Just-In-Time Research

just-in-time-research

Load when making decisions that require external knowledge - technology evaluation, standards/compliance checking, market data, or current best practices not in your training data.

telum-ai/speck·0installs2stars

SKILL.md

Full skill instructions

Just-In-Time Research

When you encounter a decision requiring external knowledge (standards, best practices, market data, technical evaluation), conduct research immediately rather than guessing.

When This Rule Applies

Load this rule when:

Evaluating technology choices or comparing options
Checking standards/specifications (WCAG, RFC, ISO)
Assessing compliance or regulatory requirements
Needing current market data or statistics
Looking up integration patterns for external services
Any decision where your training data may be outdated

Do NOT research for:

Well-established patterns you're confident about
Decisions already documented in loaded artifacts
Basic programming concepts

Research Priority Order

Use research tools in this order:

Check existing research first - Look for *-research-report-*.md files in the project/epic directories
Perplexity MCP (if configured) - Use perplexity_search for quick facts, perplexity_research for deep analysis
Built-in web_search - Fallback when Perplexity unavailable
Generate manual prompt - If automated tools insufficient, create a prompt for the user

Research Workflow

Step 1: Check Existing Research

Before conducting new research, always check:

specs/projects/[project-id]/*-research-report-*.md
specs/projects/[project-id]/epics/[epic-id]/*-research-report-*.md

Also check if upstream artifacts (architecture.md, context.md, ux-strategy.md) already contain relevant "Research Informing" sections.

If relevant research exists:

Load and extract relevant findings
Reference as "Reused Research" in your research trail
Only conduct new research if gaps remain

Step 2: Identify the Knowledge Gap

Ask yourself:

What specific information is missing?
Can this be decided from well-known best practices?
Do I need current/external information to decide wisely?

Step 3: Execute Research

For quick facts (standards, specs, simple lookups):

Use perplexity_search or web_search

For analysis (trade-offs, comparisons, deep dives):

Use perplexity_research

For complex decisions (multi-factor analysis):

Use perplexity_reason

Step 4: Synthesize and Document

Extract key findings with source URLs. Add to the artifact:

## Research Informing This Section

- **[Topic]**: [Finding] (Source: [URL], [Date])

When Automated Research Fails

If research tools don't provide sufficient information:

Create a research prompt file: [command]-research-prompt-[topic].md
Tell the user: "Deep research needed for [topic]. Please run this prompt in your preferred research tool."
Pause and wait for the user to provide findings
Continue after incorporating results

Quality Guidelines

Prefer official documentation over blog posts
Use recent sources (2 years for standards, 6 months for market data)
Cross-reference multiple sources for critical decisions
Note when information may be outdated
Document what research influenced what decision

Commands That Use This Pattern

Project Level: /project-ux, /project-context, /project-constitution, /project-architecture, /project-design-system, /project-plan

Epic Level: /epic-architecture, /epic-plan

Story Level: /story-plan

Install skill

Copy and run in your terminal

npx -y skills add https://github.com/telum-ai/speck --skill just-in-time-research

View on GitHub

.cursor/skills/just-in-time-research/SKILL.md

epic-outline
DEPRECATED in Speck v7. Use /speck-skeptical-review + /speck-decision-log instead — they replace the outline pattern with structured tradeoff enumeration and lockable decisions. The v6 epic-outline pattern (research mapping) is now embedded in /epic-plan's just-in-time research step. This skill r...
0 installs
project-specify
Load at the very start of a new project when the user describes what they want to build, or to update an existing project.md. Produces project.md — must run before project-clarify, project-context, and all downstream project commands. FIRST ACTION after loading: read template at .speck/templates/...
0 installs
epic-constitution
Load when an epic has unique technical principles that extend or override the project constitution. Produces epic-level constitution.md — optional, skip when the project constitution is sufficient for this epic's concerns.
0 installs
oauth-implementation
Load when implementing OAuth 2.0 and OpenID Connect authentication. Applies when building social login, SSO, PKCE flows, or integrating with OAuth providers like Google, GitHub, Apple.
0 installs

More skills from telum-ai

telum-ai/speck

project-brainstorm

Load when a user has a vague idea, problem, or inspiration but isn't sure what to build. Use before /project-specify when the project concept needs crystallizing from loose thoughts into something concrete.

2 0

View

telum-ai/speck

docker-containerization

Load when using Docker for containerizing applications. Applies when creating Dockerfiles, docker-compose setups, multi-stage builds, or optimizing container images.

2 0

View

telum-ai/speck

visual-quality

Enforce visual design quality in every UI file. Fires for .tsx, .jsx, .vue, .svelte, and similar component files. Ensures implementations express the project's design personality rather than producing generic/boilerplate UI.

2 0

View

telum-ai/speck

project-clarify

Load after project.md exists to fill gaps through targeted Q&A. Use when project goals, target users, or scope feel underspecified. Run before project-context or project-architecture to prevent rework downstream.

2 0

View

telum-ai/speck

story-outline

DEPRECATED in Speck v7. Use /speck-skeptical-review + /speck-decision-log instead — they replace outline-style research mapping with structured alternative enumeration and decision locking. /story-plan now performs just-in-time research inline. This skill remains for v6 compatibility but redirect...

2 0

View

telum-ai/speck

offline-first-architecture

Load when building offline-first applications that work without network connectivity. Applies when implementing local storage, sync queues, conflict resolution, or background sync.

2 0

View

telum-ai/speck

project-constitution

Load (Platform play level only) to define technical principles and architectural guardrails for the project. Produces constitution.md — optional but valuable when a team needs explicit coding standards, governance rules, or non-negotiable constraints. FIRST ACTION after loading: read template at ...

2 0

View

telum-ai/speck

posthog-integration

Load when integrating PostHog for product analytics and feature flags. Applies when implementing event tracking, A/B testing, session replay, or funnel analysis.

2 0

View

telum-ai/speck

project-validate

Load when all epics are validated and /audit has run for the project. Verifies the project meets its original vision and product-contract.md paid promise. Runs end-to-end JTBD smoke test via /larp across all personas. Declares a project-level readiness state. Produces project-validation-report.md...

2 0

View

telum-ai/speck

story-scan

Load for brownfield stories where existing code must be understood before planning. Use when a story extends, modifies, or integrates with significant existing functionality. Produces codebase-scan.md — skip for fully greenfield stories. FIRST ACTION after loading: read template at .speck/templat...

2 0

View

telum-ai/speck

serverless-architecture

Load when building serverless applications with AWS Lambda, Vercel Functions, or Cloudflare Workers. Applies when implementing FaaS patterns, managing cold starts, or optimizing serverless costs.

2 0

View

telum-ai/speck

epic-analyze

Load after epic-tech-spec.md and epic-breakdown.md exist — quality check for consistency and completeness before any story work begins. Catches spec drift and missing coverage between the tech spec and story breakdown. FIRST ACTION after loading: read template at .speck/templates/epic/epic-analys...

2 0

View