Menu
SkillsMP a collecté 107 skills depuis Miosa-osa/canopy. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 40 skills collectés sur 107.
Evaluate retrieval and generation quality in RAG pipelines. Separate scoring for retrieval (recall, precision, MRR) and generation (faithfulness, relevance, completeness). End-to-end pipeline assessment with bottleneck identification. Triggers on: "eval rag",…
Langue du texte source : anglais
Design binary pass/fail LLM-as-Judge evaluators. Structured prompt engineering for evaluation: criteria definition, rubric construction, few-shot calibration, and bias mitigation. Produces a ready-to-deploy judge prompt with scoring instructions. Triggers on:…
Langue du texte source : anglais
Language Agent Tree Search - Monte Carlo planning - 92.7% on HumanEval
Langue du texte source : anglais
Self-learning system based on SICA, VIGIL, and Mem0 patterns. Auto-triggers after task completion. Captures patterns, consolidates memory, generates skills, recovers from errors.
Langue du texte source : anglais
Self-improving prompts through meta-level optimization
Langue du texte source : anglais
Optimize token usage through prompt caching and compression
Langue du texte source : anglais
Thought-Action-Observation loop for transparent reasoning
Langue du texte source : anglais
Self-correction via critique loop - 18.5 percentage point improvement
Langue du texte source : anglais
Sample multiple paths, select most consistent - +17.9% on GSM8K
Langue du texte source : anglais
Parallel generation through skeleton-first approach for 2x speedup
Langue du texte source : anglais
Generate diverse synthetic test inputs via dimension-based tuple generation. Defines variation dimensions, enumerates combinations, filters for relevance, and produces labeled test cases. For LLM eval pipelines, training data augmentation, and stress testing.…
Langue du texte source : anglais
Multi-path reasoning with evaluation and backtracking - 74% success on complex tasks
Langue du texte source : anglais
Calibrate LLM-as-Judge evaluators against human labels. Computes TPR, TNR, precision, recall, F1, and Cohen's kappa. Detects systematic biases and recommends prompt corrections. Produces a calibration report with confidence intervals. Triggers on: "validate…
Langue du texte source : anglais
Multi-domain audit with weighted scoring. Spawns parallel subagents per audit domain. Each check has severity weight and category weight. Produces a quantified health score (0-100) with prioritized findings. Supports security, code quality, performance,…
Langue du texte source : anglais
Guided analysis of LLM traces to categorize and pattern-match failures. Reads execution traces, classifies failure modes, detects recurring patterns, and produces actionable taxonomy of errors. For diagnosing why an LLM system fails and where to focus…
Langue du texte source : anglais
Audit an LLM evaluation pipeline for correctness, coverage, and reliability. 6 diagnostic areas with structured Check/Finding output. Produces prioritized findings by severity and recommends next skills to run. Catches common eval pitfalls before they corrupt…
Langue du texte source : anglais
9 graph analysis operations for knowledge networks: triangles (synthesis opportunities), bridges (critical connectors), clusters (isolated subgraphs), hubs (high-degree nodes), siblings (unconnected items sharing topics), forward/backward traversal, orphans,…
Langue du texte source : anglais
Workspace health diagnostics. Runs targeted checks against the knowledge base: orphaned content, stale signals, missing cross-references, index drift, duplicate detection, broken references, embedding coverage, and quality distribution. Color-coded severity…
Langue du texte source : anglais
Workspace metrics dashboard. Tracks growth rate, connection density, pipeline throughput, health score trends, budget consumption, and agent utilization over time. Includes trend detection for spotting degradation or acceleration. Triggers on: "stats",…
Langue du texte source : anglais
Create animation-rich HTML presentations from scratch or convert PowerPoint. Progressive disclosure pipeline: content discovery, style discovery, generation. Zero-dependency single HTML file output. Anti-AI-slop guardrails for natural, professional…
Langue du texte source : anglais
Visual task management dashboard. Terminal-based kanban board, tiled agent status view, and progress tracking. Shows all agents, their current tasks, budget consumption, and overall workspace health at a glance. Triggers on: "board", "dashboard", "kanban",…
Langue du texte source : anglais
Atomic task locking. Ensures only one agent works on a task at a time. Returns 409 Conflict if already locked. Auto-releases on agent death or timeout. Prevents double-work and wasted compute in multi-agent systems. Triggers on: "checkout", "lock task",…
Langue du texte source : anglais
Assign work to a specific workspace agent or external runtime. Picks the right adapter (Claude for reasoning, Codex for bulk changes, Gemini for multimodal). Creates tasks with parent chain tracking for full delegation lineage. Triggers on: "delegate",…
Langue du texte source : anglais
Agent wake-up and health monitoring protocol. 9-step startup cycle that grounds the agent in identity, fetches tasks, selects work, and begins execution. Also serves as a periodic health check — detect stalled or dead agents. Scheduled or event-triggered.…
Langue du texte source : anglais
Point-to-point messaging between agents. Send, broadcast, receive, and peek at messages. File-based implementation using JSON in inbox directories with atomic writes. Includes event log for full message history. The communication backbone. Triggers on:…
Langue du texte source : anglais
Authorize agent payments via Machine Payments Protocol (MPP). Handles microtransactions, API purchases, service subscriptions within budget governance. Triggered by pay, purchase, buy, transaction, payment, MPP, commerce.
