Product & Planning

manager-dot-dev Bundle

Guides managers out of the bottleneck role — provides the Team Rep pattern, Epic Ownership model, Task-Relevant Maturity framework, kingdom ownership, and three-layer assignment strategy. Use when the user wants to delegate work or says "I'm doing everything," "team isn't taking ownership," "I can't let go," "team rep," "project ownership," "I'm the go-to person," "bus factor," "I work weekends," "how do I delegate," or "engineers don't take initiative." Do NOT use for managing a specific underperformer (use performance-reviews) or deciding what work to prioritize (use roadmap-planning).

manager-dot-dev Bundle

Helps engineering managers identify, quantify, and reduce hidden capacity drains that make teams miss commitments even when everyone is busy. Use this skill whenever the user mentions invisible work, untracked work, support requests consuming the team, glue work, shadow backlog, sprint spillover, capacity planning being wrong, teams always underestimating, senior engineers burning out, or "we are busy but nothing ships." Produces a diagnostic, evidence plan, and concrete interventions.

manager-dot-dev Bundle

Helps engineering managers build a functional PM–EM partnership and become more product-oriented — produces a 3-pattern PM–EM dynamic model (PM-Led / Engineering-Led / Fake Balanced), a true partnership definition, the "It's Important to Me" card for navigating disagreements, tips for getting engineers closer to customers and usage data (launch vs. landing, session recordings, customer conversations), and an explicit responsibilities exercise. Use when the user says "PM relationship," "PM drives me crazy," "product manager," "roadmap disagreement," "PM overrides me," "PM–EM partnership," "I want to be more product-oriented," or "how do I get engineers closer to customers." Do NOT use for general roadmap prioritization (use `roadmap-planning`) or when urgency is being manufactured by a PM (use `managing-urgency`).

manager-dot-dev Bundle

Helps engineering managers plan roadmaps, prioritize work, and communicate priorities effectively — produces the 20% tech debt framework (and its 5 traps), a phased release pressure-test, a maintenance cost model, the Always Green delivery method, sprint anti-patterns, hidden costs of custom features, a critical deadline playbook, the Iron Law of Projects with reference-class forecasting, a "no technical projects" framing, and feature factory warning signs. Use when the user says "roadmap," "quarterly planning," "OKRs," "prioritization," "what should we work on," "planning cycle," "backlog grooming," "stakeholder alignment," "capacity planning," "technical debt," "we're always late," or "leadership doesn't understand engineering work."

manager-dot-dev Bundle

Helps engineering managers write messages, announcements, and stakeholder updates that land well — produces a 3-Step Writing Framework (Prepare / Write Simply / Run a Garbage Collector), the Async Re-Explanation Trap (calling out missed messages), and the Compression/Decompression model for diagnosing why messages are misunderstood. Use when the user says "draft a message," "write an announcement," "communicate this change," "how do I word this," "message for my team," "write an update," or "how do I communicate X." Do NOT use for verbal feedback or difficult conversations (use `feedback` or `difficult-situations`).

xiaolai Skill

Web2 recon pipeline — subdomain enumeration (subfinder, Chaos API, assetfinder), live host discovery (dnsx, httpx), URL crawling (katana, waybackurls, gau), directory fuzzing (ffuf), JS analysis (LinkFinder, SecretFinder), continuous monitoring (new subdomain alerts, JS change detection, GitHub commit watch). Use when starting recon on any web2 target or when asked about asset discovery, subdomain enum, or attack surface mapping.

xiaolai Skill

Okta-as-IdP red-team attack chain — tenant discovery, user enumeration (multiple vectors), authentication flow analysis (factors enumeration, push-notification fatigue, SMS bypass), password spray with lockout discipline, Okta-specific phishing primitives (kits, FastPass abuse, OIDC redirect_uri tampering), MFA enumeration, post-compromise admin API surface. Many enterprise orgs use Okta instead of (or alongside) Entra ID. Distinct endpoints, distinct rate-limiting, distinct factor flows. Use when recon shows `<tenant>.okta.com`, `<tenant>.okta-emea.com`, `<tenant>.oktapreview.com`, or autodiscover-style records pointing at Okta IdP.

