agentsclimarketplace

Assess knowledge

Skill tacticaldoll/fornax/skills/assess-knowledge

Portable, single-purpose skills for coding agents that orient, map, plan, review, and reason over your code — read / plan / report, never editing behind your back.

Install
npx -y skills add tacticaldoll/fornax --skill assess-knowledge

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

  • 19 days oldThe repository was created 19 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 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.

What its author says it does

Copied from the file, not written here

Use when an agent needs to assess a conversation for knowledge worth extracting; identifies topics, maturity, and internalize/externalize tendency without creating artifacts or recommending next steps.

SKILL.md

4.7 KB, as published. Nobody here has run it

Assess conversation knowledge

Use this skill to scan conversation content and identify topics with extractable knowledge value — a structured assessment for the user's decision-making.

Governing intuition: name what is worth extracting; do not prescribe what to do with it. Include even thin topics — omission is itself a prescription — and never inflate maturity or volume to justify extraction.

Input: the conversation to assess — by default the current one; if the user names a span or topic, scope to that.

Boundary: assesses and reports only — does not create artifacts, modify files, invoke other skills, or recommend next steps.

Workflow

Phase 1: Thread Identification

Scan the conversation chronologically. Identify distinct discussion topics by semantic shift: a new subject, question, problem, or decision path starts a new thread.

Use this granularity rule:

  • Split compound topics only when they reach independent conclusions.
  • Keep topics merged when they share one conclusion chain.
  • Include low-value or thin topics; omission is a form of prescription.

Phase 2: Per-Topic Assessment

Assess each topic independently across nature, maturity, attribution, volume, and expansion cues.

Nature

Classify with the first matching test:

#TestNature
1Records a decision process with alternatives evaluatedDecision Record
2Derives principles applicable beyond the current projectUniversal Principle
3Solves a specific problem with root cause analysisProblem Diagnosis
4Documents a procedure or how-toOperational Knowledge
5Describes what exists or what was observedFactual Record

Maturity

RatingCriteria
NascentInitial observation; no iteration or conclusion
DevelopingHas structure, some iteration, or partial conclusion
MatureMultiple iterations, refined conclusion, and clear formulation

Raise maturity when the conversation includes trial-and-error cycles, challenge-and-revision exchanges, explicit trade-off comparison, or convergence on a principle.

Attribution

TendencySignal
InternalizeUniversal principle, methodology, or thinking pattern; value is in understanding
ExternalizeProject-specific decision, configuration, architecture constraint, or durable rule; value is in persistence
BothCore insight should be understood personally, while the specific application should be documented
NeitherTopic has conversation value but no clear artifact value

Volume

EstimateCriteria
SufficientAt least 3 refined points, clear structure, and enough depth for a standalone artifact
MarginalHas substance but fits better as a section within a larger artifact
InsufficientBrief mention, no depth, or not worth extracting

Expansion Cues

Expansion cues describe latent structure and evidence gaps for later use. They are not next steps.

Include short cues such as:

  • Narrative arc: how the topic developed over time.
  • Decision tension: alternatives, trade-offs, or redirects.
  • Evidence gap: what is missing or unsupported.
  • Conceptual insight: the transferable understanding embedded in the topic.
  • Durable claim: the specific decision, rule, or constraint the topic asserts.
  • Boundary warning: what should not be generalized.

Output Format

# Conversation Knowledge Assessment

**Date**: [YYYY-MM-DD]
**Topics identified**: [N]

| # | Topic | Nature | Maturity | Attribution | Volume | Expansion Cues | Notes |
|---|---|---|---|---|---|---|---|
| 1 | ... | Decision Record | Mature | Externalize | Sufficient | Decision tension: ... | ... |
| 2 | ... | Universal Principle | Developing | Internalize | Marginal | Conceptual insight: ... | ... |

The table is the complete output. Do not add a recommendations section, action list, or next-step suggestions.

Rules

  • Keep zero project coupling: do not reference a project's directory structure, governance framework, skill inventory, or toolchain unless it is the topic being assessed.
  • Treat expansion cues as diagnostic metadata, not recommendations.
  • Assess honestly: do not inflate maturity or volume to justify extraction.
  • Preserve completeness: every identified topic must appear in the table.
  • Distinguish value assessment from content recall. A request to "summarize our discussion" is content recall; a request for "what is worth extracting" is value assessment.

Keep looking

Skills are one crate of 328,083. 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.