journal-review
Skill0 starsChanged 7 months agoMITView on GitHub
Reviews and corrects journal entry categorizations — moves items between projects, updates types, marks tasks complete, creates new projects. Use when user says "fix the categorization", "move this to", "that's wrong project", "review my entries", "clean up journal", or provides corrections to previously written entries.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- bitrix-tools/marketplace-security-skillstheir own version, first seen Nov 15, 2026
- sghng/abstracttheir own version, first seen Oct 15, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- bitrix-tools/marketplace-security-skills★ 8same name
- sghng/abstract★ 0same name
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.
In this repository37 other files it gives its agents.
- ablation-study-frameworkSkill
- async-http-websocket-patternsSkill
- brain-dumpSkill
- chaos-controlled-behavior-systemSkill
- daily-digestSkill
- database-reset-and-seedSkill
- duckdb-analytics-layerSkill
- event-driven-backtest-engineSkill
- event-study-full-pipelineSkill
- event-study-stats-suiteSkill
- failure-learning-systemSkill
- fastapi-sse-live-dashboardSkill
- goal-task-decompositionSkill
- high-information-gain-interviewerSkill
- idea-extraction-batch-pipelineSkill
- idea-grouping-taxonomySkill
- interview-belief-extractorSkill
- journal-captureSkill
- keyword-filter-frameworkSkill
- langgraph-agentic-pipelineSkill
- llm-as-judge-eval-frameworkSkill
- multi-tab-dashboard-rendererSkill
- multi-tier-memory-systemSkill
- parquet-storage-with-walSkill
- project-insightsSkill
- pydantic-typed-config-loaderSkill
- quality-trend-detectionSkill
- research-gap-finderSkill
- safe-commitSkill
- simtom-knowledge-isolationSkill
- statistical-signal-detectionSkill
- streaming-dataset-pipelineSkill
- structured-data-extraction-pipelineSkill
- structured-logging-setupSkill
- system-health-monitoringSkill
- textual-tui-reactiveSkill
- vector-db-ingestionSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
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
- Distinctive: line 41
Before writing, show what will change:
- Distinctive: line 66
Write NEW entries with corrected project tags and types
- Distinctive: line 70
Add to project registry configuration
- Distinctive: line 71
Write entries under the new project slug
- Distinctive: line 74
Write progress entries that capture what was accomplished
- Distinctive: line 79
If new projects were created, update:
- Distinctive: line 99
When the user's correction is ambiguous:
- Distinctive: line 107
Write a new entry with the correct categorization
- Distinctive: line 109
If the old entry causes confusion, note the correction in the new entry's content
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Journal Review
Processes user corrections to journal entries — reassigns projects, fixes types, marks items complete, and creates new project categories.
When This Activates
- User reviews brain-dump output and wants changes
- User says items are in the wrong project
- User wants to mark things as done
- User wants to split a project into multiple
- User wants to merge entries or create new projects
Instructions
Step 1: Understand the corrections
Parse what the user wants changed. Common correction types:
| User Says | Action |
| "Move X to project Y" | Write new entry under project Y with the item, note removal from old project |
| "That's a new project called Z" | Add Z to project registry, write entries under new slug |
| "I already did X" | Write a progress entry marking it complete |
| "That's not a decision, it's a brainstorm" | Write corrected entry with right type |
| "Combine these two" | Merge items into single entry |
| "Split this into A and B" | Write two separate entries |
| "Remove X" / "That's not relevant" | Do not re-write the item |
Step 2: Show proposed changes
Before writing, show what will change:
## Proposed Changes
MOVE:
- "Research speech analysis" → from coaching to domain-expansions
- "Spatial reasoning scan" → from megabot to research
NEW PROJECT:
- discourse (Discourse) — for anonymized interaction items
MARK COMPLETE:
- "Google OAuth setup" → progress entry (already done)
- "Website Mii character scene" → progress entry (already done)
REMOVE:
- "SketchUp character scene" — duplicate of website entry
Proceed?Step 3: Execute changes
For moves and corrections:
- Write NEW entries with corrected project tags and types
- The old entries remain in the journal (append-only) but the newer entries take precedence since they sort by date
For new projects:
- Add to project registry configuration
- Write entries under the new project slug
For completions:
- Write progress entries that capture what was accomplished
- Note the original brainstorm/task it resolves
Step 4: Update project registry
If new projects were created, update:
- The project registry config file (e.g.,
config.pyor equivalent) - Any project table in CLAUDE.md or similar docs
- The journal-capture skill's project table (if bundled)
Step 5: Report changes
## Changes Applied
- Moved 3 items to research project
- Created discourse project with 2 entries
- Marked 4 items as complete (progress entries)
- Updated project registry: 12 → 13 projects
Dashboard re-render needed: run `conda run -n discovery python dashboard.py`Handling Ambiguity
When the user's correction is ambiguous:
- "That's wrong" → Ask: "Which project should it be in?"
- "Fix everything" → Show current state grouped by project, ask for specific corrections
- Partial corrections → Apply what's clear, ask about the rest
Append-Only Journal
The journal is JSONL (append-only). To "move" an item:
- Write a new entry with the correct categorization
- The old entry stays but newer entries appear first in the dashboard
- If the old entry causes confusion, note the correction in the new entry's content
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.

