eval-observation-writing
Write CodeFlowMu EVAL observations with evidence, impact, confidence, and follow-up.
Skill by joinwell52-AI
Chalk Labs
Need help deploying eval-observation-writing?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/joinwell52-ai-eval-observation-writing
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/eval-observation-writing
What's inside
- Skill name
eval-observation-writing- Description
- 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.
- License
- MIT
- Instructions
- 32 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# 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 ```text Observation: README lacks Chinese version Impact: ADMIN discovery friction Follow-up: local DEV task ```
From joinwell52-AI/CodeFlowMu-open, MIT.
More from joinwell52-AI/CodeFlowMu-open
- 0.557score
architect-system-design
joinwell52-AI
Produce CodeFlowMu/FCoP-aware system designs before implementation.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
dev-test-and-explain
joinwell52-AI
Verify and explain DEV changes for PM, QA, or ADMIN review.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
architect-boundary-review
joinwell52-AI
Review CodeFlowMu proposals for boundary violations.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
architect-decision-record
joinwell52-AI
Prepare or review architecture decision notes without adopting ADRs automatically.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
browser-playwright-check
joinwell52-AI
Use when an agent needs to operate or verify a web page with Playwright, including screenshots, viewport checks, navigation, forms, clicks, canvas visibility…
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
code-search-navigation
joinwell52-AI
Use when an agent needs to locate relevant files, symbols, call sites, routes, tests, configs, or ownership boundaries before editing or explaining code.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
dev-code-location
joinwell52-AI
Locate relevant CodeFlowMu code and documentation before editing.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
dev-small-scope-patch
joinwell52-AI
Make narrowly scoped CodeFlowMu changes using existing patterns.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
eval-promotion-advice
joinwell52-AI
Advise how EVAL findings should be promoted.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
eval-risk-gap-analysis
joinwell52-AI
Analyze CodeFlowMu risks and gaps from EVAL findings.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
ops-log-diagnosis
joinwell52-AI
Summarize CodeFlowMu logs into actionable evidence.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
ops-runtime-health
joinwell52-AI
Check CodeFlowMu runtime, Panel, project root, and FCoP directory health.
SkillBFreshness: B★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 30, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/joinwell52-AI/CodeFlowMu-open
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from joinwell52-AI
- 0.622score
Fcop
joinwell52-AI
FCoP Core adapter with 25 canonical tools and 6 read-only resources for durable agent work.
ConnectorAFreshness: ALocal★ 2↓ 107/wkClaude Code +5 - 0.557score
dev-test-and-explain
joinwell52-AI
Verify and explain DEV changes for PM, QA, or ADMIN review.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
architect-boundary-review
joinwell52-AI
Review CodeFlowMu proposals for boundary violations.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
architect-decision-record
joinwell52-AI
Prepare or review architecture decision notes without adopting ADRs automatically.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
browser-playwright-check
joinwell52-AI
Use when an agent needs to operate or verify a web page with Playwright, including screenshots, viewport checks, navigation, forms, clicks, canvas visibility…
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
architect-system-design
joinwell52-AI
Produce CodeFlowMu/FCoP-aware system designs before implementation.
SkillBFreshness: B★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get eval-observation-writing running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
eval-observation-writing skill. Agent Mart. https://agentmart.dev/skills/joinwell52-ai-eval-observation-writing (last updated 2026-10-24)