xiaolai Skill

Cloud IAM red-team attack chain across AWS, Azure, GCP — focused on EXTERNAL exploitation paths and post-credential-discovery privilege analysis. Covers IAM enumeration (aws iam, az role, gcloud iam), STS/AssumeRole chaining, Azure Managed Identity abuse (via SSRF/leak), GCP service account JSON abuse, IMDSv1/v2 attacks via SSRF, K8s ServiceAccount token exfil, role-trust-policy confused-deputy, cross-account assume-role enumeration, IAM privilege escalation patterns (24+ AWS, 8+ Azure, 6+ GCP). Built for the case where recon yields a credential (key, JSON, token) and you need to know what it grants and how to escalate. Use when an AWS key / Azure secret / GCP service account JSON / K8s SA token surfaces from a code repo, JS bundle, APK, breach corpus, or SSRF chain.

axross Bundle

Creating, refining, splitting, consolidating, renaming, or auditing an agent skill — portable content boundaries and agentskills.io authoring. Triggers on `SKILL.md`, frontmatter, `description`, "where does this rule belong", "split this skill", "recast this skill as a capability", and "audit skill portability". Skill management owns installation and active loading; project policy and host guidance own gates and execution. Covers capability framing, judgment versus mechanism, standard metadata versus host extensions, conditional references, a portability checklist, and structural validators.

axross Bundle

Deciding whether material belongs in a skill or project documentation, choosing its tier, and managing skill installation and active loading. Triggers on adding, editing, renaming, moving, or removing a skill; installed-copy or lockfile drift; same-name collisions, missing discovery, stale loaded content, or a loaded skill with a defective rule. Metadata authoring belongs to skill-authoring practices; host-specific reload and source-inspection commands belong to project operations. Covers source ownership, targeted installation, drift checks, and separate discovery and active-loading evidence.

axross Bundle

Updating a project's own documentation when a change alters what it says, and reading it before planning one — the `docs/` tree recording what the project is and how it works now, and the mechanism that corrects it when a change makes it wrong. Triggers on "docs/", "spec", "domain model", "glossary", "ubiquitous language", "ADR", "supersede", "the docs are stale", "is this documented anywhere", "conventions/", "operations/". Not spec-driven development — a plan drives the change and this records what became true, so "spec-first" and "generate from the spec" route elsewhere; the plan document itself belongs to a PRD capability, and sentence-level craft to a technical-writing one. Covers decision records, conventions and operations, and five single-purpose validators.

axross Bundle

Drafting, structuring, editing, or reviewing a technical document — a design doc, RFC, ADR, runbook, README, API reference, changelog, or post-mortem — and the sentence-level craft that makes any of them readable. Triggers on "make this clearer", "how should I structure this", "is this readable", "too wordy", "passive voice", "hard to follow", "tighten this prose". Not for non-software writing — marketing copy, blog posts, talks, fiction, academic papers outside software — nor for a spec's section skeleton, which a PRD capability owns. Covers naming the reader, the four Divio document types, leading with the answer, and a plain-English vocabulary ceiling. Self-contained.

axross Bundle

Writing, refining, or reviewing a PRD, feature spec, plan document, RFC, design doc, or issue description — the canonical tool-agnostic section structure such a document takes, and the craft behind each section. Includes the plan-writing or issue-drafting step of any delivery workflow. Triggers on "write a PRD", "draft a spec", "refine this issue", "structure this plan", "write acceptance criteria", "how do I verify this is done", "is this requirement testable". Not for writing the code, only the document that specifies it; UI markup, module placement, and test mechanics stay with the project's own conventions.

fernando-delosrios-sp Bundle

Survey any codebase as a senior advisor and produce prioritized handoff artifacts for OTHER models/agents to execute — OpenSpec change packages (when capability specs exist) or legacy implementation plans. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.

hongmaple0820 Bundle

飞书 OKR：管理目标与关键结果。查看和编辑 OKR 周期、目标（Objective）、关键结果（Key Result）、对齐关系、量化指标和进展记录。当用户需要查看或创建 OKR、管理目标和关键结果、查看对齐关系时使用。

treasoni Bundle

Install, configure, migrate, and validate a portable manifest registry for agent workflows, skills, subagents, and hooks. Use when a project needs manifest.yaml-based discovery, artifact versioning, dependency checks, capability declarations, permission-policy review, or reusable agent-platform setup.

