agentleFS
0xUrsanomics0xUrsanomics/utopia-os/skills/forest-synthesis/SKILL.md

forest-synthesis

Skill2 starsChanged 24 days agoMITView on GitHub

Weekly cross-corpus synthesis across accumulated daily-forest digests. Cross-day pattern extraction invisible to single-day reading. Use weekly not daily.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When asked for a "forest of forests" synthesis, cross-month pattern extraction, or strategic read across accumulated daily-forest digests.

    line 15
  2. Distinctive:

    Read the 8 most recent digests IN FULL

    line 33
  3. Distinctive:

    Read 5-7 selected digests from mid-corpus (pick around sentiment shifts or dates around key events)

    line 34
  4. Very specific:

    After operator review: move to outputs/reviewed/<agent>/

    line 69
  5. Distinctive:

    Do NOT skim all files equally.

    line 76
  6. Distinctive:

    Do NOT collapse to keyword counts.

    line 77
  7. Distinctive:

    Do NOT skip the focus-market-specific section.

    line 78

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Forest Synthesis Skill

When to Use

When asked for a "forest of forests" synthesis, cross-month pattern extraction, or strategic read across accumulated daily-forest digests. Ideally weekly (not daily. too noisy).

Prerequisites

  • Daily-forest digests at outputs/daily-forest/YYYY-MM-DD-daily-forest.md (30+ files)
  • Skills system: skills/daily-forest/SKILL.md must exist and be LIVE

Procedure

Step 1. Identify the corpus

ls outputs/daily-forest/*.md | wc -l  # count available files
ls outputs/daily-forest/*.md | head -5  # oldest
ls outputs/daily-forest/*.md | tail -8  # most recent

Step 2. Strategic read via subagent

Spawn a subagent with:

  • Read the 8 most recent digests IN FULL
  • Read 5-7 selected digests from mid-corpus (pick around sentiment shifts or dates around key events)
  • Section-header skim on remaining files
  • Goal: identify cross-day patterns invisible to single-day reading

Subagent brief (paste verbatim, replacing N):

Read the daily-forest digests at outputs/daily-forest/. Corpus has ~N files.

Strategy: read last 8 in full, skim 5-7 from mid-corpus, section-header skim the rest.

Extract cross-day patterns in 8 categories:
1. Persistent Movers (appeared 3+ times, same direction)
2. Wave Movers (spiked then faded)
3. Multi-Week Silences (present then absent)
4. Tone Arcs (sentiment shift over time)
5. Long Cross-Stitches (two unrelated themes converging)
6. Late Bloomers (absent early, strong later)
7. Focus-Market-Specific (your market's authorities, regulators, corridors, local players)
8. Platform Ecosystem (releases + tool announcements for platforms you depend on)

End with: ONE structural shift paragraph. The biggest macro pattern the corpus reveals that single-day reading misses entirely.

Output to: outputs/raw/<agent>/YYYY-MM-DD-forest-of-forests-synthesis.md

Step 3. Compress for chat delivery

Extract the ONE structural shift + 3 most actionable operator-specific findings. Deliver to chat as a compressed briefing.

Step 4. Log

echo '{"ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","category":"forest-synthesis","event":"weekly_synthesis_complete","files_read":N,"output":"outputs/reviewed/<agent>/YYYY-MM-DD..."}' >> logs/session.jsonl

Output format

  • Full synthesis: outputs/raw/<agent>/YYYY-MM-DD-forest-of-forests-synthesis.md
  • After operator review: move to outputs/reviewed/<agent>/
  • Chat message: compressed 8-bullet version, actionable operator-specific first

Cadence

Weekly (Sunday evening or Monday morning). Not daily. Cross-day pattern visibility requires 5+ digests minimum to be useful.

Anti-patterns

  • Do NOT skim all files equally. recency weighting matters (last 8 in full)
  • Do NOT collapse to keyword counts. cross-day narrative shifts are the goal
  • Do NOT skip the focus-market-specific section. that's the primary operator-actionable output

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.