eval-observation-writing
Skill2 starsChanged 4 months agoMITView on GitHub
Write CodeFlowMu EVAL observations with evidence, impact, confidence, and follow-up. Use when EVAL notices behavior, UX, governance, implementation, or documentation gaps without turning them into REPORTs.
In this repository42 other files it gives its agents.
- architect-boundary-reviewSkill
- architect-decision-recordSkill
- architect-system-designSkill
- browser-playwright-checkSkill
- browser-useSkill
- code-search-navigationSkill
- controlled-emergence-observerSkill
- dev-code-locationSkill
- dev-small-scope-patchSkill
- dev-test-and-explainSkill
- eval-promotion-adviceSkill
- eval-risk-gap-analysisSkill
- ops-log-diagnosisSkill
- ops-runtime-healthSkill
- ops-stuck-workflowSkill
- pm-acceptance-criteriaSkill
- pm-architecture-reviewSkill
- pm-delivery-planSkill
- pm-evolve-skillsSkill
- pm-long-horizon-planningSkill
- pm-priority-triageSkill
- pm-product-design-briefSkill
- pm-product-requirementsSkill
- pm-scope-controlSkill
- pm-solve-problemsSkill
- pm-tech-scopeSkill
- qa-regression-checkSkill
- qa-reproduce-issueSkill
- qa-verify-fixSkill
- run-local-command-checkSkill
- test-selectionSkill
- tm-delivery-governanceSkill
- tm-review-routingSkill
- tm-risk-dependencySkill
- ui-information-architectureSkill
- ui-requirementsSkill
- ui-usability-acceptanceSkill
- ui-visual-consistencySkill
- web-extractSkill
- web-researchSkill
- web-searchSkill
- windows-useSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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 10
Use when recording observed behavior or gaps.
- Distinctive: line 25
Do not treat observation as REPORT.
- Distinctive: line 26
Do not change lifecycle.
- Distinctive: line 27
Do not overclaim without evidence.
≈ “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
EVAL Observation Writing
When to use
Use when recording observed behavior or gaps.
Rules
- State what was seen.
- Attach evidence.
- Describe impact and confidence.
- Suggest follow-up without changing lifecycle.
Required output
Use docs/skills/eval-playbook/observation-writing.md.
Forbidden actions
- Do not treat observation as REPORT.
- Do not change lifecycle.
- Do not overclaim without evidence.
Minimal example
Observation: README lacks Chinese version
Impact: ADMIN discovery friction
Follow-up: local DEV taskDoes 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.