Results for “deliverable”

Produce a professional, send-ready deliverable on the user's behalf — in the correct file format (never raw markdown), in the user's voice, structured to lead with the strongest material, and free of document-level AI tells. Runs a gated pipeline with a fresh-context verification policeman and a Stop-hook that won't let the session finish without a verified PASS. Use when producing a job take-home, client report, executive one-pager, slide deck, proposal, or anything going out under the user's name.

The English summary is being prepared. Showing the original description.

Reviews a whole deliverable against its manifest without rewriting it — deterministic gate, per-section finders, a whole-work pass, and adjudicated findings.json and report.md with honest coverage. Use before shipping a deliverable or for the night shift.

The English summary is being prepared. Showing the original description.

Opens a talk, module, paper, chapter, or referee report as a multi-session deliverable. Interviews the author, then scaffolds deliverable.yml, HANDOFF.md, the planning/ wiki, inbox/, and checks/. Use for deadline-driven work spanning sessions.

The English summary is being prepared. Showing the original description.

Checks a master document register extract for gaps and returns a DRAFT question list for document control: missing or out-of-sequence revisions, overdue or slipping deliverables, numbering that breaks the project convention, duplicates and incomplete rows, each with row, test and quoted evidence. Never edits the register, re-baselines a date or marks a deliverable complete. Use when the user asks to "check the MDR", "find the gaps in the deliverables list" or "prepare questions on the drawing register". Do not use for drafting a transmittal from a document list, use transmittal-drafter instead. Drafts for human review; never approves, authorises or signs off.

The English summary is being prepared. Showing the original description.

Convert the canonical markdown+JSON deliverable of any SfSkills runtime agent into Excel, PDF, CSV, Notion card, ServiceNow ticket, or similar downstream format WITHOUT polluting the consumer's project with new dependencies or regenerating from the agent's source logic. NOT for authoring new agent output formats (use DELIVERABLE_CONTRACT.md). NOT for data-export SOQL (use bulk-api-2-patterns).

The English summary is being prepared. Showing the original description.

Penetration test and red team report writing methodology. Covers executive summary structuring (risk-led narrative for non-technical readers), technical finding format (title, severity, affected scope, narrative, reproduction steps, impact, remediation, references), CVSS v3.1 / v4.0 scoring with vector justification, OWASP risk rating, evidence hygiene (redacting credentials, hashing client data, time-stamping every action), screenshot and PoC artifact management, finding chain narratives, scope/limitations/assumptions documentation, retest evidence and remediation tracking, deliverable formats (PDF, DOCX, HTML, JSON for SIEM ingestion), client-customer-deliverable separation, and common report mistakes (over-CVSSing, undermining the triager, missing the 'so what'). Use at the end of an engagement when authoring a deliverable, when restructuring a draft for executive readability, or when establishing a reusable report template for a consulting practice.

The English summary is being prepared. Showing the original description.

Independently reviews deliverables handed over through Kanban, checks them against acceptance criteria and test evidence, and records an approval, actionable change request, or escalation when a human decision or external prerequisite is needed.

• Reviewing deliverables against acceptance criteria
• Rechecking corrections after a change request
• Returning reproducible defects to the implementer

Create, edit, and clean spreadsheet files, convert table formats, and add formulas, formatting, or charts. The workflow includes recalculating formulas and checking errors before delivering a spreadsheet that updates when its inputs change.

• Clean messy CSV data into a spreadsheet
• Add formulas and charts to an Excel workbook
• Create a spreadsheet template for data entry

Coordinate agent work through the Paperclip API by checking assignments, updating task status, posting progress, delegating subtasks, and requesting approvals. It records deliverables and dependencies so reviewers and other agents can follow the work and continue it.

• Check assigned tasks and choose the next action
• Record progress and deliverables on a task
• Delegate subtasks and track dependencies

Delegate work to an existing Paperclip agent by selecting a suitable assignee and creating a task with clear objectives, constraints, and deliverables. Receive a lasting task reference and check progress after the conversation ends.

• Assign requested work to an existing agent
• Create tasks with clear constraints and deliverables
• Keep a task link for follow-up after the conversation

Turn an authorized plan into Paperclip work by deciding which tasks need separate owners, defining clear deliverables, and recording real dependencies so independent work can start and dependent work waits.

