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.
In this repository57 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- advisorSkill
- agent-dispatchSkill
- arenaSkill
- audit-pypi-model-packageSkill
- branching-workflowSkill
- code-reviewSkill
- criticSkill
- cron-child-oauth-auditSkill
- daily-forestSkill
- deep-researchSkill
- diagnose-cron-timeoutSkill
- dreamingSkill
- eod-summarySkill
- filingSkill
- goalsSkill
- graph-hygieneSkill
- ideaSkill
- inline-tagsSkill
- intel-analyzerSkill
- longformSkill
- loop-experimentSkill
- loop-librarySkill
- meta-memory-reviewSkill
- office-hoursSkill
- open-loopsSkill
- plan-ceo-reviewSkill
- plan-design-reviewSkill
- prdSkill
- progressive-disclosureSkill
- reality-feedback-createSkill
- reality-review-weeklySkill
- recallSkill
- reconcile-extractionSkill
- redactSkill
- repo-auditSkill
- research-digestSkill
- review-gateSkill
- run-long-job-detachedSkill
- saveSkill
- scopeSkill
- self-auditSkill
- shadow-test-local-classifierSkill
- signal-scorerSkill
- skill-auditSkill
- skill-chainingSkill
- spawn-agent-in-tenantSkill
- spawn-tenantSkill
- split-log-rows-by-session-kindSkill
- subagent-delegationSkill
- telegram-dump-routerSkill
- telegram-reply-toolSkill
- verify-stackSkill
- wave-planSkill
- weekly-retroSkill
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
- Distinctive: line 15
When asked for a "forest of forests" synthesis, cross-month pattern extraction, or strategic read across accumulated daily-forest digests.
- Distinctive: line 33
Read the 8 most recent digests IN FULL
- Distinctive: line 34
Read 5-7 selected digests from mid-corpus (pick around sentiment shifts or dates around key events)
- Very specific: line 69
After operator review: move to outputs/reviewed/<agent>/
- Distinctive: line 76
Do NOT skim all files equally.
- Distinctive: line 77
Do NOT collapse to keyword counts.
- Distinctive: line 78
Do NOT skip the focus-market-specific section.
≈ “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.
Files
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.mdmust 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 recentStep 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.mdStep 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.jsonlOutput 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
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
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.