tomorrowlm Bundle

当用户要从零开发完整前端页面或功能模块，或大幅改造已有页面时使用；典型输入包括 Figma、原型、PRD、Swagger/OpenAPI，且需求涉及页面结构、路由、多个交互区块、接口、状态流或验收。 适用于列表页、详情页、编辑页、表单页、大屏及多步骤流程。不要用于单点 bug、文案/样式/字段/按钮微调、代码解释、代码审查或用户已限定文件与改动内容的小范围快速修改。

crbnos Bundle

Survey the Carbon codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit Carbon, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.

ceilf6 Bundle

Design, audit, and refactor the outer CLI entry layer for AI agent tools. Use when a request involves multi-mode CLI design, command dispatch, startup flags, interactive versus headless routing, SSH or remote entry flows, slash-command versus subcommand separation, plugin or skill command registration, command discovery, or cold-start optimization. Not for runtime state-tier design or terminal frame rendering.

lythos-labs Bundle

Declarative skill deck governance. `deck link` reconciles the working set to match skill-deck.toml — deny-by-default removes undeclared skills. DEFAULT patterns: PHASE SWITCH via separate deck files (deck link --deck phase<N>.toml), SEED bootstrap (minimal deck → agent self-expands via deck add + curator discovery). Always restores parent deck. Zero state pollution between phases. INNATE FIRST: after compaction, session reload, or skill refresh — read every innate skill's full SKILL.md before any tool skill. Innate = eagerly loaded, always full context. Tool = lazy, read only on trigger. CRITICAL when writing a deck for others: verify every locator path against the REAL repo structure before publishing.

lythos-labs Bundle

Register tasks BEFORE fixing bugs. Close epics when work is done. Always move state through the CLI — never mv files by hand: CLI moves write Status History, manual moves create probe mismatches. Never leave state drift for the next agent to discover via git log. GTD (Getting Things Done)-style governance across ADR (architecture decision record) / Epic / Task / Wiki. Zero-knowledge (ZK) review = a fresh-agent pass over a task card (WHAT/WHY/HOW) before assignment, so an executor with no conversation context can still run it. `cortex probe` = drift detector: stale backlog, drifted epics, history mismatches vs git reality. **Task-git discipline**: one task = 2-5 commits (core, tests, docs, trailer); every commit carries its full TASK-id (see ID Format — truncated IDs are not addressable).

ghostlygawd Bundle

EXPERIMENTAL. Preview 2–4 alternatives or a measurable roadmap without changing the project. Use for low-cost incubation, preview-only brainstorming, or roadmap drafting with exact-target approval before any later action. Do not use when the user explicitly invokes the standalone brainstorm skill or requests independent parallel candidates; do not use as build or mutation authority.

ghostlygawd Bundle

Roadmap — idea to shipped, on a deadline

wachawo Skill

Turns the current conversation context into a PRD and publishes it to the project's issue tracker. Use when the user wants to create a PRD from the current context.

wachawo Skill

Breaks a plan, spec, or PRD into independently pickable tasks in the project's issue tracker, using vertical "tracer bullet" slices. Use when the user wants to convert a plan into tasks, create implementation tickets, or split work into issues.

guillaumelessard Skill

QECTOR roadmap and promotion path (manual 27). Covers the four-step Provisional-to-stable promotion bar, the artifact roadmap, the candidate engineering items (CUDA primary context sharing, OpenCL side-wheel, hypergraph rejection testing), and the 1.x release policy. Load for any question about what is coming, what is a candidate, and when a Provisional symbol can be promoted.

guillaumelessard Skill

Quantum error correction research workflows on the QECTOR platform: threshold discovery, finite-size scaling, LER benchmarking with confidence intervals, decoder comparison, and publication-grade reproducibility artifacts. Uses the library MCP server (8 frozen tools) and the bench MCP server (29 provisional tools) for the math and DEM utilities. Load when a user wants to evaluate a code family, estimate a threshold, compare decoders, or produce paper-ready results.

