agentsclimarketplace
Sign in

Review

Skill rvanbaalen/skills/plugins/cofounder/skills/review

Review current state, progress, and priorities. Use when the user wants an overview of where things stand, or when the cofounder agent needs to assess progress. Surfaces insights and flags issues proactively.From its SKILL.md

Install
npx -y skills add rvanbaalen/skills --skill review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.1 KB, 406 tokens by cl100k_base, as published. Nobody here has run it

Review

Assess the current state of the business workspace. Surface what matters. Flag what's off.

Process

1. Read Everything

Read all files in the data directory:

  • up-next.md
  • All goal files (goals/)
  • All topic files (topics/)
  • All active action briefs (actions/)
  • Recent daily log entries (check-ins/daily-log.md)
  • Recent data files (data/)
  • Recent decision docs (decisions/)

2. Up-Next Assessment

Present the current queue with a status assessment:

  • Is "Now" set? Is it the right thing?
  • How long has the current "Now" been there?
  • Are "This Week" items on track?
  • Are any queued items stale or no longer relevant?

3. Goal Alignment Check

Review the goal cascade:

  • Does the weekly focus serve the monthly goal?
  • Does the monthly goal serve the quarterly goals?
  • Are quarterly goals still aligned with the north star?

Flag any misalignment.

4. Staleness Audit

Check last-updated dates and file modification times:

  • Topic files not updated in weeks → flag for review
  • Action briefs older than 2 weeks → flag as potentially stalled
  • Goals not reviewed in their cadence period → flag

5. Proactive Insights

Synthesize patterns across the accumulated data:

  • What trends are visible in check-in history?
  • Are there recurring themes in parked ideas?
  • Do any backlog items deserve another look given recent changes?
  • Are action completions accelerating or slowing?
  • What anti-patterns have shown up recently?

6. Recommendations

Based on the review, suggest specific actions:

  • Reprioritize if priorities look wrong
  • Archive stale items
  • Promote backlog items if context changed
  • Propose new data collection if insights are needed

Always ask before reorganizing — present the case, let the user decide.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most review quality skills give in 406 tokens

Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-07

  • Ask questions one at a timein 81 of 1048, across 64 files
  • Provide a recommended answer for each questionin 73 of 1048, across 50 files
  • Explore the codebase instead of asking answerable questionsin 66 of 1048, across 42 files
  • Resolve dependencies between decisions one-by-onein 42 of 1048, across 17 files
  • Interview the user relentlessly about the planin 38 of 1048, across 13 files
  • Order findings by severityin 31 of 1048
  • Resolve each branch of the decision treein 27 of 1048, across 5 files
  • Run a grilling sessionin 26 of 1048, across 5 files
  • Update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 11 files
  • Propose precise canonical terms for vague languagein 25 of 1048, across 7 files
  • Create documentation files lazilyin 24 of 1048, across 5 files
  • Assign severity to every findingin 24 of 1048

Said here and by no other author read

  • present the current queue with a status assessment
  • review the goal cascade for alignment
  • flag any misalignment
  • flag old or stalled items
  • synthesize patterns across accumulated data
  • suggest specific actions based on the review

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,286. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.