agentleFS
Sign inStart free
Lucas-GrilliLucas-Grilli/context-os-plugin/skills/session-log/SKILL.md

session-log

Skill1 starsChanged 3 months agoMITView on GitHub

Closes a block of work by writing a short, dated entry in the monthly dump (00_context/dump/YYYY-MM.md) and returns the same recap in chat. Use for "log this", "write the dump", "close the session", "sum up what we did".

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 10 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

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If building the recap means reading long messages or several files, state an estimate of the tokens used and a cheaper alternative if one …

    line 22

“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

v2.0

Goal: stop losing feedback, decisions and finished work that only ever existed in the conversation, or in the assistant's automatic memory, which is invisible to the user.

Steps

  1. Decide the scope ("from when") — look back through the conversation and find where the active block starts: usually the last clean change of subject, or the last dump already written in this session, whichever is more recent. If it is ambiguous, propose the scope in one line ("Summing up from X, right?") and wait for confirmation before writing.
  2. Filter first, then categorise — a line earns its place only if it matters later: a behaviour to repeat or avoid, a decision worth re-reading, a fact that changes a project's state. Process details internal to the session do not qualify, even when true. When in doubt, 1-2 lines, not 4. Categories: [feedback] (a correction or preference that changes future behaviour), [recap] (what was done, decided or produced), [other] (an open thread with no answer yet).
  3. Write into the current month's dump — get the real date with a command before naming the file. 00_context/dump/YYYY-MM.md, create the file if the month does not exist yet, using the header already in use. Format: - **YYYY-MM-DD [category]:** content in 1-2 lines.
  4. Return the recap in chat — paste the same lines just written, without reformatting or expanding them. No preamble.

Hard rules

  • It does not work on an empty or already closed chat: it needs a live conversation to extract the block from.
  • If building the recap means reading long messages or several files, state an estimate of the tokens used and a cheaper alternative if one exists.
  • Manual trigger, never automatic. If it ever becomes automatic: validate it over 2-3 manual runs first (an over-sensitive trigger writes noise the user then has to filter), and coordinate it with Rule 14 of CLAUDE.md (self-improvement log) so the same line is not written twice.

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.

Check your setup, free