nota-america/forgecat-agent-profiles / profiles/addyosmani/agent-skills/for-claude/.claude/skills/source-driven-development
source-driven-development
VerifiedGrounds every implementation decision in official documentation. Use when you want to verify an approach against the official docs before implementing it, or when you want authoritative, source-cited code free from outdated patterns. Use when building with any framework or library where correctness matters.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.8 KB |
| scripts/sdd-cache-post.shexecutable | script | 4.5 KB |
| scripts/sdd-cache-pre.shexecutable | script | 4.2 KB |
scripts/sdd-cache-pre.sh
View on GitHub#!/bin/bash
# sdd-cache-pre.sh — PreToolUse hook for WebFetch.
#
# HTTP resource cache keyed by URL. Freshness is delegated to the origin via
# HTTP validators; 304 Not Modified is the only signal to serve from cache.
# On hit, exits 2 and writes the cached body to stderr so Claude Code can
# deliver it to the agent in place of the WebFetch result. Otherwise exits 0.
#
# No TTL: if validators don't catch a change, nothing will. Entries without
# ETag or Last-Modified are never cached (can't revalidate).
#
# Cached bodies are prompt-shaped (WebFetch post-processes through a model),
# so the key is URL-only and the original prompt is surfaced in the hit
# message so the next agent can tell if the earlier reading still applies.
#
# Dependencies: jq, curl, shasum (or sha256sum).
set -euo pipefail
# Graceful degradation: if any dependency is missing, let the fetch through.
command -v jq >/dev/null 2>&1 || exit 0
command -v curl >/dev/null 2>&1 || exit 0
command -v shasum >/dev/null 2>&1 || command -v sha256sum >/dev/null 2>&1 || exit 0
if [ -t 0 ]; then INPUT="{}"; else INPUT=$(cat); fi
# Debug logging: active when SDD_CACHE_DEBUG=1 is set, or when a sentinel
# file exists at .claude/sdd-cache/.debug. Toggle with `touch` / `rm`.
dbg() {
local dir="${CLAUDE_PROJECT_DIR:-$PWD}/.claude/sdd-cache"
[ "${SDD_CACHE_DEBUG:-0}" = "1" ] || [ -f "$dir/.debug" ] || return 0
mkdir -p "$dir"
printf '%s [pre] %s\n' "$(date -u +%FT%TZ)" "$*" >> "$dir/.debug.log"
}
dbg "fired"
URL=$(printf '%s' "$INPUT" | jq -r '.tool_input.url // empty' 2>/dev/null || true)
if [ -z "$URL" ]; then dbg "no url in tool_input, exit"; exit 0; fi
dbg "url=$URL"
# Cache key is sha256(URL), truncated to 128 bits.
hash_key() {
if command -v shasum >/dev/null 2>&1; then
printf '%s' "$1" | shasum -a 256 | cut -c1-32
else
printf '%s' "$1" | sha256sum | cut -c1-32
fi
}
CACHE_DIR="${CLAUDE_PROJECT_DIR:-$PWD}/.claude/sdd-cache"
CACHE_FILE="$CACHE_DIR/$(hash_key "$URL").json"
if [ ! -f "$CACHE_FILE" ]; then dbg "no cache file at $CACHE_FILE, exit"; exit 0; fi
dbg "cache file exists: $CACHE_FILE"
FETCHED_AT=$(jq -r '.fetched_at // 0' "$CACHE_FILE" 2>/dev/null || echo 0)
ORIGINAL_PROMPT=$(jq -r '.prompt // empty' "$CACHE_FILE" 2>/dev/null || true)
ETAG=$(jq -r '.etag // empty' "$CACHE_FILE" 2>/dev/null || true)
LAST_MOD=$(jq -r '.last_modified // empty' "$CACHE_FILE" 2>/dev/null || true)
# No validator means we cannot verify freshness — never serve from cache.
if [ -z "$ETAG" ] && [ -z "$LAST_MOD" ]; then
dbg "cached entry has no etag/last-modified, cannot revalidate, bypass"
exit 0
fi
HEADERS=()
[ -n "$ETAG" ] && HEADERS+=(-H "If-None-Match: $ETAG")
[ -n "$LAST_MOD" ] && HEADERS+=(-H "If-Modified-Since: $LAST_MOD")
STATUS=$(curl -sI -o /dev/null -w "%{http_code}" \
--max-time 5 -L \
"${HEADERS[@]}" \
"$URL" 2>/dev/null || echo "000")
dbg "revalidation HEAD status=$STATUS"
if [ "$STATUS" != "304" ]; then
dbg "not 304, letting WebFetch proceed"
exit 0
fi
# Server confirmed content unchanged. Serve cached copy to the agent.
CONTENT=$(jq -r '.content // empty' "$CACHE_FILE" 2>/dev/null || true)
if [ -z "$CONTENT" ]; then dbg "cache file has empty content field, bypass"; exit 0; fi
dbg "cache HIT, blocking WebFetch with ${#CONTENT} bytes of cached content"
VERIFIED_AT_ISO=$(date -u -r "$FETCHED_AT" +"%Y-%m-%dT%H:%M:%SZ" 2>/dev/null \
|| date -u -d "@$FETCHED_AT" +"%Y-%m-%dT%H:%M:%SZ" 2>/dev/null \
|| echo "unknown")
# Emit the payload with printf so $CONTENT is never interpreted by the shell
# (docs contain backticks, $vars, and backslashes in code examples; an
# unquoted heredoc would treat them as command substitution).
{
printf '[sdd-cache] Cache hit for %s\n\n' "$URL"
printf 'Revalidated via HTTP 304; unchanged since %s. Use the cached\n' "$VERIFIED_AT_ISO"
printf 'content below as if WebFetch had just returned it.\n\n'
if [ -n "$ORIGINAL_PROMPT" ]; then
printf 'Original WebFetch prompt: "%s". If your angle differs, judge\n' "$ORIGINAL_PROMPT"
printf 'whether this reading still covers it.\n\n'
fi
printf -- '----- BEGIN CACHED CONTENT -----\n'
printf '%s\n' "$CONTENT"
printf -- '----- END CACHED CONTENT -----\n'
} >&2
exit 2
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 197k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |