agentleFS
flonatflonat/flonat-research/skills/session-log/SKILL.md

session-log

Skill150 starsChanged 9 days agoMITView on GitHub

Create a timestamped research-session progress log that records completed work, evidence, decisions, and next steps. Use when closing or checkpointing substantive project work that needs a durable chronology. Not for saving one reusable finding; use $store-insight.

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ml-training-recipe, replication and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • getcompanion-aiSkill

    ml-training-recipe

    Find implementable ML training recipes from papers, datasets, docs, and code. Use when the user wants to fine-tune, train, reproduce, or choose a practical ML method, dataset, hyperparameter setup, or benchmark recipe.

    Also in 3 projects that use this

  • getcompanion-aiSkill

    replication

    Plan a replication of a paper, claim, or benchmark, and execute only after an explicit environment choice. Use when the user asks to replicate results, reproduce an experiment, verify a claim empirically, or build a replication package.

    Also in 3 projects that use this

  • brainbytes-devSkill

    alpha-research

    Also in 3 projects that use this

  • JaimeParkerSkill

    paper-code-audit

    Perform three-way cross-validation of a research paper by comparing the original paper text (via Zotero), official code implementation (via Git), and personal Obsidian notes. Use this skill whenever the user wants to "audit a paper", "verify paper claims against code", "cross-check notes with implementation", "triangulate paper + code + notes", "find discrepancies between paper and code", or mentions wanting a deep, structured comparison of a paper's claims against its implementation and their own notes. Also trigger when the user asks to "analyze this paper thoroughly" with code available, or when they want to systematically reconcile what the paper says, what the code does, and what their notes claim.

    Also in 3 projects that use this

  • JimLiuSkill

    pdf-explore

    Use this skill when the user has attached a PDF, paper, report, or other document and the answer needs content from more than one place in it: summarize the methods or any other section, compare sections, find where a topic is discussed, read a value or label off a figure or chart, or find/list/extract every instance of something across the whole document (datasets, benchmarks, citations, figures, table rows, accession numbers — including appendices). Skip it only for a single lookup of 1–4 pages quoted in your very next response — `read_file(pages=[...])` attaches pages as images that are dropped from context after one turn, so multi-section answers end up re-reading the same ranges repeatedly. Parses the PDF once in the Python kernel: `pdf_pages` (pages as persistent text), `pdf_outline` (TOC), `pdf_scan` (rank pages by relevance), `pdf_map`/`pdf_extract` (per-page summary / structured fields via parallel haiku calls). For PDF creation/manipulation, use reportlab/pypdf directly.

    Also in 3 projects that use this

  • KISHOR403Skill

    session-search

    This skill should be used when searching Claude Code session transcripts with semantic understanding. Triggers on queries like "find sessions about X", "when did I work on Y", "search previous conversations". Supports natural language queries with synonym matching.

    Also in 4 projects that use this

  • +1 more from getcompanion-ai

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before writing anything, inventory which projects were affected during this session.

    line 25
  2. Very specific:

    Create log/ directory: if it doesn't exist

    line 43
  3. Distinctive:

    If there's only one project, this reduces to a single log (the common case).

    line 47
  4. Distinctive:

    When multiple logs are created, add a brief cross-reference at the top of each:

    line 51
  5. Distinctive:

    If multiple projects were touched, offer to update focus for each

    line 62

“Common” is measured: kept by at least 6 in 10 of the 15 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Session Log Skill

Automatically create timestamped progress logs for research sessions.

Purpose

Based on Scott Cunningham's session workflow: “Progress logs are my autosave of the workflow.” When sessions end or crash, the next AI client can read logs and pick up exactly where you left off.

When to Use

At the end of any significant work session, or when asked to "log this session" or "update progress".

Workflow

Step 1: Identify Projects Touched

Before writing anything, inventory which projects were affected during this session. A "project" is any directory with its own CLAUDE.md or log/ directory. Common splits:

ScopeWhere the log goes
Work inside a specific projectThat project's log/
Global infrastructure (skills, hooks, rules, settings)Task Management's log/
Course/module-level changes (reorganisation, new CLAUDE.md)That module's log/

Signs of a multi-project session:

  • Files changed in AI client infrastructure (skills, hooks, settings) → global/infrastructure log
  • Files changed in the CWD project → project-specific log
  • Files changed in a parent or sibling directory → check if that's a separate project

Step 2: Create One Log Per Project

For each project identified in Step 1:

  1. Read existing context — check that project's .context/current-focus.md and recent log/ entries
  2. Create log/ directory if it doesn't exist
  3. Write the log to log/YYYY-MM-DD-HHMM.md within that project
  4. Scope the content — each log only covers what happened in that project, not the whole session

If there's only one project, this reduces to a single log (the common case).

Step 3: Cross-Reference

When multiple logs are created, add a brief cross-reference at the top of each:

> Also logged: [other project name] — `[relative or absolute path to other log]`

This lets a future session in one project discover that related work happened elsewhere.

Step 4: Offer Follow-Up

  • Offer to run update-focus for a structured update (session rotation, open loops), rather than making ad-hoc edits to current-focus.md
  • If multiple projects were touched, offer to update focus for each

Log Template

# Session Log: [Date] [Time]

## Project: [Project Name]

## What We Did
- [Bullet points of accomplishments]

## Key Decisions
- [Any choices made and why]

## Problems/Blockers
- [Issues encountered]

## Next Steps
- [ ] [Actionable next items]

## Files Changed
- [List of modified files — only those in THIS project]

Examples

Single-project session

"Please log this session — we worked on the research paper, fixed the simulation code, and decided to target Journal B instead of Journal A."

→ One log in the MCDM project's log/

Multi-project session

"Please log this session — we did Workshop 17, reorganised the module folder, and created two new global skills."

→ Three logs:

  1. Module project log/ — workshop completion, reorganisation, CLAUDE.md creation
  2. Task Management log/ — new skills (init-project-course, audit-project-course), new hook (ensure-latexmkrc.sh), settings.json changes

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.