Monitor CI
nrwl/nx
Monitor Nx Cloud CI pipeline and handle self-healing fixes. An agent skill from nrwl/nx.
A skill your agent uses when policy health needs tuning: too many explore pipelines, repeated failures, stalled promotions, or noisy rollback behavior.
Install Policy Optimization
$ npx skills add jianzhichun/emerge --skill policy-optimization -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jianzhichun/emerge policy-optimization --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jianzhichun/emerge.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/policy-optimization .claude/skills/policy-optimization && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "policy-optimization" agent skill from https://github.com/jianzhichun/emerge/tree/main/skills/policy-optimization into .claude/skills/policy-optimization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "policy-optimization", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jianzhichun/emerge/tree/main/skills/policy-optimizationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jianzhichun/emerge --skill policy-optimization -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jianzhichun/emerge policy-optimization --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jianzhichun/emerge.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/policy-optimization .agents/skills/policy-optimization && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "policy-optimization" agent skill from https://github.com/jianzhichun/emerge/tree/main/skills/policy-optimization into .agents/skills/policy-optimization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "policy-optimization", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jianzhichun/emerge --skill policy-optimization -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jianzhichun/emerge policy-optimization --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jianzhichun/emerge.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/policy-optimization .cursor/skills/policy-optimization && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "policy-optimization" agent skill from https://github.com/jianzhichun/emerge/tree/main/skills/policy-optimization into .cursor/skills/policy-optimization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "policy-optimization", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jianzhichun/emerge.git --path skills/policy-optimization--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jianzhichun/emerge --skill policy-optimization -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jianzhichun/emerge policy-optimization --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jianzhichun/emerge.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/policy-optimization .gemini/skills/policy-optimization && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "policy-optimization" agent skill from https://github.com/jianzhichun/emerge/tree/main/skills/policy-optimization into .gemini/skills/policy-optimization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "policy-optimization", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jianzhichun/emerge policy-optimizationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jianzhichun/emerge --skill policy-optimization -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jianzhichun/emerge.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/policy-optimization .github/skills/policy-optimization && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "policy-optimization" agent skill from https://github.com/jianzhichun/emerge/tree/main/skills/policy-optimization into .github/skills/policy-optimization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "policy-optimization", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jianzhichun/emerge --skill policy-optimization -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jianzhichun/emerge policy-optimization --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jianzhichun/emerge.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/policy-optimization .opencode/skills/policy-optimization && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "policy-optimization" agent skill from https://github.com/jianzhichun/emerge/tree/main/skills/policy-optimization into .opencode/skills/policy-optimization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "policy-optimization", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
policy-optimization- GitHub stars
- 106
- Token cost
- ~916 tokens
- SKILL.md length
- 399 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when policy health needs tuning: too many explore pipelines, repeated failures, stalled promotions, or noisy rollback behavior.
- Works in 5 steps: Capture policy snapshot → Classify risk buckets → Prioritize remediation → …
- Policy health needs tuning: too many explore pipelines
- SKILL.md covers Overview, When to Use, Workflow and Output Contract, plus 1 more section
- Calls python3
What it does
Policy Optimization is an agent skill from jianzhichun/emerge. Use when policy health needs tuning: too many explore pipelines, repeated failures, stalled promotions, or noisy rollback behavior. Produces a prioritized optimization plan with safe threshold recommendations.
Its SKILL.md is about 920 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in DevOps & Cloud. The licence is MIT.
When your agent uses it
- Policy health needs tuning: too many explore pipelines
- Repeated failures
- Stalled promotions
- Noisy rollback behavior
Example prompts
- “/policy-optimization”
Requirements
- Python 3
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 035db30. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Policy Optimization loads about 916 tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 399 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from jianzhichun/emerge at commit 035db30, republished under its MIT licence (© jianzhichun). 399 words, ~916 tokens.
Download SKILL.mdSave it as
.claude/skills/policy-optimization/SKILL.md (or your agent's skills folder).- name
- policy-optimization
- description
- Use when policy health needs tuning: too many explore pipelines, repeated failures, stalled promotions, or noisy rollback behavior. Produces a prioritized optimization plan with safe threshold recommendations.