Langue du texte source : anglais
Launch a specialized agent for a subtask. Assigns identity, workspace scope, available commands, and communication protocol. Supports tmux-based (visual) or subprocess (headless) execution backends. The primary way to parallelize work. Triggers on: "spawn",…
Langue du texte source : anglais
Autonomous iterative improvement loop. Agent modifies code, verifies against metrics, keeps improvements or reverts failures, and repeats. Uses git as memory — each change is committed, measured, and kept or discarded. Runs until a target metric is hit or max…
Langue du texte source : anglais
Transform any GUI application into an agent-controllable CLI. 7-phase pipeline: analyze the GUI, design CLI commands, implement adapters, plan tests, write tests, document, and publish. Produces a standalone CLI tool that wraps GUI functionality for…
Langue du texte source : anglais
Branch code review with structured scoring against project guidelines. Produces categorized findings with severity levels and LLM-generated fix prompts. Quality gate: only posts review to PR if score meets threshold. Triggers on: "code review", "review…
Langue du texte source : anglais
Guided spec creation through 9 phases from discovery to testing strategy. Supports spec types: library, feature, change. Produces a complete specification document with requirements, architecture, constraints, and YAML test data. Interactive or autonomous…
Langue du texte source : anglais
Enforces Test-Driven Development discipline with RED-GREEN-REFACTOR cycle
Langue du texte source : anglais
Human-in-the-loop approval gates. Creates approval requests for high-stakes actions like hiring agents, strategy proposals, or budget overrides. Tracks states from pending through approved/rejected/revision_requested. Blocks execution until resolved. Triggers…
Langue du texte source : anglais
3-tier budget enforcement for AI agent workspaces. Visibility dashboards (always on), soft alerts at 80% threshold, hard ceilings at 100% that auto-pause agents. Tracks per-agent, per-task, and per-project costs in both tokens and dollars. Triggers on:…
Langue du texte source : anglais
Add an agent to a workspace from the agent library. Proposes agent configuration including name, role, capabilities, adapter, and budget. Requires board approval via /approve before onboarding. Completes with identity setup and coordination prompt. Triggers…
Langue du texte source : anglais
Produce paid ad creative briefs + copy variants across 8 ad types (Profile Funnel / Retargeting / Video Hook / Video Story / Testimonial / Image / Carousel / UGC). the paid media director depth. Voice-matched. Compliance-checked. Ships ready for Meta Ads…
Langue du texte source : anglais
Design affiliate program structure — commission rates + payout logic + affiliate portal + promotion assets + recruitment outreach + compliance. Built for Stripe / ThriveCart / FirstPromoter / Everflow integrations.
Langue du texte source : anglais
Produce a high-ticket qualifying application form — 8-12 questions calibrated for show-rate + close-rate + refund-prevention. Offers 3 archetypes (high-barrier for founder calls / medium for setter screen / low for flywheel) with disqualification logic.…
Langue du texte source : anglais
Design a complete funnel architecture using one of 7 archetypes (VSL Funnel / Webinar / Application / Book-a-Call / Tripwire / Challenge / Community Lead Magnet). Consumes Offer Document + VSL Script + ICP. Produces funnel blueprint with stage-by-stage…
Langue du texte source : anglais
Build a complete Ideal Customer Profile Document (13 sections) with Completeness Score >= 80. Populates Compartment 2 (Audience Intelligence System) to at least 70%. Second skill in the Foundations chain — consumes Market Research Brief, produces ICP…
Langue du texte source : anglais