Erkennt kriechende Mandatserweiterung und erzeugt Nachtragskommunikation. Für Managing Partner, Management Committee oder COO/CFO einer deutschen mittelständischen Kanzlei mit…
Scope Cut Behördenfragen einhegen: Zu weite Behördenfragen nach Zeitraum, System, Datenart, Gesellschaft und Betroffenenkreis begrenzen. Normanker: DSGVO Art.
Limit an agent's blast radius before implementation by defining allowed files, read-only areas, forbidden operations, commands, and stop conditions.
Analyze task scope and recommend execution strategy (sub-agent, multi-session, or scope cut). Orchestrates existing skills like /decompose, /task-enrich, and /task-handoff.
Block scope creep. Every feature ask gets pressure-tested against scope.md. Bar to amend: specific evidence from real users.
Use when creating handoff documentation for branched conversations in stay-on-target focused mode
Use after the goals are set and before design — to draw a project's boundary: what's in, what's explicitly out, and the smallest cut that still meets the goal.
بروتوكول قفل النطاق — لكل طلب ميزة/تغيير كود قبل كتابة أي سطر: عقد نطاق صريح (داخل/خارج) + قيود التنفيذ + انتظار موافقة بكلمة واحدة.
Grill a cliban ticket or milestone until every decision that changes the slicing is settled, then fill it with tracer-bullet tickets carrying native blocking edges.
Use when a request is broad, fuzzy, overgrown, multi-directional, or likely to balloon, and Codex needs to reduce it to the smallest valuable current-turn scope.
Open source license compliance audit — flag GPL, LGPL, AGPL, copyleft risks. Use when asked to "check our open source licenses", "do we have GPL risk", or "run an OSS license…
Create technical implementation plan and time estimate. Use this for planning and estimation when user asks to create an implementation plan or estimate.
Adversarial project planning workflow. Explores the problem space, drafts tickets in batches, then runs two sequential adversarial loops — a UX reviewer ("should we build this?")…
Use when the user wants feedback on whether a game's scope is achievable, evaluate project feasibility, identify what to cut, or assess whether constraints are being used as…
Triage §Side findings into child GitHub issues. Reads the parent issue's §Side findings section, lets the user pick which entries to spin off, files each via /sketch's mechanics…
Scope the project to a vertical slice that proves the core loop is fun before scaling content, to de-risk the build. Reach for this at greenlight.
Judgment rules for locating the correct boundary of a requested change: staying inert outside it while completing every required site inside it.
Use after changing code, before claiming work is done — picks the correctly scoped pytest command instead of running the whole suite.
ScopeMaster integration. Manage Organizations, Users. Use when the user wants to interact with ScopeMaster data.
Help users scope projects and cut features effectively. Use when someone is defining an MVP, dealing with scope creep, trying to ship faster, or needs to make tradeoffs about what…
Define the scope and purpose of a complex inquiry before mapping or futures work begins. Use when a class or group needs to agree what they are investigating, who it matters to,…
Use when POC scope, exclusions, participants, data boundaries, environments, and success criteria must be defined before work starts.
Score commits using Claude Haiku to measure intellectual value and categorize changes. Use after extraction to add AI-powered productivity metrics. Requires an Anthropic API key.
Score any recurring object against a written rubric and return a decision you can defend, with the evidence that earned it.
Score and prioritize leads or cold contacts (mixed ZoomInfo person IDs, emails, or name+company rows).
Berekent en vergelijkt speler- en teamscores via de Geunificeerde Score Schaal (USS). Vertaalt KNKV teamratings, scouting spelersscores, coach-evaluaties en spelerratings naar een…
Apply reusable evaluators to model outputs when you need lightweight scoring, rationale capture, or quick eval loops in code.
Measure whether a RAG change actually improved answers and retrieval, instead of guessing from a few spot checks.
Score a single role against the user's ICP and scoring weights. Triggers on "score this role", "score this JD", "is this a fit", "rate this", "/score", or pasting a JD URL with no…
Use when when comparing raw link scores (strain correlation or IOKR) across different GCF-MF or BGC-spectrum pairs and you need to distinguish true positive links from background…
Audit the OpenSSF Scorecard rating for py-lintro. Use when asked to check the scorecard, understand the rating, or find what's missing. Specific to github.com/lgtm-hq/py-lintro.
ScoreDetect integration. Manage Organizations. Use when the user wants to interact with ScoreDetect data.
Motor de scoring cuantitativo del Financial Intelligence System. ACTÍVALO cuando el orquestador necesite consolidar outputs de múltiples módulos en un score compuesto, cuando el…
Structures ESG scoring methodology with environmental, social, and governance pillar assessment. Use when scoring ESG, evaluating sustainability, or building ESG frameworks.
Use when you have two or more complementary scoring functions (e.g., strain correlation and IOKR scores) that you wish to combine, and you need to determine which combination…
Conduct a focused interview to capture complete bug details and write a structured bug report for downstream investigation.
Investigate a reported bug, identify likely root cause with evidence, and produce a handoff for scorpio-task-plan.
Manage git branching, staging, and commits with strict safety rules. Determines the appropriate branch, stages changes, creates conventional commit messages, and never touches a…
Execute development tasks from task files. Implements code in focused subagent sessions. Use when the user has task files to execute, wants to run through a task list, or asks to…
Curate high-signal lessons from postmortems, QA reports, and retrospectives into concise, non-redundant entries with root causes and mitigations.
Create a database migration the right way for the project's ORM/migration tool — edit the schema, generate the migration, review the SQL, then apply it.
Assemble coherent strategic solution packages from objective parameters and scenario dimensions without scoring or selecting a winner.
Critique the strongest objective solution packages without generating replacements or editing package content.
Score objective solution packages against the fixed rubric without editing packages or selecting a winner.
Conduct the objective intake interview that normalizes a business objective into canonical planning artifacts for the objective workflow.
Expand normalized objective parameters into bounded strategy dimensions without selecting a winning package.
Synthesize scored and critiqued objective packages into one recommendation with alternates and explicit tradeoffs.
Analyze a failed or degraded pipeline run to produce an evidence-backed diagnosis with root causes, affected sessions, and proposed remediation tasks.
Conduct a structured PM-style requirements interview to extract roles, user stories, process flows, and technical decisions.
Per-task code review that validates acceptance criteria, checks correctness, and catches bugs immediately after implementation.
Review QA findings, classify issues, and generate rework tasks for scorpio-execute. Use after scorpio-qa-final produces a QA report to decide what needs fixing and what can be…
Prepare code for release — generate PR descriptions, compile release notes, run pre-merge checklists, and define post-merge verification.
Analyze completed development cycles to extract lessons learned, identify recurring patterns, and improve future workflows.
Systematically explore a codebase to find bugs, code quality issues, and improvement opportunities. Produces a prioritized report with findings that route into existing…
Translate an approved objective package into SOLUTION-BRIEF.md and canonical TASK-PLAN-HANDOFF.json without reopening package choice.
The reality-check hotline. Mid-conversation, leave the closed room and go to the internet to ground what was just said against how the world actually does it.
START HERE — Skill discovery and installation assistant. The recommended first skill when you don't know which skills you need.
Für Scout- und Advisor Agreements: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Scout APM integration. Manage data, records, and automate workflows. Use when the user wants to interact with Scout APM data.
Detects and removes cognitive biases from reasoning using Julia Galef's Scout Mindset framework. Provides reversal tests, scope sensitivity checks, status quo bias tests,…