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/lythos-labs-lythoskill-project-onboarding
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
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 and code. Checked Oct 26, 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/lythoskill-project-onboarding
What's inside
- Skill name
lythoskill-project-onboarding- Description
- Session context loader. Reads the latest daily handoff to restore project context without redundant file exploration. Three-layer loading: CLAUDE.md (stable) → daily handoff (session state) → git verification (ground truth). Degrades to file exploration when no handoff exists. Read-side pair with project-scribe (scribe writes the daily, onboarding reads it).
- License
- MIT
- Instructions
- 121 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: "lythoskill-project-onboarding" does not match folder "skill"
Files (6)
- SKILL.md
- autonomy-decision-quadrant.md · references/
- autonomy-quadrant-case-studies.md · references/
- cqrs-architecture.md · references/
- latest-daily-query.md · references/
- output-formats.md · references/
SKILL.md (first lines)
# Project Onboarding
> Read the handoff. Don't re-explore what's already written down.
## Three-Layer Loading
Loading order optimized for KV cache (stable content first, volatile last):
### Layer 1: Meta-skill (rarely changes)
```bash
cat CLAUDE.md
```
Provides: how to work in this project, architecture, conventions.
### Layer 2: Session State (from latest daily file)
```bash
# Find the most recent daily file.
# Filter to dated filenames BEFORE sorting — never `ls daily/*.md | sort | tail -1`.
# That form answers a date question with lexicographic position and has returned
# README.md / _README.md twice (locale-dependent). See references/latest-daily-query.md.
ls daily/ 2>/dev/null | grep -E '^[0-9]{4}-[0-9]{2}-[0-9]{2}\.md$' | sort | tail -1
# Read first section (## Session Handoff)
```
**Handoff is fresh if**: `git_commit` in handoff matches current HEAD and
date is recent (within 3 days).
**If fresh**: use handoff directly. Skip cortex/skills exploration.
**If stale or missing**: degrade to file exploration (see below).
**If stale + gap >7 days**: `git log --since="7 days ago" --oneline` to reconstruct activity, then `cortex probe` to check current state. Don't rely on stale Next Steps.
### Layer 3: Ground Truth Verification (always required)
```bash
git status
git log --oneline -5
```
Compare against handoff's **0. Verify Current State** section. If they diverge,
handoff is stale — flag it and rely on real-time git output.
### Layer 3b: Project shape survey → initialize the PROJECT's own conventions
The generic skill does not require CI tail-checks — that was one project's
rule, and a project's rules belong in the project's own agent-facing docs
(AGENTS.md / CLAUDE.md), not in a universal onboarding gate. What this layer
MUST do is survey the shape and hand the finding back:
| Project shape | What this layer does |
|---------------|----------------------|
| Not a git repo, or no remote | Note "no VCS remote" in the summary. Nothing to tail. |
| Remote host is not GitHub | Note the host. `gh` cannot help there — the project's own docs would name the right CLI. |
| GitHub repo with Actions | Note the workflows found (`gh run list --limit 5`). **Suggest initializing the project's AGENTS.md with a CI-tail-check line** if the project wants that discipline — the lythoskill repo's own AGENTS.md is one example of such a project-level rule. |
| GitHub repo without Actions | Note "no CI". Offer the same AGENTS.md suggestion for whatever check the project does have (or none). |
Tailing CI only happens when the PROJECT's own conventions declare it — read
the project's AGENTS.md/CLAUDE.md for that; if declared, use ambient `gh`
auth (never export a project-specific token here; this skill runs in projects
it cannot know). Failure semantics when you do tail: not logged in →
`gh auth login`; 401 = token expired; 404 = the logged-in account's token has
no grant for this repo — check `gh auth status` or the project's own auth doc.
## Degraded Exploration (no usable handoff)
Only when Layer 2 fails. Read in this order:
```bash
cat skill-deck.toml # What skills are active
cat cortex/INDEX.md # Project governance state
git log --oneline -10 # Recent changes
ls -lt cortex/adr/02-accepted/ | head -10 # Recent decisions
ls -lt cortex/wiki/02-research/ | head -10 # Recent research
ls cortex/epics/01-active/ # Active epics
ls cortex/tasks/01-backlog/ # Pending work
ls cortex/tasks/02-in-progress/ # Active work
```
**If the project has cortex**, the `ls -lt` on adr/, wiki/, epics/, tasks/ directories
tells you what happened recently without reading every file — timestamps reveal
the most recent decisions, research, and active work at a glance.
**Cortex ID = timestamp**: ADR-/TASK-/EPIC- prefixes use `yyyyMMddHHmmssSSS`.
This enables date-range grep reconstruction (e.g., `ls cortex/adr/02-accepted/ |
grep '^ADR-2026051'` finds all May 2026 decisions). Use this when a weekly is
missing or when verifying claims across a date range.
