Claude Skills by Federico-Anastasi

Analyses the brief, runs a short Q&A, and produces the validated data model (tables, relations, integrations) in data_model.json. Updates context.md.

Builds the project decks (kickoff, recurring status report, estimate presentation, demo) in deck.json. The data-driven slides are regenerated, the hand-written ones are preserved. Exports to PowerPoint and HTML.

Designs graphic artefacts (social posts, stories, banners) as free HTML/CSS artboards in design.json — one artboard per design at its exact pixel size. The craft is in the guidance: committed aesthetic, brand tokens, anti-slop rules. Exports to design.html with per-post PNG download.

Breaks a confirmed estimate into granular dev tasks. Every estimate task becomes 1-3 assignable pieces of work, written inside estimate.json (epics[].tasks[].dev_tasks[]).

Produces the technical diagrams of the project (architecture, operational workflows, dataflows, sequences) in diagram.json. Uses the brief and the data model when available. Exports to a self-contained HTML.

Produces the work plan in days from the brief — epics, tasks, E2E test rows and contingency — in estimate.json. Uses the data model when one is available.

Turns a meeting recording or transcript into minutes people actually read: who was there, what was decided, what is still open, and who owes what by when. Writes a markdown file in meetings/.

Merges a meeting transcript into the project brief: updates brief.json incrementally, extracts the questions still open, records decisions and people, and flags contradictions with earlier meetings.

Composes a component-based mockup (mockup.json) from the standard themed component library. Uses the data model when available to structure the views. The interactive HTML is generated by the backend on demand.

Runs the whole estimation flow in one session: Q&A, data model, estimate, dev tasks, mockup. To produce a single deliverable, use the dedicated skills instead (/data-model, /estimate, /dev-tasks, /mockup).

Builds the application test plan from the estimate, data model, mockup and brief. Produces test_plan.json with cases traced to the estimate epics, exportable to Excel.

Triages a maintenance ticket on a delivered project: which area and epic are involved, which objects are likely affected, what the brief says should happen, and a first hypothesis. It does not fix anything — it points.

Analyses the brief, runs a short Q&A, and produces the validated data model (tables, relations, integrations) in data_model.json. Updates context.md.

Builds the project decks (kickoff, recurring status report, estimate presentation, demo) in deck.json. The data-driven slides are regenerated, the hand-written ones are preserved. Exports to PowerPoint and HTML.

Designs graphic artefacts (social posts, stories, banners) as free HTML/CSS artboards in design.json — one artboard per design at its exact pixel size. The craft is in the guidance: committed aesthetic, brand tokens, anti-slop rules. Exports to design.html with per-post PNG download.

Breaks a confirmed estimate into granular dev tasks. Every estimate task becomes 1-3 assignable pieces of work, written inside estimate.json (epics[].tasks[].dev_tasks[]).

Produces the technical diagrams of the project (architecture, operational workflows, dataflows, sequences) in diagram.json. Uses the brief and the data model when available. Exports to a self-contained HTML.

Produces the work plan in days from the brief — epics, tasks, E2E test rows and contingency — in estimate.json. Uses the data model when one is available.

Turns a meeting recording or transcript into minutes people actually read: who was there, what was decided, what is still open, and who owes what by when. Writes a markdown file in meetings/.

Merges a meeting transcript into the project brief: updates brief.json incrementally, extracts the questions still open, records decisions and people, and flags contradictions with earlier meetings.

Composes a component-based mockup (mockup.json) from the standard themed component library. Uses the data model when available to structure the views. The interactive HTML is generated by the backend on demand.

Runs the whole estimation flow in one session: Q&A, data model, estimate, dev tasks, mockup. To produce a single deliverable, use the dedicated skills instead (/data-model, /estimate, /dev-tasks, /mockup).

Builds the application test plan from the estimate, data model, mockup and brief. Produces test_plan.json with cases traced to the estimate epics, exportable to Excel.

Triages a maintenance ticket on a delivered project: which area and epic are involved, which objects are likely affected, what the brief says should happen, and a first hypothesis. It does not fix anything — it points.