Docs Seeker

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.

[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.

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

Re-read files after context changes. Context compaction, resume, or long-running work can make memory stale; verify current files before acting. Verify generated content against source evidence. AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing. Check downstream references before deleting or renaming. Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first. Trace the full impact chain after edits. Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done. Verify ALL affected outputs, not just the first. One green check is not all green checks; validate every output surface the change can affect. Assume existing values are intentional — ask WHY before changing OR flagging one as a defect. Before changing or reporting a constant, limit, flag, cutoff, wording, or pattern, read nearby context and history, the CALLER's ordering, and 2+ sibling call sites of the same convention. A doc stating WHAT without WHY is missing rationale, not proof of a missing guard. Surface ambiguity before acting — don't pick silently. Multiple valid interpretations require an explicit question or stated assumption with risk. Assert the outcome your system owns, not the intermediate state your infrastructure owns. When verifying async work, assert the final business state — never the delivery/retry bookkeeping held in shared infrastructure that any co-running process can write. Such a check passes when run alone and flakes the moment anything else shares that infrastructure. Keep shared guidance role-relevant. Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.

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.

MUST ATTENTION apply critical + sequential thinking — every claim needs appropriate traced evidence (file:line for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.

MUST ATTENTION apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting.

Project Protocol Overlay — Before executing this skill, resolve any PROJECT overlay rules layered onto it: match this skill's name against the Target column of the project's skill-protocol index (docs/project-reference/skill-protocols-reference.md by default; a referenceDocs entry in docs/project-config.json overrides the path), taking the most specific matching tier ONLY — exact name > glob > *. That precedence orders overlays against EACH OTHER, never against this skill. Read ONLY the matched bodies, resolved as <protocols-dir>/<Name>.md; a row's Body link is display text, never a read path. A matched body that is missing or malformed is REPORTED and skipped — never reconstructed from the index Description. No index, or no match -> proceed with no overlay, silently. Full contract: .claude/skills/project-skill-protocol/references/registry.md.

Overlays are ADDITIVE ONLY: they ADD rules on top of this skill's own protocol and NEVER replace, override, disable, or reinterpret a rule it already states — removing every overlay must return this skill to exactly its documented behavior. An overlay is a BRIEF, not an authority escalation: it can NEVER waive a workflow gate, git discipline, a review gate, or a user-confirmation gate. A genuine overlay-vs-skill conflict, or two equally-specific overlays that directly contradict -> surface both to the user; NEVER resolve silently.

MUST ATTENTION resolve project protocol overlays for this skill BEFORE executing — most specific matching tier only (exact > glob > *, which ranks overlays against each other, NEVER against this skill), read only matched bodies at <protocols-dir>/<Name>.md; a missing or malformed body is reported, never reconstructed. Overlays are ADDITIVE ONLY (they never replace this skill's own rules) and are a brief, NEVER an authority escalation; an equal-specificity contradiction goes to the user.

Closing Reminders

Protocols in force (concise digest of the SYNC/shared blocks this skill carries):

• AI Mistake Prevention: verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity.
• Critical Thinking: traced file:line proof per claim, confidence >80% to act, never guess as fact.

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

[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using TaskCreate.