• Deciding which parts of a plan need delegation
• Assigning owners and clear deliverables
• Recording prerequisites between tasks

Extract text from PDFs, create new PDF documents, and work with forms. Use it for press releases, branded one-page documents, and printable design deliverables. The full workflow requires installing the upstream skill bundle.

• Extracting text from an existing PDF
• Preparing a press release as a PDF
• Creating a branded one-page document

Create, edit, and analyze Word documents with formatting, comments, and tracked changes that show revisions. Use it to prepare design briefs, copy documents, and deliverables ready for review.

• Preparing a design brief in Word
• Revising copy with tracked changes
• Preparing documents with comments for review

Coordinate multiple AI agents through a lead agent that breaks goals into tasks, delegates to research, coding, analysis, and testing workers, monitors progress, resolves conflicts, and brings their work together into a final deliverable.

• Splitting complex projects into tasks and dependencies
• Delegating research, implementation, analysis, and testing
• Monitoring progress and reassigning delayed work

Review an AI team's work against its acceptance criteria using collected evidence. Match requirements to task results or artifacts, distinguish verified facts from agent claims, and identify uncertainty or missing work before recommending completion.

• Review evidence before closing an AI team run
• Check whether deliverables meet acceptance criteria
• Separate verified results from agent claims

Verify documents, spreadsheets, presentations, and web deliverables before sharing them. Combine file checks with inspection of freshly rendered output, and scan for unfinished text to catch clipped content, layout problems, and leftover placeholders.

• Check documents before delivery
• Inspect rendered pages for layout problems
• Find leftover placeholders and sample text

Create, edit, or inspect standalone documents such as memos, reports, and proposals. Use the shared documents skill to handle Word, Google Docs, or PDF deliverables, preserve the requested format, and verify the document before delivery.

• Turn notes into an editable decision memo
• Update a Word proposal with tracked changes
• Check definitions and footnotes in an existing agreement

Create, edit, and clean spreadsheet files, including Excel workbooks and CSV data. Add formulas, formatting, and charts, preserve existing workbook conventions, and recalculate formulas with error checks before delivering the spreadsheet.

• Clean messy CSV data into a spreadsheet
• Edit an Excel workbook while preserving its formatting
• Create a financial model with recalculating formulas

Read, create, and edit Excel workbooks, including formulas, formatting, charts, and multiple sheets. Clean CSV or TSV tables and prepare spreadsheet deliverables, with guidance on choosing fixed calculated values or formulas that update later.

• Clean inconsistent CSV or TSV tables
• Build Excel reports with totals and charts
• Update an existing workbook while keeping its formatting

Create, edit, and clean spreadsheet files, including Excel workbooks and CSV data. Add formulas, formatting, and charts, preserve existing template styles, and recalculate formulas to check for errors before delivering the spreadsheet.

• Clean messy CSV rows and headers into a usable spreadsheet
• Add formulas and charts to an existing Excel workbook
• Build a financial model with editable assumptions

Turn a Zoom integration idea into a practical implementation plan. Identify the required products and APIs, authentication and access permissions, delivery phases, and risks, then define a small first deliverable to test the proposed architecture.

• Turning a Zoom integration idea into a build plan
• Clarifying authentication and access permissions
• Planning delivery from prototype to launch

Deliver knowledge-page updates with links derived from Git paths and checked after pushing. Use defined alternatives for local repositories, rewrite paths relayed by other agents, and keep links between pages relative to preserve their connections.

• Include verified page links in completion messages
• Investigate page links that return a 404 error
• Rewrite local paths returned by other agents for delivery

Draft freelance contracts, project proposals, and confidentiality agreements with clauses tailored to US, EU, UK, or DACH contexts. Organize scope, payments, ownership, and deliverables in Markdown, with instructions for conversion to Word.

• Drafting a contract for a new freelance engagement
• Preparing a client proposal with budget and timeline
• Defining deliverables and acceptance criteria

Guide new Kortix users from a vague idea to a concrete task and a finished deliverable. Introduce relevant connections, memory, parallel agents, or scheduled follow-ups as useful next steps after completing the first result.

• Help new users choose their first Kortix task
• Turn a vague request into a concrete deliverable
• Guide users through completing their first result