[IMPORTANT] Use

TaskCreate

to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.

<!-- SYNC:critical-thinking-mindset -->

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

<!-- /SYNC:critical-thinking-mindset --> <!-- SYNC:ai-mistake-prevention -->

AI Mistake Prevention — Failure modes to avoid on every task:

• Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal.
• Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing.
• Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain.
• Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path.
• When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site.
• Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code.
• Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks.
• Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis.
• Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly.
• Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.

<!-- /SYNC:ai-mistake-prevention -->

Quick Summary

Goal: Search and fetch technical documentation using executable scripts with llms.txt standard (context7.com).

Workflow:

1. Detect — Run

   scripts/detect-topic.js

   to classify query type (topic-specific vs general)
2. Fetch — Run

   scripts/fetch-docs.js

   to retrieve documentation with automatic fallback
3. Analyze — Run

   scripts/analyze-llms-txt.js

   to categorize URLs and recommend agent distribution

Key Rules:

• Always execute scripts in order: detect -> fetch -> analyze
• Scripts handle URL construction and fallback chains automatically; no manual URL building
• Zero-token overhead: scripts run without context loading

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

Documentation Discovery via Scripts

Overview

Script-first documentation discovery using llms.txt standard.

Execute scripts to handle entire workflow - no manual URL construction needed.

Primary Workflow

ALWAYS execute scripts in this order:

# 1. DETECT query type (topic-specific vs general)
node scripts/detect-topic.js "<user query>"

# 2. FETCH documentation using script output
node scripts/fetch-docs.js "<user query>"

# 3. ANALYZE results (if multiple URLs returned)
cat llms.txt | node scripts/analyze-llms-txt.js -

Scripts handle URL construction, fallback chains, and error handling automatically.

Scripts

detect-topic.js

- Classify query type

• Identifies topic-specific vs general queries
• Extracts library name + topic keyword
• Returns JSON:

  {topic, library, isTopicSpecific}

• Zero-token execution

fetch-docs.js

- Retrieve documentation

• Constructs context7.com URLs automatically
• Handles fallback: topic → general → error
• Outputs llms.txt content or error message
• Zero-token execution

analyze-llms-txt.js

- Process llms.txt

• Categorizes URLs (critical/important/supplementary)
• Recommends agent distribution (1 agent, 3 agents, 7 agents, phased)
• Returns JSON with strategy
• Zero-token execution

Workflow References

Topic-Specific Search - Fastest path (10-15s)

General Library Search - Comprehensive coverage (30-60s)

Repository Analysis - Fallback strategy

References

context7-patterns.md - URL patterns, known repositories

errors.md - Error handling, fallback strategies

advanced.md - Edge cases, versioning, multi-language

Execution Principles

1. Scripts first - Execute scripts instead of manual URL construction
2. Zero-token overhead - Scripts run without context loading
3. Automatic fallback - Scripts handle topic → general → error chains
4. Progressive disclosure - Load workflows/references only when needed
5. Agent distribution - Scripts recommend parallel agent strategy

Quick Start

Topic query: "How do I use date picker in shadcn?"

node scripts/detect-topic.js "<query>"  # → {topic, library, isTopicSpecific}
node scripts/fetch-docs.js "<query>"    # → 2-3 URLs
# Read URLs with WebFetch

General query: "Documentation for Next.js"

node scripts/detect-topic.js "<query>"         # → {isTopicSpecific: false}
node scripts/fetch-docs.js "<query>"           # → 8+ URLs
cat llms.txt | node scripts/analyze-llms-txt.js -  # → {totalUrls, distribution}
# Deploy agents per recommendation

Environment

Scripts load

.env

:

process.env

>

.claude/skills/docs-seeker/.env

>

.claude/skills/.env

>

.claude/.env

See

.env.example

for configuration options.

---

Closing Reminders

• IMPORTANT MUST ATTENTION break work into small todo tasks using

  TaskCreate

  BEFORE starting
• IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code
• IMPORTANT MUST ATTENTION cite

  file:line

  evidence for every claim (confidence >80% to act)
• IMPORTANT MUST ATTENTION add a final review todo task to verify work quality <!-- SYNC:critical-thinking-mindset:reminder -->
• MUST ATTENTION apply critical thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact. <!-- /SYNC:critical-thinking-mindset:reminder --> <!-- SYNC:ai-mistake-prevention:reminder -->
• MUST ATTENTION apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction. <!-- /SYNC:ai-mistake-prevention:reminder -->