a-v-ershov Skill

Commit the current uncommitted changes: read the diff, group files by logic rather than path (a definition change split from its ripple of usage updates), write conventional-commit messages in English — with the [T###] backlog task id where one applies — and commit on the current branch, never branching, pushing, merging, amending or adding AI-attribution trailers. By default only the files this session touched are committed. Invoked by run-task for checkpoint commits and by cut-release for the release commit; otherwise use ONLY on the user's explicit request to commit — finishing a task or a review is not such a request. /commit [--dry-run] [--single] [--all] [--message <msg>]

a-v-ershov Bundle

Drive ONE task through the full development cycle: the implementer builds it, a separate fresh verifier independently proves the acceptance criteria, its findings go back for exactly one fix round, the static gate plus this task's scoped test selection must be green (the whole suite is never run here), the human accepts the work or it is auto-accepted, and a checkpoint commit carrying the task id lands. Two entry points: a task id from the backlog, or a free-form request it files itself with origin: adhoc. A small, obvious change can take the quick lane instead. Anything the single fix round leaves open escalates to needs_human. Sequential, single working tree, current branch.

a-v-ershov Skill

Work through the development plan: take tasks from .dev-skills/build-plan/ one at a time and run each through run-task. The order is deterministic, not a judgement call — the ready task (status todo, all blocked_by done) with the lowest id; no parallel tasks, one working tree. It refuses to start when the spec has moved ahead of the plan and offers plan-development first, skips tasks another session has claimed, and never retries a needs_human task. By default it runs straight through, pausing only for a real reason; one-at-a-time and thinned acceptance are opt-in. Resumable — the backlog is the source of truth. Use after plan-development. It writes no code and duplicates no cycle.

a-v-ershov Bundle

Interview the human to extract maximum context before and during spec work — a relentlessly curious discovery grill that turns a short brief into a rich, shared understanding of what to build. Two roles: as the FIRST step of create-project-spec it runs a full intake interview and writes .dev-skills/project-spec/project-brief.research.md plus a short human summary, which every later phase reads as settled intent; on demand it is a reusable grill any phase can invoke, scoped to a fork blocked on context only the human holds. Captures intent, audience, scope, constraints and developer preferences as soft priors. It does NOT validate the idea or define features.

a-v-ershov Skill

Turn the finished project spec into a buildable backlog. Use after setup-dev-environment, as the planning step of the build phase: it reads the committed feature set, the user flows, the architecture and the dev-architecture, and emits a kanban backlog under .dev-skills/build-plan/ — one markdown file per task plus a derived board.md and a short plan.summary.md. Tasks are coarse on purpose: the backlog holds at most 15 open ones. When the repo already has working code it plans only the gap. Re-run after the spec changes and it amends instead — task deltas, never a regenerate; re-run with 'consolidate' and it merges the open backlog back under the ceiling. Run before build-tasks.

a-v-ershov Skill

Build one backlog task's feature in the working tree. Use as the implementation stage of the build loop — normally spawned fresh per task by run-task, or standalone on a task id. It reads the task's description and acceptance criteria, builds on the current branch following the project's CLAUDE.md and existing patterns, writes its journal into the task file as it goes, then self-verifies against .dev-skills/project-setup/verification.md and gets the static gate plus this task's scoped test selection green before handing off. It never runs the whole suite, does not run the verifier and does not commit.

adaptico Bundle

Customer-conversation engine for /gtm interviews <target>. Two jobs in one command - generate a customer-discovery interview kit (who to talk to, where to find them, questions that surface real past behavior instead of compliments, a per-conversation capture sheet), and synthesize the founder's transcripts or notes into validated pains, verbatim customer quotes, segments, and switching triggers, written back into PROFILE.md so positioning, copy, and outreach start from real customer language. Use when the user wants to talk to users or customers, validate a problem or an idea, prepare for user interviews, or make sense of interview notes. Also trigger for "customer interviews", "user interviews", "talk to customers", "customer discovery", "validate my idea", "interview questions", "discovery questions", "synthesize my interview notes", or "what did my customers actually say".

willianbs Bundle

Runs incident command: severity, roles, comms cadence, war-room loop, and stabilization criteria. Use for production outages and sev events. Emits INCIDENT_LOG. Never silently implements fixes or skips stakeholder updates.

mqmalagris Bundle

Turn a settled feature scope into a concrete implementation plan and write it to docs/plans/NNNN-<slug>.md. Plans the job like a heist — crew (files touched), sequence (ordered tasks), getaway (rollback/risks), payoff (acceptance criteria). Use when user has a PRD, ADR, or settled feature spec and wants a step-by-step build plan before coding. Triggers on /heist, "plan this feature", "implementation plan", "break this down", "how do we build X", or after to-prd / compass when ready to code.