docs
Look up documentation for any library, framework, or product concept.
Skill by drlove2002
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/drlove2002-docs
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, data
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/docs
What's inside
- Skill name
docs- Description
- Look up documentation for any library, framework, or product concept. Checks local docs first (Nextcord, Discord.py, Turso, Toasty, wwideas product docs), falls back to Context7 API, then browser. Use when the user asks about API syntax, configuration, version migration, setup, or "how do I" with a specific technology. Never rely on training data for API details.
- License
- MIT
- Instructions
- 67 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Docs Lookup priority: **local → Context7 → browser**. Check each tier before falling through. ## 0. Product / Domain Questions If the question is about the Worldwide product (how a feature works, what a system does, game mechanics, terminology), read from wwideas first: - `CONTEXT.md` — canonical domain language - `LIVE_FEATURES.md` — what's currently live - `issues/` — active plans and PRDs - `systems/existing/` — documented live mechanics **Read these before touching any implementation code.** If wwideas doesn't answer, fall through to the code itself. ## 1. Local Docs Check `~/Projects/worldwide/docs/index.json` for the package. Currently: | Package | Local path | Format | |---------|-----------|--------| | Nextcord | `~/Projects/worldwide/docs/nextcord/docs/` | `.rst` | | Discord.py | `~/Projects/worldwide/docs/discord.py/docs/` | `.rst` | | Turso | `~/Projects/worldwide/docs/turso/docs/` | `.md` | | Toasty | `~/Projects/worldwide/docs/toasty/docs/` | `.md` | If the package is in the index, read the local files: - Start from `index.md`, `index.rst`, `README.md`, or the package's documented entrypoint - Grep for the specific topic - Read the most relevant page fully — don't skim If the package is NOT in the index, skip to Context7. ## 2. Context7 (ctx7 CLI) For libraries not in the local index, or when local docs don't answer the question. **Step 1 — Resolve the library ID:** ```bash npx ctx7@latest library <name> "<query describing what you need>" ``` **Step 2 — Query with the resolved ID:** ```bash npx ctx7@latest docs <libraryId> "<specific question>" ``` Max 3 attempts. If all fail, tell the user why and fall through to browser. ### Retry with --research If the default `npx ctx7@latest docs` answer was shallow, re-run with `--research` for deeper analysis. ### Quota exhausted If Context7 hits a quota error, tell the user and fall through to browser. Never silently fall back to training data. ## 3. Browser If local docs + Context7 both fail, use the `browser` subagent to fetch docs from the official source. Prefer official documentation sites over forum posts or blogs. ## Rules - Never answer API questions from training data alone. Always check a tier. - One tier at a time. Don't jump to browser when local docs exist. - If local docs exist but don't answer, say "local docs don't cover this" before moving on. - For Rust stdlib and Python stdlib (not yet in local index), skip straight to Context7 or browser.
From drlove2002/ai-config, MIT.
More from drlove2002/ai-config
- 0.479score
web-test
drlove2002
Browser automation via agent-browser CLI for testing pages, debugging, performance audits, visual review, accessibility checks, and interaction testing.
SkillCFreshness: CClaude Code +9 - 0.479score
simplify-code
drlove2002
Review uncommitted changes, unpushed commits, or a provided git diff range with a reuse-first simplification lens.
SkillCFreshness: CClaude Code +9 - 0.474score
plan
drlove2002
Turn conversation context into a Product Requirements Document (PRD) and break it down into independently-grabbable tracking issues.
SkillCFreshness: CClaude Code +9 - 0.474score
readability
drlove2002
Examine and improve code holistically — structure, naming, readability, API design, performance, and file organization.
SkillCFreshness: CClaude Code +9 - 0.474score
add-model
drlove2002
Test availability, benchmark speed, and add a new model to any OpenAI-compatible provider in models.json.
SkillCFreshness: CClaude Code +9 - 0.474score
refactor
drlove2002
Improve existing code through inspection, simplification, and testing.
SkillCFreshness: CClaude Code +9 - 0.474score
recover
drlove2002
Surgical recovery from production regressions caused by agent-introduced bugs.
SkillCFreshness: CClaude Code +9 - 0.474score
design
drlove2002
Design interfaces and domain models.
SkillCFreshness: CClaude Code +9 - 0.474score
simplify-writing
drlove2002
Normalize written knowledge by eliminating redundancy, centralizing canonical descriptions, and surfacing contradictions.
SkillCFreshness: CClaude Code +9 - 0.474score
triage
drlove2002
Diagnose bugs, capture feature requests, and manage issues through a label-based workflow.
SkillCFreshness: CClaude Code +9 - 0.471score
commit
drlove2002
Automate the workflow of grouping unstaged changes or squashing unpushed commits into logical, high-quality conventional commits.
SkillCFreshness: CClaude Code +9 - 0.450score
skill
drlove2002
Create new agent skills with proper structure, progressive disclosure, and bundled resources.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 17, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/drlove2002/ai-config
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from drlove2002
- 0.479score
web-test
drlove2002
Browser automation via agent-browser CLI for testing pages, debugging, performance audits, visual review, accessibility checks, and interaction testing.
SkillCFreshness: CClaude Code +9 - 0.479score
simplify-code
drlove2002
Review uncommitted changes, unpushed commits, or a provided git diff range with a reuse-first simplification lens.
SkillCFreshness: CClaude Code +9 - 0.474score
design
drlove2002
Design interfaces and domain models.
SkillCFreshness: CClaude Code +9 - 0.474score
plan
drlove2002
Turn conversation context into a Product Requirements Document (PRD) and break it down into independently-grabbable tracking issues.
SkillCFreshness: CClaude Code +9 - 0.474score
readability
drlove2002
Examine and improve code holistically — structure, naming, readability, API design, performance, and file organization.
SkillCFreshness: CClaude Code +9 - 0.474score
add-model
drlove2002
Test availability, benchmark speed, and add a new model to any OpenAI-compatible provider in models.json.
SkillCFreshness: CClaude Code +9
Cite this page
docs skill. Agent Mart. https://agentmart.dev/skills/drlove2002-docs (last updated 2026-10-24)