session-start-status
Produce a 5-bullet session-start orientation summary by reading tasks.md, recent git log, and the latest specstory tail. Run at the start of any session that resumes work on an active project. Don't use when starting a brand-new project from scratch (use /playbook:foundations or /playbook:tech-plan instead) or when a fresh checkpoint already exists (read docs/checkpoints/latest.md instead — that's higher signal).
What this skill does
# Session Start Status
## Problem
Every session starts cold. Without an orientation pass, agents re-discover the same context every time: which tasks are open, what shipped recently, what the user was last working on, what's blocked. Deep analysis of multi-week projects (Memory & Personalization Phase 1) shows agents burning **10–30K tokens per session** on re-orientation reads — and still missing context that lived in untracked files or recent specstory transcripts.
This skill collapses that work into a single fixed pass that costs predictable tokens and produces a fixed-shape summary.
## When to Use
- **Resuming work on an active project** — branch already exists, tasks.md exists, recent commits exist
- **After context compaction mid-session** — re-orient without re-reading everything
- **When the user asks "what's the status of X?" / "where were we?"** — but a `latest.md` checkpoint does NOT exist (if it does, prefer `session-checkpoint` skill)
## When NOT to Use
- Brand-new project with no tasks.md yet (use `/playbook:foundations` or `/playbook:tech-plan`)
- Session-checkpoint skill already wrote `docs/checkpoints/latest.md` — that file is higher signal
- One-shot question that doesn't depend on project state ("what's the syntax for X?")
## Process
### Inputs to Read (in order, in parallel where possible)
1. **`projects/in-progress/*/tasks.md`** (or `projects/[active-project]/tasks.md` if known) — read just the summary table and "Current Focus" section, NOT the full task details. Goal: identify in-flight task and the immediate next task.
2. **`git log --oneline -10`** on the current branch — what shipped in the last 10 commits.
3. **`git status -sb`** — uncommitted changes, branch state vs. upstream.
4. **Most recent SpecStory transcript** if any: `ls -t .specstory/history/*.md 2>/dev/null | head -1` then read the **last ~80 lines only**. Goal: capture the last user/agent exchange to anchor session continuity.
5. **CLAUDE.md "Quick Reference" section** if present — confirms test/dev/build commands haven't changed.
### Output Shape (Fixed 5 Bullets)
Emit exactly five bullets. No preamble, no closing summary, no extra prose.
```
**Session start orientation**
- **Branch & state**: [branch name] — [N commits ahead/behind] — [N uncommitted files]
- **Active task**: [Task ID + name] — [status from tasks.md] — [one-line next action]
- **Last shipped**: [most recent commit subject + date] — [what user was last asking about, from specstory tail]
- **Blockers / open questions**: [from specstory tail or "none surfaced"]
- **Suggested next step**: [single, specific action — not a menu]
```
### Discipline
- **Hard cap on input reads**: tasks.md summary table + commit log + git status + last 80 lines of one specstory file. Total budget < 3K tokens. If you find yourself wanting to read more, stop — that's the user's job to ask for.
- **Do NOT read the full tasks.md** — only the summary table at the top and the "Current Focus" section. Detail sections waste budget at orientation time.
- **Do NOT read multiple specstory files** — one is enough to anchor continuity. If the latest specstory is from days ago, say so in "Last shipped" and stop.
- **Do NOT enumerate every open task** — only the in-flight one and the suggested next.
- **Output the 5 bullets and stop.** Do not propose a plan, do not start work, do not ask for permission to start. Wait for the user.
## Why This Skill Exists
Memory & Personalization Phase 1 retrospective (2026-04-26) measured that session-start re-orientation consumed 10-30K tokens per session, every session, across a 4-week project. The 23KB initial briefing existed but was rarely re-read. Agents asked "how do I see what's been extracted?" across 3+ separate sessions because no orientation pass surfaced the answer. This skill makes the orientation cost fixed, predictable, and low.
Related in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".