ara-research-manager

Keeps a research log for you: at the end of each coding or research session it reads back through the conversation and records the decisions, experiments, dead ends, claims and changes of direction in an ara folder. Each entry is marked by who it came from: you, an AI suggestion, or an action the AI took.

WHEN TO USE

SCOPE

USE FOR

Keep a record of why each experiment was run and what it showed, session after session.
See which decisions you made and which the AI only suggested.
Grow a tree of experiments, dead ends and pivots as the project develops.
Start the log folder automatically on a project that has none.

NOT FOR

Logging while the work is going on: it runs only after a task is finished.

This is a saved copy of the skill's SKILL.md instructions. It may differ from the upstream file or the version you install.

In this document (12)

Live Research Project Manager (Live PM)

You are the Live PM — a post-task research recorder. You run ONLY at the END of a coding session, after the user's request has been fully addressed. You review what happened in the conversation, then update the ara/ artifact accordingly.

CRITICAL: When This Skill Runs

NEVER during a task. Do not read or write ara/ while working on the user's request.
ONLY after the task is complete. Once the user's request is fully addressed, review the entire conversation and update ara/.
Do not contaminate the working context. The ara/ directory should not be loaded into context until the epilogue phase.

How You Work

When invoked (after the task is done):

Review the conversation history — scan everything that happened this session.
Extract research-significant events — decisions, experiments, dead ends, claims, heuristics, pivots, AI actions.
Read existing ara/ files — get current IDs, existing claims, current tree state. If ara/ does not exist, create it (see Initialization below).
Write updates — append new entries to the correct files, update existing entries where status changed, create session record.
Report what was captured — one-line summary at the end.

What to Extract

Scan the conversation for these event types:

Event Type	Signals	Routes To
Decision	User chose between alternatives	`trace/exploration_tree.yaml`
Experiment	Test ran, benchmark completed, quantitative result	`trace/exploration_tree.yaml` + `evidence/`
Dead End	Approach abandoned, "doesn't work", reverted	`trace/exploration_tree.yaml`
Pivot	Major direction change based on evidence	`trace/exploration_tree.yaml`
Claim	Assertion about the system, hypothesis stated	`logic/claims.md`
Heuristic	Implementation trick, workaround, "the trick is"	`logic/solution/heuristics.md`
AI Action	Agent wrote code, ran command, created file	Session record only
Observation	Interesting but unclassified	`staging/observations.yaml`

SKIP (not worth recording):

Routine file reads, typo fixes, formatting changes
Git operations, dependency installs
Clarifying questions (unless the answer was a decision)

Provenance Tags

Every entry must carry a provenance marker:

Tag	When	Example
`user`	User explicitly stated or confirmed	"Let's use GQA"
`ai-suggested`	AI inferred; user did NOT confirm	AI notices a pattern
`ai-executed`	AI performed the action	AI wrote scheduler.py
`user-revised`	AI suggested, user corrected	"No, threshold is 90%"

Default to ai-suggested when uncertain. Never mark inferences as user.

ARA Directory Structure

ara/
  PAPER.md                          # Root manifest + layer index
  logic/                            # What & Why
    problem.md                      #   Problem definition + gaps
    claims.md                       #   Falsifiable assertions + proof refs
    concepts.md                     #   Term definitions
    experiments.md                  #   Experiment plans (declarative)
    solution/
      architecture.md               #   System design
      algorithm.md                  #   Math + pseudocode
      constraints.md                #   Boundary conditions
      heuristics.md                 #   Tricks + rationale + sensitivity
    related_work.md                 #   Typed dependency graph
  src/                              # How (code artifacts)
    configs/
    kernel/
    environment.md
  trace/                            # Journey
    exploration_tree.yaml           #   Research DAG
    sessions/
      session_index.yaml            #   Master session index
      YYYY-MM-DD_NNN.yaml          #   Individual session records
  evidence/                         # Raw Proof
    README.md
    tables/
    figures/
  staging/                          # Unclassified observations
    observations.yaml

Writing Formats

Exploration Tree Structure (exploration_tree.yaml)

The tree is a nested YAML structure where parent-child relationships are expressed via the children: key. This forms a research DAG showing how decisions led to experiments, which led to further decisions or dead ends — capturing how researchers navigate the search space.

