agentleFS
Sign inStart free
michalparkolamichalparkola/tapestry-skills-for-claude-code/session-log/SKILL.md

session-log

Skill557 starsChanged 12 months agoMITView on GitHub

Summarize the current conversation session and append results to the weekly agent-log. Use when user says "log this", "session log", "summarize this session", or asks to write results to the agent-log.

We split this skill into the rules it gives an agent

9 rules. 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 7

    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
  • could be automatic: a setting could enforce it
  1. Very specific:

    If that date's heading (## YYYY-MM-DD) already exists in the file, append new topics under it

    line 78
  2. Distinctive:

    If the date heading is not yet in the file, add it in the correct reverse-chronological position

    line 79
  3. Distinctive:

    If the file doesn't exist, create it

    line 80
  4. Distinctive:

    Cross-week dates: If a topic belongs to a date in a different ISO week than the target file, note this to the user and ask whether to add …

    line 82
  5. Distinctive:

    If user edited/corrected something → use the corrected version, ignore earlier drafts

    line 87
  6. Very specific:

    If today's ## YYYY-MM-DD heading already has bullets, add new ones at the end — never delete or rewrite existing bullets

    line 90
  7. Distinctive:

    If a topic from this session overlaps with an existing bullet, add the new details as additional nested bullets under a new topic bullet — …

    line 91
  8. Distinctive:

    Keep bullets ruthlessly short — one sentence, no semicolons chaining multiple thoughts

    line 100
  9. Distinctive:

    Do NOT include the full chunk content in the log — just the marker

    line 102

“Common” is measured: kept by at least 6 in 10 of the 13 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

Summarize the current conversation and append to the weekly agent-log file.

Output Location

YYYY-wWW Agent Log.md

Where YYYY-wWW is the ISO week of today's date. Calculate with:

date +%Y-w%V

Format Rules

  1. Reverse chronological order — newest day on top
  2. One ## heading per day — format: ## YYYY-MM-DD
  3. Bullets, not subheadings — inside a day, use plain bullet - Topic title as topic separator, not ###. No bold, no formatting on topic lines.
  4. Details as nested bullets — one sentence per sub-bullet, can nest if needed for details. No bold. Nesting uses a TAB.
  5. CHUNK markers — if a topic produced a reusable output (a plan, a summary, a framework, a draft message), add nested bullet: CHUNK: <descriptive title>
  6. No explanatory text — no intros, no "in this session we discussed", no meta-commentary
  7. Append, don't replace — when a day heading already exists, add new bullets under it without removing existing content

Example

## 2026-02-28

- Analiza strategii X vs framework Y + moje obserwacje
  - Strategia jest silna w A i B, słaba w C — brakuje fosy i horyzontu 3+lat.
  - Naming produktu "Rescue" implikuje że kupujący jest ofiarą, co blokuje referencje.
  - Anty-segment nie jest sprawdzalny z zewnątrz — to opis doświadczenia, nie filtr.
  - CHUNK: 3-zdaniowe podsumowanie strategii
  - CHUNK: Scorecard po 6 osiach
- Decyzja: follow-up z klientem
  - Nie wysyłać feedbacku (nie prosił), wysłać link do artykułu jako wartość bez CTA.

Step-by-Step Workflow

1. Determine the target file

WEEK=$(date +%Y-w%V)

Target: ${WEEK} agent-log.md

2. Read existing file (if any)

The file may already have entries from earlier sessions this week. Read it first to avoid overwriting.

3. Review the full conversation and determine dates

Scan the entire conversation history. Identify:

  • Topics — distinct subjects discussed (group related back-and-forth into one topic)
  • Decisions — what was decided or concluded
  • Outputs — any reusable artifacts (summaries, plans, draft messages, frameworks, scorecards)

Date attribution: A conversation may span multiple days. Determine the correct date for each topic using these signals (in priority order):

  1. System reminders about date changes ("The date has changed. Today's date is now...")
  2. File names with dates (e.g., 2026-02-26 client email.md was created/discussed on that date)
  3. Context from session summaries — if the session was continued from a compacted conversation, the summary may mention which work happened when
  4. Default — if no date signal exists, use today's date

Group topics by their actual date, not just "today."

4. Write the log entry

For each date that has topics:

  • If that date's heading (## YYYY-MM-DD) already exists in the file, append new topics under it
  • If the date heading is not yet in the file, add it in the correct reverse-chronological position
  • If the file doesn't exist, create it

Cross-week dates: If a topic belongs to a date in a different ISO week than the target file, note this to the user and ask whether to add it to the current file or the correct week's file.

Condensation rules:

  • Multiple related exchanges → one topic bullet
  • Back-and-forth refinement → only the final conclusion matters
  • If user edited/corrected something → use the corrected version, ignore earlier drafts

Append rules:

  • If today's ## YYYY-MM-DD heading already has bullets, add new ones at the end — never delete or rewrite existing bullets
  • If a topic from this session overlaps with an existing bullet, add the new details as additional nested bullets under a new topic bullet — don't merge into existing text

5. Confirm

Tell the user what was logged (topic titles only, one line).

Important Notes

  • The user may have a preferred topic title style — if they edited a previous entry, match that style
  • Keep bullets ruthlessly short — one sentence, no semicolons chaining multiple thoughts
  • CHUNKs reference outputs that exist in the conversation, not in files — they're bookmarks for the user to find later
  • Do NOT include the full chunk content in the log — just the marker
  • Language: match the language the conversation was conducted in (use the user's language)

Download now (ZIP)

  • Other versions21 projects use a version of this.

    Word for word · 2

    1. michalparkola/tapestry-skills★ 538100% same
    2. jacobgreenwald21/claude-skills★ 0100% same

    Edited · 0

    None found.

    Wrote their own version · 19

    1. advaitpaliwal/feynman★ 10ksame name
    2. companion-inc/feynman★ 10ksame name
    3. getcompanion-ai/feynman★ 10ksame name
    4. searlsco/prove_it★ 198same name
    5. flonat/flonat-research★ 145same name
    6. Felpix-Studios/social-science-research★ 8same name
    7. cyberfly/agent-skills★ 3same name
    8. gufranco/claude-engineering-rules★ 3same name
    9. AN0099/toothpaste-kit★ 2same name
    10. Lucas-Grilli/context-os-plugin★ 1same name

    9 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects 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.
    • advaitpaliwalSkill

      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

    • advaitpaliwalSkill

      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 advaitpaliwal
  • In this repository6 other files it gives its agents.

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