Policy Optimization
Overview
Use this skill when /policy output shows drift, stalls, or noisy failure patterns.
Goal: improve promotion quality and stability without unsafe threshold changes.
Core principle: diagnose first, tune second. Do not change thresholds without clear evidence from attempts, success_rate, verify_rate, and failure patterns.
When to Use
explorecount is high and long-lived.- Any pipeline has
consecutive_failures >= 1. canarypipelines fail to reachstabledespite enough attempts.- Rollbacks are frequent (
rollback_executed_countgrows). - The team asks "which policy threshold should we tune next?"
Do not use when:
- The request is only to display status (use
policycommand only). - There are no meaningful signals (too little data / low attempts).
Workflow
1) Capture policy snapshot
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/repl_admin.py" policy-status --prettyIf parsing is needed:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/repl_admin.py" policy-status2) Classify risk buckets
Classify each pipeline into one bucket:
- Critical:
consecutive_failures >= rollback_consecutive_failures - Warning:
consecutive_failures == 1or verify_rate materially low - Stalled: high attempts but still
explore/canary - Healthy: stable or trend strongly positive
3) Prioritize remediation
Priority order:
- Fix
Criticalpipelines first (execution correctness and rollback safety) - Fix high-volume
Warningpipelines - Promote
Stalledbut healthy candidates (remove lifecycle friction) - Leave
Healthyunchanged
Tie-breakers:
- Higher
consecutive_failuresfirst - Then lower
verify_rate - Then higher policy traffic (
policy_enforced_count)
4) Propose threshold tuning (guardrailed)
Threshold changes are allowed only when:
- Sample size is credible (attempts near/above promotion thresholds)
- Signal is consistent across multiple pipelines (not one-off noise)
- A specific failure mode is identified
Guardrails:
- Never relax all gates at once.
- Change one threshold group at a time, then observe.
- Keep rollback protection conservative (
rollback_consecutive_failures). - Prefer pipeline fixes over threshold relaxation when failures are deterministic.
Show full SKILL.md (139 more words)Show less
5) Define verification window
After any tuning, run a short observation window and re-check:
- status movement (
explore -> canary -> stable) - success/verify trend
- new consecutive failure bursts
- rollback/stop counts
Output Contract
Return a concise optimization report:
- Snapshot: total pipelines, status distribution, threshold values
- Findings: critical/warning/stalled groups with evidence
- Actions: top 3-5 actions in execution order
- Threshold proposal: optional, with explicit risk statement
- Verification plan: what to watch and pass/fail criteria
Common Mistakes
| Mistake | Better approach |
|---|---|
| Tune thresholds from one bad run | Wait for enough attempts and consistent pattern |
| Lower multiple promotion gates together | Change one gate group, then observe |
| Ignore verify_rate and focus only on success_rate | Treat verify as first-class gate for safety |
| Keep retrying a broken pipeline in explore | Fix pipeline logic before policy tuning |
| Optimize by intuition | Base every action on measurable policy signals |
© jianzhichun, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/policy-optimization of jianzhichun/emerge.
Open the folder on GitHubat commit 035db30
Compare with similar skills
Policy Optimization next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Policy Optimization this skilljianzhichun/emerge | 106 | — | ~916 | Automated safety check: Pass | MIT | |
| Monitor CInrwl/nx | 29k | 6 repos | ~4.7k | Automated safety check: Pass | MIT | |
| Terraform and OpenTofu Guideagentscope-ai/QwenPaw | 36k | 6 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Vercel Optimize Auditvercel-labs/agent-skills | 32k | 8 repos | ~4.3k | Automated safety check: Pass | None | |
| Analyze GitHub Action Logswithastro/astro | 63k | 1 repos | ~1.3k | Automated safety check: Pass | Custom licence | |
| Openclaw Live Updateropenclaw/openclaw | 392k | — | ~3.7k | Automated safety check: Pass | MIT |
Similar skills
Terraform and OpenTofu Guide
agentscope-ai/QwenPaw
Guidance for writing and testing Terraform and OpenTofu code: module structure, naming, test approaches, CI/CD workflows, state handling and security scanning.