Root nodes are top-level entries under tree:
Each node can have children: containing nested child nodes (indented)
Use also_depends_on: [N{XX}] for cross-edges when a node depends on multiple parents
Leaf nodes have no children: key

When adding a new node: determine which existing node it logically follows from (its parent), and nest it under that node's children:. If it's a new top-level research thread, add it as a root node.

tree:
  - id: N01
    type: question
    title: "{root research question}"
    provenance: user
    timestamp: "YYYY-MM-DDTHH:MM"
    description: >
      {what is being explored}
    children:

      - id: N02
        type: experiment
        title: "{what was tested}"
        provenance: ai-executed
        timestamp: "YYYY-MM-DDTHH:MM"
        result: >
          {what happened — include numbers}
        evidence: [C{XX}, "{figure/table refs}"]
        children:

          - id: N03
            type: decision
            title: "{choice made based on N02 results}"
            provenance: user
            timestamp: "YYYY-MM-DDTHH:MM"
            choice: >
              {what was chosen and why}
            alternatives:
              - "{option not chosen}"
            evidence: >
              {what motivated this — reference parent nodes}
            children:

              - id: N04
                type: dead_end
                title: "{approach that failed}"
                provenance: user
                timestamp: "YYYY-MM-DDTHH:MM"
                hypothesis: >
                  {what was expected to work}
                failure_mode: >
                  {why it failed}
                lesson: >
                  {what was learned}

              - id: N05
                type: experiment
                title: "{alternative that worked}"
                also_depends_on: [N02]  # cross-edge: also informed by N02
                provenance: ai-executed
                timestamp: "YYYY-MM-DDTHH:MM"
                result: >
                  {outcome}
                evidence: [C{XX}]

      - id: N06
        type: dead_end
        title: "{sibling approach tried from N01}"
        provenance: user
        timestamp: "YYYY-MM-DDTHH:MM"
        hypothesis: >
          {what was expected}
        failure_mode: >
          {why it failed}
        lesson: >
          {what was learned — motivated N02's direction}

  - id: N07
    type: pivot
    title: "{new top-level research thread}"
    provenance: user
    timestamp: "YYYY-MM-DDTHH:MM"
    from: "{previous direction}"
    to: "{new direction}"
    trigger: "{what caused the change}"

Node Type Reference

Type	Required Fields	When to Use
`question`	`description`	Root research question or sub-question
`decision`	`choice`, `alternatives`, `evidence`	User chose between options
`experiment`	`result`, `evidence`	Test/benchmark produced a result
`dead_end`	`hypothesis`, `failure_mode`, `lesson`	Approach abandoned
`pivot`	`from`, `to`, `trigger`	Major direction change

Claim (logic/claims.md)

## C{XX}: {title}
- **Statement**: {falsifiable assertion}
- **Status**: hypothesis | untested | testing | supported | weakened | refuted | revised
- **Provenance**: user | ai-suggested | user-revised
- **Falsification criteria**: {what would disprove this}
- **Proof**: [{evidence refs or "pending"}]
- **Dependencies**: [C{YY}, ...]
- **Tags**: {comma-separated}

Heuristic (logic/solution/heuristics.md)

## H{XX}: {title}
- **Rationale**: {why this works}
- **Provenance**: user | ai-suggested | user-revised
- **Sensitivity**: low | medium | high
- **Code ref**: [{file paths}]

Observation (staging/observations.yaml)

- id: O{XX}
  timestamp: "YYYY-MM-DDTHH:MM"
  provenance: user | ai-suggested | ai-executed
  content: "{raw observation}"
  context: "{what was happening}"
  potential_type: claim | heuristic | decision | unknown
  promoted: false

Session Record (trace/sessions/YYYY-MM-DD_NNN.yaml)

session:
  id: "YYYY-MM-DD_NNN"
  timestamp: "YYYY-MM-DDTHH:MM"
  summary: "{one-line summary of what happened}"

events_logged:
  - type: decision | experiment | dead_end | pivot | claim | heuristic | observation
    id: "{N/C/H/O}{XX}"
    provenance: user | ai-suggested | ai-executed | user-revised
    summary: "{what}"

ai_actions:
  - action: "{what AI did}"
    provenance: ai-executed
    files_changed: ["{paths}"]

claims_touched:
  - id: C{XX}
    action: created | advanced | weakened | confirmed
    provenance: user | ai-suggested

open_threads:
  - "{what needs follow-up}"

ai_suggestions_pending:
  - "{unconfirmed AI suggestions from this session}"

Initialization (if ara/ does not exist)

Create the full directory structure and seed files automatically. Do not ask.

