Agent skill · Code Review & Quality

lit-pm

Use when coordinating comprehensive literature reviews requiring multi-stage pipeline (archival setup, scope refinement, parallel review discovery, outline synthesis, section writing, fact-checking, editorial polish). Orchestrates literature-researcher, lit-synthesizer, fact-checker, and editor skills with adaptive checkpoints based on complexity and stakes.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill lit-pm-dangeles-claude --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 26 KB
Bundled scripts: none
Path: skills/analysis/lit-pm-dangeles-claude/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

lit-pm is a Tier 1 orchestrator that coordinates a nine-stage literature review pipeline. It manages parallel review discovery, adaptive checkpoints, and handoffs between specialist skills to produce comprehensive, decision-useful literature reviews.

How it works

It acts as the coordinator, not a specialist. It performs session setup and state management (Stage 0), creates an outline structure, and runs quality gates to ensure outputs meet criteria. It delegates workload to:

  • literature-researcher (Stages 2, 3, 5: discovery and section writing)
  • lit-synthesizer (Stages 4, 7: introduction and synthesis)
  • fact-checker (Stages 6a, 6b: validation)
  • editor (Stage 8: polish) It uses a 9-stage pipeline, with parallel execution in Stage 2, and a sequence of handoffs and checkpoints. It includes a pre-flight validation to ensure required skills exist and defines a session-based workflow with archival guidelines, directory creation, and archival_context in handoffs. It enforces quality gates at each stage (e.g., Stage 6a blocking checks, Stage 6b non-blocking validation, Stage 6c adversarial review, Stage 7 synthesis checks) and manages a potential Devils-Advocate stage (Stage 6c and 7.5). The workflow includes a handoff protocol, session_dir creation, and archival-guidelines output. If a required specialist is unavailable, it aborts with an explicit error message.

When to use it

Use lit-pm for internal research synthesis, literature surveys, comprehensive reviews for grant proposals or scientific documents, cross-domain literature, or high-stakes deliverables requiring thoroughness and accuracy.

What it can touch

It dispatches tasks to these tools/skills via Task tool (for parallel and coordinated actions) and Skill tool (for loading domain knowledge if needed). It requires the following skills to exist: requirements-analyst, literature-researcher, lit-synthesizer, fact-checker, editor, devils-advocate.

Caveats

Pipeline duration is 4-24 hours. Requires all dependent skills to be present; missing skills abort with an explicit error: "ERROR: Required skill '{skill}' not found. lit-pm requires all dependencies. See references/stage-specifications.md for skill details." It delegates all specialist work to the appropriate tools and does not perform literature search, writing, verification, or editing itself. Archival handling defaults to a fallback if archival metadata is malformed or missing. Session directories are cleaned up only after successful completion; otherwise they are retained for debugging with a path logged to the user.

From the SKILL.md

# lit-pm: Literature Pipeline Manager ## Overview lit-pm is a Tier 1 orchestrator skill that coordinates a 9-stage literature review pipeline. It manages parallel review discovery, adaptive checkpoints, and handoffs between specialist skills to produce comprehensive, decision-useful literature reviews. ## Delegation Mandate You are an **orchestrator**. You coordinate specialists -- you do not perform specialist work yourself. You MUST delegate all specialist work using the appropriate tool (see Tool Selection below). This means you do not search for papers, do not read papers, do not write literature review prose, do not verify citations, and do not polish prose. Those are specialist tasks. You are NOT a literature researcher. You do not search for papers or read them. You are NOT a synthesizer. You do not write literature review prose. You are NOT a fact-checker. You do not verify citations or claims. You are NOT an editor. You do not polish prose or fix formatting. You ARE the coordinator who ensures all of the above happens through delegation. **Orchestrator-owned tasks** (you DO perform these yourself): - Session setup, directory creation, state file management (Stage 0) - Outl

What's inside
Steps it walks through
  1. Overview
  2. Delegation Mandate
  3. Tool Selection
  4. State Anchoring
  5. During Parallel Execution
  6. Three-Tier Architecture
  7. When to Use This Skill
  8. When NOT to Use This Skill
  9. Pre-Flight Validation
  10. The 9-Stage Pipeline
  11. Stage 0: Archival Guidelines Review
  12. Primary Source: .archive-metadata.yaml
  13. Fallback: CLAUDE.md (Deprecated)
  14. Output
Ships with 1 file
  • metadata.json
Commands it runs
Standard invocation
lit-pm "Comprehensive review of [topic] for [purpose]"
With explicit checkpoint control
lit-pm --review-outline "Survey of current approaches to [topic]"
lit-pm --full-auto "Quick survey of [topic]"
Resume interrupted workflow
lit-pm --resume workflow-id
More from claude-skill-registry
All skills →
About this skill
What does the lit-pm skill do?

Use when coordinating comprehensive literature reviews requiring multi-stage pipeline (archival setup, scope refinement, parallel review discovery, outline synthesis, section writing, fact-checking, editorial polish). Orchestrates literature-researcher, lit-synthesizer, fact-checker, and editor skills with adaptive checkpoints based on complexity and stakes.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill lit-pm-dangeles-claude --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going