eval-promotion-advice
Advise how EVAL findings should be promoted.
Skill by joinwell52-AI
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-promotion-advice
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: productivity
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-promotion-advice
What's inside
- Skill name
eval-promotion-advice- Description
- Advise how EVAL findings should be promoted. Use when EVAL needs to suggest local task, CodeFlowMu issue draft, FCoP issue draft, or hold while applying public safety boundaries and ADMIN approval requirements.
- License
- MIT
- Instructions
- 32 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# EVAL Promotion Advice ## When to use Use when an observation may need follow-up beyond the EVAL file. ## Rules - Suggest target only. - Run safe-public-draft thinking before public issue drafts. - Keep `admin_approved` false by default. - Require ADMIN for public submission. ## Required output Use `docs/skills/eval-playbook/promotion-advice.md`. ## Forbidden actions - Do not submit GitHub issues. - Do not bypass ADMIN. - Do not archive/delete/move lifecycle. ## Minimal example ```text Target: local_task Reason: project docs need update Required authority: PM ```
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-observation-writing
joinwell52-AI
Write CodeFlowMu EVAL observations with evidence, impact, confidence, and follow-up.
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
Cite this page
eval-promotion-advice skill. Agent Mart. https://agentmart.dev/skills/joinwell52-ai-eval-promotion-advice (last updated 2026-10-24)