## Freshness Decision Table
| Condition | Verdict | Action |
|-----------|---------|--------|
| Daily exists, git_commit matches HEAD, date ≤3 days | ✅ Fresh | Use handoff directly |
| Daily exists, git_commit ≠ HEAD | ⚠️ Stale | Read handoff for context, but verify everything |
| Daily exists, date >3 days old | ⚠️ Probably stale | Same as above |
| No daily file found | ❌ Missing | Full degraded exploration |
## Batch Index scan (read side of the write-side contract)
A handoff whose git state matches HEAD is trustworthy for state — but before
concluding "no prior art" on a live problem, scan the handoff's
`### Batch Index` `read when` triggers. A matched trigger means the work
already exists: follow its refs, don't re-derive. Weight **experiment and
research/wiki entries highest** (paths are project conventions — this
repo's instances: `playground/`, `runs/`, `cortex/wiki/`) — their carriers
are quiet and surface no other way; a code batch leaves trails, an
experiment or wiki batch leaves only this line.
If the first handoff's index doesn't match your problem, scan the next
handoff section below — prepend days accumulate one index per session, and
every one of them is live until its commits are verified. Stale handoffs:
scan too, but treat matched refs as leads to verify against current state,
not settled prior art.
## Output Format
After loading, summarize to user:
```
📋 Project: <name> (<tech stack>)
📌 Version: <tag> (git: <hash>)
📄 Source: daily/<date>.md | degraded exploration
⚠️ Pitfalls: <top 1-2 from handoff>
🎯 Current: <active task>
💡 Next: <prioritized next step>
✅ Verification: git state matches handoff | ⚠️ diverged
```
## Checklist
- [ ] Layer 1: Read CLAUDE.md
- [ ] Layer 2: Find latest daily/, read handoff section
- [ ] Assess freshness (git_commit match, date recency)
- [ ] Layer 3: Verify with `git status` + `git log`
- [ ] Layer 3b: Project shape survey — repo? remote? host? Actions? Record findings in the summary; if CI exists, SUGGEST writing a tail-check into the project's own AGENTS.md (project-level rule, not a universal gate). Only actually tail CI when the project's own docs declare it.
- [ ] If handoff fresh → use directly
- [ ] Batch Index: scanned `read when` triggers for prior art matching your live problem (experiment/research/wiki entries especially) before concluding "no prior art"
- [ ] If handoff stale/missing → degraded exploration
- [ ] Output summary to userFrom lythos-labs/lythoskill, MIT.
More from lythos-labs/lythoskill
- 0.605score
lythoskill-project-scribe
lythos-labs
Session context dump.
SkillAFreshness: A★ 3Claude Code +9 - 0.605score
lythoskill-reminders
lythos-labs
Reconciles a declarative session-reminder registry (cortex/REMINDERS.toml) against the host's session-scoped cron tools.
SkillAFreshness: A★ 3Claude Code +9 - 0.605score
lythoskill-dreaming
lythos-labs
Project memory consolidation — 夜有所梦 ("night dreams": the day's scattered notes get consolidated into long-term memory while "sleeping").
SkillAFreshness: A★ 3Claude Code +9 - 0.602score
lythoskill-red-green-release
lythos-labs
User-acceptance-driven release workflow using heredoc patch files.
SkillAFreshness: A★ 3Claude Code +9 - 0.602score
lythoskill-project-scribe-weekly
lythos-labs
Weekly synthesis writer.
SkillAFreshness: A★ 3Claude Code +9 - 0.602score
lythoskill-coach
lythos-labs
Analyzes SKILL.md files against Agent Skills best practices.
SkillAFreshness: A★ 3Claude Code +9 - 0.602score
lythoskill-writer
lythos-labs
Human-first documentation writer and reviewer.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
lythoskill-arena
lythos-labs
Test play for skills and deck configurations.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
lythoskill-sober
lythos-labs
Stay clear-headed.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
lythoskill-project-cortex
lythos-labs
Register tasks BEFORE fixing bugs.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
lythoskill-curator
lythos-labs
Skill curator (买家秀 — "buyer show": hands-on QA notes, as opposed to the author's own 卖家秀 "seller show" claims).
SkillAFreshness: A★ 3Claude Code +9 - 0.598score
lythoskill-creator
lythos-labs
Scaffold and build projects for the lythoskill ecosystem only.
SkillAFreshness: A★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 23, 2026 (7 days ago)
- Last release
- Oct 14, 2026 (16 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/lythos-labs/lythoskill
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from lythos-labs
- 0.605score
lythoskill-dreaming
lythos-labs
Project memory consolidation — 夜有所梦 ("night dreams": the day's scattered notes get consolidated into long-term memory while "sleeping").
SkillAFreshness: A★ 3Claude Code +9 - 0.605score
lythoskill-reminders
lythos-labs
Reconciles a declarative session-reminder registry (cortex/REMINDERS.toml) against the host's session-scoped cron tools.
SkillAFreshness: A★ 3Claude Code +9 - 0.605score
lythoskill-project-scribe
lythos-labs
Session context dump.
SkillAFreshness: A★ 3Claude Code +9 - 0.602score
lythoskill-coach
lythos-labs
Analyzes SKILL.md files against Agent Skills best practices.
SkillAFreshness: A★ 3Claude Code +9 - 0.602score
lythoskill-project-scribe-weekly
lythos-labs
Weekly synthesis writer.
SkillAFreshness: A★ 3Claude Code +9 - 0.602score
lythoskill-writer
lythos-labs
Human-first documentation writer and reviewer.
SkillAFreshness: A★ 3Claude Code +9
Cite this page
lythoskill-project-onboarding. Agent Mart. https://agentmart.dev/skills/lythos-labs-lythoskill-project-onboarding (last updated 2026-10-24)