Каталог навыков агентов

Specialist reliability workflow for AndroidX Media3 playback, MediaSession/MediaLibrarySession, MediaLibraryService, And...

Retrieves, classifies, validates, and optionally persists compact durable knowledge so future tasks can reuse verified e...

High-rigor model-agnostic engineering and visual-production skill protocol for complex, risky, multi-file, debugging, ar...

Defines a compact preservation contract before risky changes to working systems. Use for cache, playback, persistence, s...

Production observability and instrumentation skill for services, background jobs, queues, external integrations, retries...

Evidence-driven performance engineering for latency, throughput, CPU, memory, startup, build time, rendering, I/O, concu...

Maintains an opt-in, repository-local project knowledge layer for stable architecture, invariants, decisions, regression...

Project-version-aware Python engineering for services, libraries, automation, data tooling, and applications. Use for Py...

Adaptive deliberation layer for difficult engineering and design work. Use when a task is ambiguous, high-risk, multi-st...

Behavior-preserving refactoring protocol for simplifying, restructuring, modularizing, or modernizing existing code with...

Runs risk-sized, evidence-first review of code changes. Use before completion, PR creation, or after meaningful implemen...

Chooses the smallest compatible process, language, domain, platform, visual, cognitive, and installed-skill stack for a...

Project-aware Rust engineering for libraries, services, CLIs, async applications, and systems code. Use for Rust source,...

Performs evidence-backed application and agentic-workflow security review. Use for auth, authorization, untrusted input,...

Autonomous skill-selection layer for Thalarch. Use at the start of non-trivial work and again after project discovery wh...

Grounds version-sensitive framework, library, runtime, browser, database, and platform decisions in the exact project ve...

Turns broad feature or architecture requests into an executable acceptance contract. Use for multi-file features, refact...

Audits provenance and instruction-supply-chain risk for external skills, MCP/tool descriptions, retrieved prompts, agent...

Runs a bounded teacher/judge/revision loop around model-produced engineering work. Use when an independent evaluator can...

Designs high-value regression, property, integration, fuzz, and risk-based mutation tests for behavior changes. Use afte...

Project-aware TypeScript/JavaScript engineering for browser, Node.js, full-stack, libraries, and tooling. Use for TS/JS...

Directs distinctive, product-specific UI/UX work and visual verification. Use for redesigns, new interfaces, layout, sty...

Performs evidence-first visual QA for images, generated assets, screenshots, branding, image edits, diagrams, and implem...

Designs and implements distinctive, production-grade websites, landing pages, dashboards, web apps, and frontend compone...

Debrief the user after a real interview and draft personalized thank-you notes to each interviewer. Use right after the...

Automate Thanks IO tasks via Rube MCP (Composio). Always search tools first for current schemas.

System maintenance, memory queries, and pattern analysis. USE WHEN user mentions system, memory, patterns, history, past...

"Provides Thanos in High availability Prometheus solution with long-term storage"

The Thanos review method, a Steve Jobs-style simplicity review for code diffs, design documents and architecture. Use wh...

Route all OpenClaw user messages through Thanos orchestration.

General SOP for common requests related to that, can, as.

General SOP for common requests related to that, more, chinese.

Coordinate incoming bug reports for a project: triage reports from the user or from other agent sessions over cross-sess...

Use when the user asks "walk me through this change", "explain what this PR does", or wants to understand the code touch...

Prose rules for every piece of text a human reads that no dedicated skill already covers - PR and ticket comments posted...

Use when the user asks you to investigate an existing feature, debug an unfamiliar area of the code, or begin a new tick...

Use when the user asks "walk me through this feature", "how does X work", or wants on-demand documentation about a featu...

Plan and execute code changes with a task-list-driven workflow. Use when implementing features, fixing bugs, or making m...

Classify the relationship between two similar memory entries for deduplication. Use when thatch_find_duplicates identifi...

Extract durable project facts, user preferences, and environment knowledge from recent tool interactions. Use when thatc...

Compile everything thatch knows about a topic into a curated, self-contained markdown file for knowledge transfer to ano...

Fact-check a single thatch memory against the current codebase and correct it if stale. Use when the user asks to verify...

Consistency audit for a plan document - a section-vs-section contradiction sweep checking whether the plan's own section...

Evidence audit for a plan document - an exhaustive citation sweep verifying that every file, line, function, constraint,...

Refine a plan for a code change by dispatching a fresh-context reviewer subagent to hunt for gaps, unverified premises,...

Draft a PR description (SYNOPSIS / PURPOSE / DESCRIPTION / WALK-THROUGH / NOTES) with bold and italic emphasis on the ph...

Prime the project memory store by investigating the codebase from multiple angles and writing foundational memories. Use...

Classify the current project (audience, lifecycle, surface) and refine a plan under that type's requirements. Entry poin...

Type-specific requirements for refining a plan that touches infrastructure (CI pipelines, Terraform, Kubernetes manifest...

