, name real consumers, choose the smallest sufficient solution and require evidence.

bytedance/deer-flow

Clarifies what to build before how, by asking one question at a time about a feature idea and then handing the result on to planning.

VeryGoodOpenSource/vgv-wingspan

Scores a bug, issue or task from severity, impact and likelihood on a 0-30 scale and maps the total to a P0 to P4 priority category with a suggested action.

maslennikov-ig/claude-code-orchestrator-kit

A skill your agent uses when a team sees repeated @codex review cycles or Codex Cloud feedback churn and needs root-cause attribution by development stage.

victorGPT/vibeusage

Identify underspecified areas in YAML spec and encode clarifications back into the spec.

ariel-frischer/autospec

A skill your agent uses for GitHub release, Hangar, CurseForge/BukkitDev upload, Spigot release handoff, licence, asset naming, supported-version, and workflow readiness checks; do not use for…

kernitus/BukkitOldCombatMechanics

Plans work too big for one agent session as a shared map of investigation tickets, resolved one at a time until the route to the destination is clear.

rengwu/wayfinder-maps

Turns Riffrec screen, voice and event recordings into evidence for bug reports and requirements, and helps set up Riffrec when no recording exists yet.

EveryInc/compound-engineering-plugin

PI Cognitive AI. An agent skill from share-skills/pi.

share-skills/pi

Multi-agent review/refine loop. An agent skill from OpenCyphal/pycyphal.

OpenCyphal/pycyphal

End-to-end workflow for agent-driven changes that add or modify behavior in the toolkit packages.

OfficeDev/microsoft-365-agents-toolkit

A skill your agent uses for change traceability review across specs, commits, PRs, branches, local diffs, and git history, including Spec Preparation, Review Readiness Checks, and Review…

QoderAI/better-harness

Operate TikTok Shop research and planning with KSS MCP across product discovery, shop analysis, viral commerce videos, creator matching, caption extraction, pagination, sorting, and evidence-based…

aronhy/tiktok-agent-skills

Runs the gstack CEO, design, engineering and DX review skills on a plan file in sequence and makes borderline taste decisions automatically using six stated decision principles.

garrytan/gstack

Reviews a plan for a developer-facing product by profiling developer personas, benchmarking rivals and scoring friction, in expansion, polish or triage mode.

garrytan/gstack

Produces a weekly engineering retrospective from commit history, work patterns and code quality metrics, with trend tracking and per-person breakdowns.

garrytan/gstack

7-section readiness scorecard for a LOCAL repo. An agent skill from ruvnet/metaharness.

ruvnet/metaharness

A skill your agent uses when the user wants to plan, decompose, track, or resume a multi-task project: scoping a new idea, importing or onboarding an existing repo or workspace, asking what to work…

FrkAk/piyaz

This skill should be used when user asks to "use supabase CLI", "supabase init", "supabase start", "run migrations", "deploy edge functions", "manage Supabase project", or works with the supabase…

fcakyon/claude-codex-settings

Define or revise a Roam product milestone and its engineering, adoption and offer-readiness sequence.

Cranot/roam-code

Retrieve GitHub issues, pull requests, and milestones with read-only, whitelisted gh commands only.

eclipse-rdf4j/rdf4j

Detect pull requests aging past warn / critical thresholds, score severity, and nudge reviewers via Slack DM, channel, email, or directly as a PR comment — with one-time auto-escalation when a PR…

aozyildirim/Agena

Turns a product idea into a coarse, ordered scope kept in docs/scope, then keeps it current: plan a product, plan the next slice, enroll one feature or reconcile after shipping.

jsmastery-pro/skills

Starts a feature as a demo narration instead of a PRD: you approve the script before any code, then the agent builds in a fresh worktree and opens a PR with proof.

Devin-AXIS/iPolloWork

已有功能的需求变更闭环（门禁式七步）。触发硬条件：要改的功能已经实现并跑起来了。当用户说"改需求""需求变更""调整交互""改功能""重构流程"，或改动容易散到多个文件、碰到鉴权/存储/配置/权限、需要可靠验证 + 回滚方案时使用。流程：锁 scope 写 change brief → 从代码确认当前行为（不靠记忆和假设）→ 影响面与风险评估 + 回滚计划 →…

yunshu0909/yunshu_skillshub

PI Cognitive AI. An agent skill from share-skills/pi.

share-skills/pi

Interviews you about scope, behavior, edge cases and verification, then writes a self-contained SPEC.md that a fresh session can implement without this conversation.

poshan0126/dotclaude

Create, get, update, abandon, and link SDK PRs to release plan work items for Azure SDK releases.

Azure/azure-sdk-tools

A skill your agent uses when running a broad manual/AI-driven end-to-end verification of Breeze RMM across many merged PRs or commits — "test everything since the last release", release-readiness…

LanternOps/breeze

Develops two or more independent, concrete candidates for a brief, judges them against shared criteria, and returns one synthesis.

EveryInc/compound-engineering-plugin

A skill your agent uses when one idea feels exciting enough that the user may rush into implementation before the scope is stable.

cnfjlhj/ai-collab-playbook

Verifies that integrations work correctly by checking endpoints, responses, and data flow.

allgpt-co/QuickVoice

Run the pi-lens retrospective — turn a session, an incident, or a merged bug fix into environment changes (checks, hooks, contract lines, deletions), classified mechanical-vs-judgement, each with…

apmantza/pi-lens

Pre-PR advisory check for deviations from the project spec. An agent skill from joshukraine/dotfiles.

joshukraine/dotfiles

A skill your agent uses when handed a GitHub issue (number or URL) to execute end to end.

lbedner/aegis-stack

Runs a structured requirements interview to produce a feature specification with EARS requirements, acceptance criteria and an implementation checklist.

Jeffallan/claude-skills

A skill your agent uses when the user wants to release a new version.

s-morgan-jeffries/apple-mail-fast-mcp

Manages GitHub issues and project boards with swarm coordination: issue creation and triage, issue-to-task conversion, progress tracking and stale issue cleanup.

ruvnet/agentic-flow

A skill your agent uses whenever the user asks to implement, execute, deliver, verify, or close a task from an existing Cabloy suite specification, including requests such as “implement WBS-…”…

cabloy/cabloy

Take committed work from a branch to a verified pull request — push, open the PR, settle CI and the automated review, answer and resolve every finding, and hand off.

vfarcic/dot-agent-deck