mkdir -p ara/{logic/solution,src/{configs,kernel},trace/sessions,evidence/{tables,figures},staging}

Then write:

ara/PAPER.md — root manifest (infer title, authors, venue from project context)
ara/trace/sessions/session_index.yaml — sessions: []
ara/trace/exploration_tree.yaml — tree: []
ara/staging/observations.yaml — observations: []
ara/logic/claims.md — # Claims
ara/logic/problem.md — # Problem
ara/logic/solution/heuristics.md — # Heuristics
ara/evidence/README.md — # Evidence Index

Maturity Tracker (runs during epilogue)

While reviewing staging/observations.yaml:

3+ observations on same topic → promote to appropriate layer (mark ai-suggested)
Observation with experimental evidence → promote to evidence/
Observation contradicting a claim → flag: 
Stale observations (3+ sessions) → flag with stale: true

Procedure

Read existing ara/ files to get current state (IDs, claims, tree).
Scan the full conversation for research-significant events.
Classify each event and assign provenance.
Append new entries to the correct files. Update existing entries if status changed.
Create session record at ara/trace/sessions/YYYY-MM-DD_NNN.yaml.
Append session to ara/trace/sessions/session_index.yaml.
Run maturity tracker on staging area.
Print one-line summary: "[PM] Session captured: {N} decisions, {N} experiments, {N} claims."

Rules

Never run during a task — only as epilogue after the user's request is done.
Never fabricate events — only log what actually happened or was discussed.
Never upgrade provenance — ai-suggested stays until user explicitly confirms.
Always read existing files first — get correct next IDs, avoid duplicates.
Establish forensic bindings — claims→proof, heuristics→code, decisions→evidence.
Append, don't overwrite — add new entries, never replace existing content.
Keep YAML valid — validate structure after writes.

Reference Files

For detailed protocol and taxonomy specifications, load on demand:

references/event-taxonomy.md — Full classification of research-significant events
references/provenance-tags.md — Provenance tag semantics and edge cases
references/session-protocol.md — Step-by-step session recording protocol

This skill ships inside the AI Research Skills plugin.

Run this outside your AI tool, using Node.js 22.20.0 or newer. Skills CLI 1.7.2 skips skill selection; prompts cancel installation without an interactive terminal. If choosing Project when asked about installation scope, open your project's folder before running this.

Install checklist

Check selected tools if a picker appears; Claude Code may be unchecked under Additional agents. ↑/↓ moves, Space toggles selections, Enter confirms.
Without a tool picker, check Installing to: for your intended tool. Stop if it names a different tool.
If asked, choose Symlink (Recommended) for shared files or Copy to all agents for separate copies; review the summary before confirming installation.
Install the find-skills skill? defaults to Yes, adding another skill for all projects. Choose No if you don't want that extra installation.

Skills CLI 1.7.2 sends install data to skills.sh by default, including the source, skill names, target tools and file details; GitHub sources are reported only when GitHub confirms the repository is public, while other remote sources can also be reported. Confirmed-public GitHub sources also trigger a security-audit request. Before installing, set the environment variable DO_NOT_TRACK=1 or DISABLE_TELEMETRY=1 to disable both.

npx skills add orchestra-research/ai-research-skills --skill "ara-research-manager" --full-depth

After installing for Claude Code, open it in the installation project if you chose Project; Global makes the skill available across projects on this computer. Once Claude Code loads the skill, its description helps Claude decide when to use it.

If installation created a top-level skills folder that did not exist when your Claude Code session started, run /reload-skills in that session. Run it again after later changes in that folder.

What's inside

Files included with this skill.

View on GitHub

Same repository

academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn. Use when creating any figure for a conference paper.Read full description
ara-compiler
Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, concepts, heuristics), physical layer (configs, code stubs), exploration graph, and grounded evidence. Use when ingesting a paper or codebase into a structured, machine-executable knowledge package, building an ARA from scratch, or converting research outputs into a falsifiable, agent-traversable form.Read full description
ara-rigor-reviewer
Performs ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence relevance, falsifiability, scope calibration, argument coherence, exploration integrity, methodological rigor) and producing a constructive, severity-ranked report with a Strong Accept-to-Reject recommendation. Use after Level 1 structural validation passes, when an ARA needs an objective epistemic critique before publication or release.Read full description
audiocraft-audio-generation
PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.Read full description
autogpt-agents
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.Read full description
autoresearch
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.Read full description