Type-specific requirements for refining a plan for a contribution to an open source repository the user does not maintai...

Type-specific requirements for refining a plan in a solo personal project with no downstream consumers. Loaded by thatch...

Type-specific requirements for refining a plan that touches a library's API surface, in any repo, including personal one...

Type-specific requirements for refining a plan for a throwaway prototype or time-boxed spike. Loaded by thatch-refine af...

Type-specific requirements for refining a plan in a multi-developer team codebase (production app or service shared by a...

Behavioral and product-level code review — UX coherency, behavioral delta, integration effects, user assumptions. Use fo...

Comment narrative evaluation — do comments form a coherent outline of the code's behavior? Use for post-implementation r...

Prose clarity in the change's comments, docstrings, error strings, and docs - made-up phrases, buzzwords, untranslated j...

Gather project and feature context before a code review. Investigates PR descriptions, git history, ticket references, l...

Design simplicity and maintainability review — is the complexity earned? Evaluates both the overall change design (the f...

Alternate entrypoint for follow-up review rounds. Verifies whether the author's responses and code changes since your la...

Positive finding detection — notably clever solutions, cleanup done along the way, documentation that meaningfully helps...

Mechanical change completeness audit — verifies that renames, flag removals, API substitutions, and mass replacements le...

AI writing anti-pattern detection — change narration comments, fourth wall breaks, em dashes, hedging, filler, stale ins...

Mechanical correctness code review — spelling, naming, doc accuracy, specs, guidelines, stale artifacts, structural conv...

Respond to code review on the user's own PR. Triage findings (legitimate, intentional, false positive, unlikely edge cas...

Data flow and contract code review — module boundaries, implicit state machines, error propagation, separation of concer...

Verify and synthesize findings from multiple review specialist skills into a single deduplicated, severity-grouped repor...

Technique review lens — teaching-grade observations the author can act on or dismiss: helpers and internal packages they...

Record what you learned during a session — project facts, user preferences, tool tips, self-identity. Use at the end of...

Split already-completed work from an overlarge PR into human-reviewable, release-safe PRs. Use when the user asks to spl...

Draft a ticket description (SYNOPSIS / PROBLEM / BACKGROUND / PROPOSED APPROACH / ACCEPTANCE CRITERIA / RELEASE PLAN / V...

Break the paralysis on the thing you keep not starting with a 2-minute launch sequence — a countdown into motion before...

This prompt instructs an image generator to produce a photorealistic, cozy winter travel portrait in a vertical, medium...

Architecture decisions, trade-off analysis, and ADR authoring. Trigger when a significant technical decision needs to be...

This skill should be used when engineering decisions are being made during code implementation. The Archivist enforces d...

Strategic communication filter. Transforms raw emotional input into strategic output. Use when user says 'audit this', '...

Audits the codebase for security vulnerabilities and regulatory compliance (LGPD, GDPR, DORA, MiCA, HIPAA, SOC II, ISO 2...

Scan a plan, draft, or idea for the generic, textbook, everyone-would-say-that lines — and push each toward something sh...

Embody The Buddha - AI persona expert with integrated methodology skills

Ensures the application builds successfully and fixes any build errors.

This prompt instructs an AI to generate a dramatic fantasy battle scene dominated by a divine firestorm, specifying the...

Simulate the car-buying gauntlet before you walk in — the four-square worksheet, the payment-question trap, the trade-in...

This prompt instructs an image-generation model to produce a high-resolution, photorealistic vertical nighttime interior...

Simulate the exact customer who will quietly cancel in month 4 — their internal monologue through the lifecycle and the...

Creates well-structured git commits with conventional commit messages and proper attribution.

Turns a set of hook verdicts (from the viewer panel, the four failures check or user feedback) into the top 3 changes, r...

Run The Crucible (圆桌萃鉴), a rigorous evidence-backed multi-reviewer review. Configure a confirmed table, preserve separat...

Transfer der Multi-Agent Orchestrierungs-Patterns aus the-dmz (TheMorpheus407) auf Hermes/GreyHack. Enthält: auto-develo...

Simulate the due-diligence call where an acquirer's or investor's analyst takes your metrics apart — the questions behin...

Simulate defending your study or protocol before an ethics committee — the consent-comprehension probe, the vulnerable-p...

The Fool workflow skill. Use this skill when the user needs challenging ideas, plans, decisions, or proposals. Invoke to...

Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's a...

Stress-test a pending decision, plan or claim with its rationale, alternatives and reversibility; expose concrete threat...

Use when challenging ideas, plans, decisions, or proposals. Invoke to play devil's advocate, run a pre-mortem, red team,...

Challenges ideas, plans, decisions, and proposals using structured critical reasoning as devil's advocate, pre-mortem, r...

Operate The Forge graphics framework at its current Codeberg source: inspect pinned Windows/D3D12 scope, audit component...