client-manager
CRM health scoring, relance checker, and report generator for Orchestra Intelligence clients.
Skill by LG15601
Chalk Labs
Need help deploying client-manager?
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/lg15601-client-manager
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: documents, data, sales
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
- Runs as
- Shell scripts
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/client-manager
What's inside
- Skill name
client-manager- Description
- CRM health scoring, relance checker, and report generator for Orchestra Intelligence clients. Use when asked about clients, pipeline, MRR, or client health.
- License
- MIT
- Instructions
- 46 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Agent Skills spec issues
- allowed-tools: must be a space-separated string
Files (4)
- SKILL.md
- check-relances.sh · scripts/
- generate-report.sh · scripts/
- health-score.sh · scripts/
SKILL.md (first lines)
# Client Manager Production CRM system with health scoring, relance detection, and reporting. ## Health Score Formula ``` Health = (0.30 x Engagement) + (0.25 x Delivery) + (0.20 x Revenue) + (0.15 x Satisfaction) + (0.10 x Growth) ``` Scores checked against live email activity via `gog` CLI. ## Usage ```bash # Score all clients bash ~/.claude/skills/client-manager/scripts/health-score.sh # Score specific client bash ~/.claude/skills/client-manager/scripts/health-score.sh --client wella # JSON output bash ~/.claude/skills/client-manager/scripts/health-score.sh --json # Check relances needed bash ~/.claude/skills/client-manager/scripts/check-relances.sh # Generate client report bash ~/.claude/skills/client-manager/scripts/generate-report.sh ``` ## Client Tiers - Platinum (MRR >= 10K): 4h SLA, daily health check - Gold (MRR >= 3K): 8h SLA, daily health check - Silver (MRR >= 1K): 24h SLA, weekly health check - Bronze: 48h SLA, bi-weekly - Prospect: 24h SLA, on-activity ## Data - `../../data/clients.json` — 10 real clients with contacts, MRR, project details - `../../data/pipeline.json` — active deals ## Risk Levels - Score >= 80: LOW risk (green) - Score >= 50: MEDIUM risk (yellow) - Score < 50: HIGH risk (red) — alert generated
From LG15601/alba-blueprint, MIT.
More from LG15601/alba-blueprint
- 0.410score
veille
LG15601
AI/Tech intelligence gathering from YouTube, Twitter, RSS, and GitHub.
SkillDFreshness: DClaude Code +9 - 0.410score
health-check
LG15601
System health monitor with 10+ checks: disk, Docker, Alba agent, internet, Tailscale, LaunchAgents, secrets, memory, CPU.
SkillDFreshness: DClaude Code +9 - 0.410score
morning-brief
LG15601
Generate daily morning briefing from 6 real data sources: emails, calendar, GitHub, client pipeline, system health, Google Drive.
SkillDFreshness: DClaude Code +9 - 0.410score
inbox-zero
LG15601
DPYS email classifier for 3 mailboxes.
SkillDFreshness: DClaude Code +9 - 0.407score
codex
LG15601
Codex CLI integration for PR code review and autonomous fix execution.
SkillDFreshness: DClaude Code +9 - 0.406score
daily-briefing
LG15601
Generate morning briefing with calendar, email, tasks, news, Twitter, Slack.
SkillDFreshness: DClaude Code +9 - 0.406score
simulate
LG15601
Run MiroFish social simulation to test public reaction before strategic decisions.
SkillDFreshness: DClaude Code +9 - 0.406score
apex
LG15601
10-step autonomous feature workflow: branch → analyze → plan → execute → validate → review → fix → test → verify → PR.
SkillDFreshness: DClaude Code +9 - 0.403score
self-improve
LG15601
End-of-session self-improvement protocol.
SkillDFreshness: DClaude Code +9 - 0.403score
tool-discover
LG15601
Detect and register new tools when installed.
SkillDFreshness: DClaude Code +9 - 0.403score
nightly-routine
LG15601
Run nightly maintenance: update tools, monitor repos, consolidate memory, check competitors, cleanup.
SkillDFreshness: DClaude Code +9 - 0.397score
clean-test-skill
LG15601
A benign skill for testing false-positive rates
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 1, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/LG15601/alba-blueprint
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from LG15601
- 0.410score
veille
LG15601
AI/Tech intelligence gathering from YouTube, Twitter, RSS, and GitHub.
SkillDFreshness: DClaude Code +9 - 0.410score
health-check
LG15601
System health monitor with 10+ checks: disk, Docker, Alba agent, internet, Tailscale, LaunchAgents, secrets, memory, CPU.
SkillDFreshness: DClaude Code +9 - 0.410score
morning-brief
LG15601
Generate daily morning briefing from 6 real data sources: emails, calendar, GitHub, client pipeline, system health, Google Drive.
SkillDFreshness: DClaude Code +9 - 0.410score
inbox-zero
LG15601
DPYS email classifier for 3 mailboxes.
SkillDFreshness: DClaude Code +9 - 0.407score
codex
LG15601
Codex CLI integration for PR code review and autonomous fix execution.
SkillDFreshness: DClaude Code +9 - 0.406score
daily-briefing
LG15601
Generate morning briefing with calendar, email, tasks, news, Twitter, Slack.
SkillDFreshness: DClaude 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 client-manager 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
client-manager skill. Agent Mart. https://agentmart.dev/skills/lg15601-client-manager (last updated 2026-10-24)