agentleFS
qkitzeroqkitzero/kage-bunshin/.claude/skills/evaluate/SKILL.md

evaluate

Skill1 starsChanged 8 months agoMITView on GitHub

Structured multi-dimensional evaluation. Use when assessing the feasibility of ideas or proposals. Triggered by "is this feasible?", "feasibility?", "should we do this?", "Go/No-Go decision", decision support, or proposal evaluation.

23 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use compare, outreach and 6 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • n24q02mSkill

    compare

    Structured comparison of 2+ alternatives with consistent criteria and decision matrix

    Also in 3 projects that use this

  • QuixiAISkill

    outreach

    Decide whether a message is worth someone's attention, then reach the user through the outbox, or people on a connected chat channel, on their behalf or your own initiative

    Also in 3 projects that use this

  • rhowardstoneSkill

    apply

    Research-backed job application workflow emphasizing relationship-building over mass applications

    Also in 4 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 4 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 23 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If NOTEBOOK_PATH is set, search for past entries related to the evaluation target:

    line 25
  2. Distinctive:

    Read up to 3 matching entries (frontmatter + first 200 characters of body)

    line 28
  3. Very specific:

    Create a team with the following teammates using their agent definitions from .claude/agents/:

    line 35

“Common” is measured: kept by at least 6 in 10 of the 23 edited versions of this file we could read. “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

Evaluate Skill

A workflow that creates an Agent Team of Researcher and Analyst to perform multi-dimensional evaluation through iterative investigation and assessment.

Workflow

Step 1: Understand the Evaluation Target

Accurately understand the idea, proposal, or plan presented by the user. Clarify:

  • Overview of the evaluation target
  • Context (market, organization, technical environment, etc.)
  • Any priority evaluation axes if specified

Step 2: Retrieve Past Notebook Context

If NOTEBOOK_PATH is set, search for past entries related to the evaluation target:

  1. Grep $NOTEBOOK_PATH/reviews/ and $NOTEBOOK_PATH/research/ for keywords from the target
  2. Read up to 3 matching entries (frontmatter + first 200 characters of body)
  3. Include the retrieved content as context when creating the team

Skip this step if zero matches or NOTEBOOK_PATH is not set.

Step 3: Create Agent Team

Create a team with the following teammates using their agent definitions from .claude/agents/:

Teammates:

  • researcher — gathers background information and evidence
  • analyst — performs structured evaluation and scoring

Team instructions:

Evaluation target: [Description]
[Past Notebook context if found]

Collaboration protocol:
1. Researcher investigates: similar cases, market/tech landscape, competitors, risks, required resources
2. Analyst performs initial evaluation based on research (6 dimensions: Feasibility, Market Fit, Effort, Risk, Innovation, Impact)
3. Analyst identifies information gaps and requests additional research from Researcher
4. Researcher conducts targeted follow-up investigation
5. Analyst refines scores and produces final Go / Conditional Go / No-Go recommendation
6. Continue iterating until Analyst is confident in the assessment (aim for 2-3 rounds)

Rules:
- Output language: Use the language specified by OUTPUT_LANGUAGE env var. If not set, match the user's language (default: English)
- If NOTEBOOK_PATH is set: Researcher saves to $NOTEBOOK_PATH/research/, Analyst saves to $NOTEBOOK_PATH/reviews/
- Each agent writes its own deliverables with structured frontmatter

Step 4: Final Output

## Evaluation Results: [Subject]

### Investigation Summary
[How the research and evaluation evolved through discussion]

### Decision Matrix

| Dimension | Score | Rationale |
|-----------|-------|-----------|
| Feasibility | X/5 | ... |
| Market Fit | X/5 | ... |
| Effort | X/5 | ... |
| Risk | X/5 | ... |
| Innovation | X/5 | ... |
| Impact | X/5 | ... |
| **Overall** | **X.X/5** | |

### Recommendation: [Go / Conditional Go / No-Go]

**Reason:** [2-3 sentence overall judgment]

### Strengths / Risks & Concerns / Research Summary

### Next Steps
- If Go: Recommend `/plan-project` for project planning
- If further research needed: Present specific research points

Output Format

Present the following to the user:

  1. Brief summary of the team investigation process
  2. Decision Matrix (6-dimension score table)
  3. Go / Conditional Go / No-Go recommendation with reasoning
  4. Strengths and risks summary
  5. Next step suggestions
  6. Notebook save notification if applicable

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.