project-insights
Skill0 starsChanged 7 months agoMITView on GitHub
Deep analysis of any project using journal entries, repo files, and strategy docs. Use when user says "give me insights on", "analyze project", "how is X going", "project status", "what's stalled", or asks about a specific project's health.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- Happy-Technologies-LLC/happy-platform-skillstheir own version, first seen Nov 1, 2026
- vinci7/project-insights-skilltheir own version, first seen Oct 18, 2025
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- Happy-Technologies-LLC/happy-platform-skills★ 41same name
- vinci7/project-insights-skill★ 1same 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
- journal-reviewSkill
- keyword-filter-frameworkSkill
- langgraph-agentic-pipelineSkill
- llm-as-judge-eval-frameworkSkill
- multi-tab-dashboard-rendererSkill
- multi-tier-memory-systemSkill
- parquet-storage-with-walSkill
- 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
8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
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
- Very specific: line 23
Journal entries: Read ALL entries for the project from your journal file (filter by project:<slug> tag)
- Distinctive: line 24
Repo files: Read the project's repo — strategy docs, PLAN.md, FEATURES.md, README, CLAUDE.md
- Distinctive: line 25
Principles: Check any team/personal principles docs for anti-pattern checks
- Distinctive: line 35
No entries in 14+ days
- Distinctive: line 50
No validation entries (who have you talked to?)
- Distinctive: line 51
No user feedback logged
- Distinctive: line 52
No marketing or distribution work
- Distinctive: line 53
No revenue model discussion
≈ “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
Project Insights
Delivers deep analysis of any project by cross-referencing journal entries, repo files, and strategy docs.
Instructions
Step 1: Identify the project
Match the user's request to a project. If ambiguous, ask.
Step 2: Gather all data
- Journal entries: Read ALL entries for the project from your journal file (filter by
project:<slug>tag) - Repo files: Read the project's repo — strategy docs, PLAN.md, FEATURES.md, README, CLAUDE.md
- Principles: Check any team/personal principles docs for anti-pattern checks
Step 3: Analyze across 5 dimensions
1. Momentum
- Frequency and recency of entries
- Regular work vs sporadic bursts
- Shipped features with real user impact
2. Stalls
- No entries in 14+ days
- Open decisions older than 14 days without resolution
- Action items from brainstorms that never got started
3. Repeated Patterns
- Same anti-pattern tags appearing multiple times
- Similar decisions being re-made (indecision loop)
- Brainstorms without follow-through (idea accumulation without execution)
4. Strategy Contradictions
- What journal says vs what strategy docs say
- Stated priorities vs actual work logged
- Common anti-patterns: infrastructure trap, feature overload, validation avoidance, perfection loop
5. Gaps
- No validation entries (who have you talked to?)
- No user feedback logged
- No marketing or distribution work
- No revenue model discussion
Step 4: Deliver the analysis
Be specific — cite journal entries by date and content. No vague observations.
## [Project Name] — Deep Analysis
### Momentum: [Good/Slowing/Stalled]
[Specific evidence with dates]
### Key Wins
- [Dated, specific wins]
### Concerns
- [Dated, specific concerns with evidence]
### Anti-Pattern Check
- [Any violations detected]
### Recommended Actions
1. [Most impactful action]
2. [Second action]
3. [Third action]Honesty Rules
- Challenge bad reasoning, don't just record it
- Flag when the user is repeating a known anti-pattern
- Push back when something contradicts their own strategy docs
- "What are you missing?" is always a valid question
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.

