daily-briefing-builder
Generate a clean morning brief in Claude Code — pulls today's priorities, unposted content, and weather from your vault.
What this skill does
# Daily Briefing Builder
Generates a morning brief from your Obsidian vault. Reads today's action file, scans for unposted content, and fetches weather — all inside a Claude Code session.
No APIs. No paid services. No agent autonomy required. You run it, you get your brief.
---
## How to Use
Open Claude Code in your vault directory and say:
```
Run the Daily Briefing Builder skill.
```
Or with context upfront:
```
Run the Daily Briefing Builder skill. My vault is at /path/to/vault and my city is Ann+Arbor.
```
---
## Skill Instructions (for Claude Code)
When this skill is invoked, follow these phases exactly.
---
### PHASE 1: INTAKE
Check whether the user has provided:
- `vault_path` — absolute path to their Obsidian vault
- `city` — city name for weather (wttr.in format, spaces as `+`)
**If either is missing, ask before proceeding:**
```
To run your morning brief, I need two things:
1. Your vault path (e.g. /root/obsidian-vault)
2. Your city for weather (e.g. Ann+Arbor or London)
```
Do not proceed to PHASE 2 until both values are confirmed.
---
### PHASE 2: ANALYZE
Run these shell commands in sequence. Capture all output before formatting.
**Step 1 — Today's actions:**
```bash
TODAY=$(date +%Y-%m-%d)
VAULT="VAULT_PATH_HERE"
ACTIONS_FILE="$VAULT/bambf/tracking/daily-actions/${TODAY}.md"
if [ -f "$ACTIONS_FILE" ]; then
echo "FILE_FOUND"
awk '/## Today.s 3 Actions/{found=1; next} found && /^[0-9]/{print} found && /^##/{exit}' "$ACTIONS_FILE"
else
echo "FILE_MISSING:$ACTIONS_FILE"
fi
```
**Step 2 — Unposted content scan:**
```bash
VAULT="VAULT_PATH_HERE"
READY_DIR="$VAULT/content/ready-to-post"
if [ -d "$READY_DIR" ]; then
find "$READY_DIR" -name "*.md" -printf "%T@ %p\n" 2>/dev/null \
| sort -rn | awk '{print $2}' \
| while read f; do
if grep -q '\*\*Posted:\*\* ❌' "$f" 2>/dev/null; then
platform=$(echo "$f" | sed "s|.*/ready-to-post/||" | cut -d'/' -f1)
title=$(grep -m1 '^[^#\-\*>|` ]' "$f" 2>/dev/null | head -c 100)
rel="${f##$VAULT/}"
echo "ITEM|$platform|$rel|$title"
fi
done
else
echo "DIR_MISSING:$READY_DIR"
fi
```
**Step 3 — Weather:**
```bash
curl -s --max-time 5 "wttr.in/CITY_HERE?format=3" || echo "WEATHER_UNAVAILABLE"
```
---
### PHASE 3: OUTPUT
Format and print the brief to the terminal:
```
☀️ Morning Brief — [Weekday, Month Day]
TODAY'S 3 ACTIONS
[numbered actions, or fallback message if file missing]
READY TO POST ([shown] of [total])
[platform] [title] — [relative file path]
...and X more in the pipeline ← only if total > 5
WEATHER
[wttr.in output or fallback]
```
**Formatting rules:**
- Cap ready-to-post display at **5 items** (newest-modified first)
- If `content/ready-to-post/` doesn't exist: `No ready-to-post folder found`
- If no unposted files: `Content queue is empty`
- If actions file missing: `No actions file for today — create one at bambf/tracking/daily-actions/YYYY-MM-DD.md`
- If weather fails: `Weather unavailable (offline)` — do not abort the brief
---
### PHASE 4: SELF-CRITIQUE
Before delivering, run this internal check. Fix anything that fails — do not deliver until all 4 pass.
1. **Actions accuracy** — Was the actions file found? Did numbered items extract correctly? If the file exists but no items were found, note the potential heading mismatch.
2. **Content completeness** — Count the `ITEM|` lines in Step 2 output. Does the number shown in the brief match? Were any files skipped?
3. **Weather result** — Did curl return valid output? Is the fallback shown if it failed?
4. **Format cleanliness** — No raw bash output. No placeholder text. All three sections present.
---
## Example Output
```
☀️ Morning Brief — Friday, February 28
TODAY'S 3 ACTIONS
1. Finish Q1 content calendar
2. Send invoice to BAMBF client
3. Publish LinkedIn post on AI ops
READY TO POST (5 of 9)
[linkedin] Nobody talks about what happens when your AI system fails... — content/ready-to-post/linkedin/ai-ops-failure.md
[twitter] The overnight ops shift is real. We run Scribe at 2am... — content/ready-to-post/twitter/async-ops.md
[newsletter] AI marketing systems that actually work — content/ready-to-post/newsletter/systems-post.md
[linkedin] Three things I stopped doing after deploying agents — content/ready-to-post/linkedin/stopped-doing.md
[twitter] Founders who ignore async AI ops are about to find out why — content/ready-to-post/twitter/ignore-ops.md
...and 4 more in the pipeline
WEATHER
Ann Arbor: ☀️ +42°F
```
---
## Daily Actions File Format
Expected path: `<vault>/bambf/tracking/daily-actions/YYYY-MM-DD.md`
Expected structure:
```markdown
# Daily Actions — 2026-03-01
## Today's 3 Actions
1. First priority
2. Second priority
3. Third priority
```
If you use a different path or heading, tell Claude Code when invoking the skill.
---
## Requirements
- Claude Code with bash tool access
- Vault with `content/ready-to-post/` folder (files must contain `**Posted:** ❌` to register as unposted)
- `curl` installed (weather fails gracefully without it)
- Daily actions file optional — brief still runs without it
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.