Results for “spec”

Transform Markdown or text specifications into human-readable HTML documents with summaries, reordered structure, visual explanations, diagrams, charts, and traceability to the source. Use when asked to convert a spec, requirements document, API spec, product spec, design doc, or technical document into readable HTML, especially when the user wants summarization, restructuring, diagrams, graphs, images, or visual aids rather than a literal Markdown-to-HTML conversion.

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

Weed the Allium garden. Find where Allium specifications and implementation code have diverged, and help resolve the divergences. Use when the user wants to check spec-code alignment, compare specs against implementation, audit for spec drift or violations, sync specs with code or code with specs, or verify whether the implementation matches what the spec says.

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

Manage and run Spec Kit automation workflows via `specify workflow`. USE FOR: running a workflow by ID or local YAML, resuming a paused/failed run, checking run status, listing/installing/removing workflows, searching the workflow catalog, showing a workflow step graph. DO NOT USE FOR: extensions (use speckit-extension), presets (use speckit-preset), or bundles (use speckit-bundle).

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

Check the local environment for Spec Kit by running `specify check` (and `specify version`). USE FOR: verifying required tools are installed, diagnosing a broken spec-kit setup, reporting CLI version/feature capabilities. DO NOT USE FOR: installing or upgrading the CLI itself (use the speckit-self skill).

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

Genera una nueva especificación de cambio ligera copiando el directorio de plantilla de especificación en una carpeta de especificación con nombre. Úsalo cuando la persona quiera iniciar una especificación, planificar un cambio/funcionalidad o crear un documento de diseño antes de implementar (p. ej. "especifica el rediseño del checkout", "crea una especificación para el nuevo flujo de autenticación").

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

Deep spec analysis on a Confluence page. Reads page (+ children) via the confluence-as wrapper, produces a structured Spec Research Report with requirements, acceptance criteria, gaps, ambiguities, and suggested user stories for human review. Read-only — does NOT create Jira tickets. Triggers: 'analyze spec for PAGE-ID', 'extract requirements from confluence page', 'spec research on URL'. NOT for raw page CRUD (mk:confluence-page); NOT for ticket complexity scoring (mk:planning-engine).

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

Bootstrap project-specific Trellis coding specs with a platform-neutral single-agent workflow. Use when creating or refreshing .trellis/spec guidelines, analyzing a codebase with GitNexus, ABCoder, or source inspection, decomposing package/layer spec work, and writing real codebase-backed spec docs without placeholder text.

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

Debug Node.js from the terminal by pausing execution, inspecting variables, and tracing function calls. Use interactive commands or scripts to investigate failing tests, collect runtime state, and capture CPU profiles or memory snapshots.

• Inspecting intermediate state in failing Node.js tests
• Tracing function calls and unexpected variable values
• Investigating stalled asynchronous processing

Find available AI models across configured providers and browse a catalog that includes provider-specific variants. Inspect individual models and create or update aliases, alternative names used to refer to models.

• List models available across configured providers
• Browse provider-specific model variants
• Create or update a model alias

Turn a feature idea into a structured specification before coding. Review requirements, system connections, constraints, and failure scenarios, define testable acceptance criteria, and save the specification in memory for later development phases.

• Defining requirements before building a new feature
• Writing testable acceptance criteria
• Documenting constraints and failure scenarios

Create concise B2B outreach emails and follow-ups tailored to a prospect’s situation. Plan sending setup, coordinate email with LinkedIn and other channels, and organize reply handling to move interested prospects toward meetings.

• Writing an initial email tailored to a prospect’s situation
• Planning follow-ups that add new information
• Coordinating email and LinkedIn outreach

Clean and compare tandem mass spectra, measurements used to study molecular fragments, with matchms. Standardize metadata, filter peaks, search reference libraries, and export ranked candidate matches with similarity scores and matched-peak counts.

• Clean MS/MS spectra and standardize metadata
• Search reference libraries for compound candidates
• Compare spectra using similarity scores and matched peaks

Search the 1000 Genomes Project’s 3,202 participants for genetic variants and their carriers. Filter by frequency or annotations, inspect variants in selected individuals, and check relatedness between two participants.

• Find participants carrying variants that match specified criteria
• Inspect genetic variants carried by selected participants
• Identify participants with two reference copies at a position

Turn a specification file into a GitHub feature request issue. The skill extracts requirements, checks existing issues, and creates or updates one issue covering the specification, using a template to organize the problem, solution, and context.

• Turn a specification into a feature request issue
• Check existing issues before registering a request
• Update an existing issue with specification requirements

Turn an existing GitHub Actions workflow into a structured specification for maintenance and AI reference. Document its purpose, triggers, job dependencies, inputs, outputs, permissions, and failure handling, focusing on expected behavior rather than implementation details.

• Documenting an existing GitHub Actions workflow
• Reviewing job order and dependencies
• Organizing permissions and failure handling

Create structured Markdown specifications that AI agents can read and use. Organize requirements, constraints, interfaces, acceptance criteria, and testing plans into a self-contained document with clear definitions and examples.

• Writing specifications for AI-assisted implementation
• Defining requirements and acceptance criteria
• Documenting APIs and data contracts

Check training data and machine learning models for malicious changes, including backdoors that cause unexpected behavior on specific inputs. Combine data quality checks, model analysis, and file integrity verification, then document findings and retest after remediation.

• Screening third-party data before training
• Checking downloaded model weights before deployment
• Investigating unexpected behavior on specific inputs

Build a sales prospecting package by researching the market, ranking potential customers, drafting messages in the sender's voice, and logging outreach. Separate approvals govern key stages, with customer files and spreadsheets supporting work when connectors are unavailable.

• Find prospects similar to existing paying customers
• Use market and competitor changes to refine sales targeting
• Draft personalized outreach for an approved prospect list

Find prospective customers resembling your best existing customers, identify relevant decision makers, and rank them by fit, buying signals, and ease of contact. Results include reasons to reach out, source information, and a full XLSX list.

• Finding companies similar to your best customers
• Building a prioritized prospect list
• Identifying decision makers and contact routes

Draft personalized sales emails or a series of follow-ups using prospect details and past conversations. Create reviewable email drafts, provide copy-ready text when tools are unavailable, and send or enroll contacts in outreach sequences when requested.

• Writing a first sales email to a prospect
• Following up on an earlier email conversation
• Re-engaging a prospect after a gap

Plan features before coding by defining requirements, acceptance criteria, and scope. Validate the specification, generate starter tests from expected behaviors, and guide implementation and review so each delivered feature can be checked against its agreed requirements.

• Define requirements before implementing a feature
• Turn acceptance criteria into starter tests
• Check specifications for missing requirements

Write and improve B2B outreach emails to new prospects, with relevant opening lines, subject options, and one clear request. Build follow-up sequences with sending intervals, or use performance data and a scoring script to identify revisions.

• Drafting a first outreach email to a new business prospect
• Building follow-up emails with distinct angles and sending intervals
• Rewriting an overly promotional sales email

Convert a Notion specification into a linked implementation plan and manageable tasks. Extract requirements and acceptance criteria, record uncertainties, and keep task statuses, checklists, blockers, and milestone updates aligned as the work progresses.

• Turn a Notion feature specification into a plan
• Break implementation work into one- or two-day tasks
• Link specifications, plans, and task pages

Run a structured sprint retrospective, a review of a short work cycle, using team feedback and delivery results. Identify shared themes and produce two or three prioritized improvements with owners, deadlines, and measures of success.

• Facilitating a team retrospective
• Grouping survey responses and team feedback
• Turning problems into assigned improvement actions