- Official
Vercel Optimize Audit
vercel-labs/agent-skills
Runs a metrics-first audit of a deployed Vercel project, gating investigations on real signals to produce ranked, citation-backed cost and performance recommendations.
- Official
Analyze GitHub Action Logs
withastro/astro
Analyze recent GitHub Actions workflow runs to identify patterns, mistakes, and improvements.
Openclaw Live Updater
openclaw/openclaw
Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation.
Docs Learn PR Preview
netdata/netdata
Use only when the user explicitly asks to build, run, preview, inspect, or validate learn.netdata.cloud locally using the contents of a PR or documentation branch before merge.
More from jianzhichun/emerge
All 14 skills in this repoDistilling Operator Flows
jianzhichun/emerge
A skill your agent uses when wiring a generic connector to capture remote operator actions and convert repeated event facts into pending pipeline work through Claude Code skills.
Emerge Forward Synthesis
jianzhichun/emerge
Distill Emerge forward flywheel WAL samples into a parameterized pipeline result.
Emerge Reverse Synthesis
jianzhichun/emerge
Distill Emerge reverse flywheel raw operator events into a structured synthesis result.
Initializing Vertical Flywheel
jianzhichun/emerge
A skill your agent uses when a user asks to initialize a domain flywheel from natural language context, especially when environment details are incomplete or mixed with execution assumptions.
Operator Monitor Debug
jianzhichun/emerge
A skill your agent uses when the operator monitoring pipeline appears broken: EventBus has no events, PatternDetector is not firing, elicitation dialog never appears, or OperatorMonitor is silent.
Reflection Deep Dive
jianzhichun/emerge
A skill your agent uses when connector flywheel history is large/noisy and lightweight reflection is insufficient.
Related
Categories
Questions about Policy Optimization
What does Policy Optimization do?
A skill your agent uses when policy health needs tuning: too many explore pipelines, repeated failures, stalled promotions, or noisy rollback behavior. Policy Optimization is an agent skill from jianzhichun/emerge. Use when policy health needs tuning: too many explore pipelines, repeated failures, stalled promotions, or noisy rollback behavior.
When should I use Policy Optimization?
Policy Optimization fits situations like: policy health needs tuning: too many explore pipelines; repeated failures; stalled promotions; noisy rollback behavior.
How do I install Policy Optimization in Claude Code?
Run `npx skills add jianzhichun/emerge --skill policy-optimization -a claude-code`. Or copy the skill folder (skills/policy-optimization in jianzhichun/emerge) into .claude/skills/policy-optimization in your project. Claude Code loads it when a task matches its description.
How do I install Policy Optimization in Codex?
Run `npx skills add jianzhichun/emerge --skill policy-optimization -a codex`. Or copy the skill folder (skills/policy-optimization in jianzhichun/emerge) into .agents/skills/policy-optimization in your project. Codex loads it when a task matches its description.
Can I use Policy Optimization in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jianzhichun/emerge --skill policy-optimization -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/policy-optimization, .gemini/skills/policy-optimization, .github/skills/policy-optimization and .opencode/skills/policy-optimization in your project.
What does Policy Optimization need to run?
Going by SKILL.md and its folder, Policy Optimization needs the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Policy Optimization access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Policy Optimization safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Policy Optimization use?
Policy Optimization is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Policy Optimization use?
About 916 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Policy Optimization?
Skills that share tags, products or a category with Policy Optimization: Monitor CI (nrwl/nx, 29k stars), Terraform and OpenTofu Guide (agentscope-ai/QwenPaw, 36k stars), Vercel Optimize Audit (vercel-labs/agent-skills, 32k stars) and Analyze GitHub Action Logs (withastro/astro, 63k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Policy Optimization?
jianzhichun (a GitHub user) maintains it in jianzhichun/emerge, which has 106 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on April 26, 2026.
Source: jianzhichun/emerge on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.