Adoption

Agent Skills are supported by leading AI development tools.

VS Code Gemini CLI GitHub Goose Amp Cursor Claude Code Letta OpenCode Claude OpenAI Codex Factory VS Code Gemini CLI GitHub Goose Amp Cursor Claude Code Letta OpenCode Claude OpenAI Codex Factory

akshay-na/cco-orchestration

Name: cco-orchestration
Author: akshay-na

ai/gemini-content-team/skills/cco-orchestration/SKILL.md

npx skillsauth add akshay-na/dotfiles cco-orchestration

Clean

TrivyContainer and dependency vulnerability scanner

Clean

SemgrepStatic code analysis for vulnerabilities

Clean

mcp-scan (Snyk)Model Context Protocol security validation

Skipped

Snyk (dep)Open source security scanning

Skipped

Socket.devSupply chain security analysis

Skipped

VirusTotalMulti-engine malware detection

Skipped

CrowdStrikeAdvanced threat intelligence

Skipped

OSV-ScannerOpen Source Vulnerability database check

Skipped

OWASP Dep-Check

cco orchestration checklist

Read rules/orchestration.md, rules/repo-hygiene.md, rules/project-identity.md, skills/project-identity/SKILL.md, rules/brain-paths.md, rules/brain-conventions.md, and rules/cco-single-invocation.md first.

Start of run

Resolve <content-brain> per rules/project-identity.md (same ~/ai-brain/projects/<project_name>/ as Cursor kb-identity).
Parse inbound JSON; validate run_id, action, event_id idempotency.
Optional git pull for active workspace per rules/repo-hygiene.md when using git-tracked brain or project files.
METRICS_READ — load <content-brain>/analytics/metrics-current.json, metrics-latest.md; append metrics_snapshot_read to ~/.gemini/memory/observability/events.jsonl.
Load pipeline state (~/.gemini/memory/pipelines/current-state.md); align FSM with action.
Append phase_enter audit for current phase.

Per phase

Execute parallel group personas (see orchestration table); internal comms: caveman ultra except security-autoclarity.
After each handoff between personas: append handoff audit (hashes not bodies).
On phase completion: phase_exit audit.
No mid-pipeline hand-holding: do not end a turn by telling the operator to run cco again or to “start BRIEF” manually. After RESEARCH, enter BRIEF (cmo, vp-brand, vp-editorial per orchestration) in the same invocation / continued session until awaiting_user.

Human gate

When drafts + QA complete: set FSM awaiting_user; emit cco.run.awaiting_user with CcoRunReport JSON only.

Continue / revise

continue: METRICS*READ if policy says so; archivist when publish metadata present; phase*\* audits.
revise: jump to last_checkpoint from run record; re-run downstream; emit cco.run.revision_applied when done.

End

Success: cco.run.completed, ledger consistent under <content-brain>/_meta/; commit via normal git if applicable.
Failure: ~/.gemini/memory/pipelines/failures/<run_id>-<ts>.md, cco.run.failed, FSM failed.

Forbidden

Third production external agent; caveman in outbound JSON; skipping QA before awaiting_user.

akshay-na/cco-orchestration

ai/gemini-content-team/skills/cco-orchestration/SKILL.md

Executable checklist for one cco pipeline run (parallel groups, METRICS_READ, audit NDJSON, n8n gates).

4 stars

testing

Updated May 9, 2026

$ install --global

skillsauth

npx skillsauth add akshay-na/dotfiles cco-orchestration

Install this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.

Security Scan Results

3 of 9 scanners reported clean

Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.

Scanners Passed

Scanners in report

Clean

TrivyContainer and dependency vulnerability scanner

95%

Clean

SemgrepStatic code analysis for vulnerabilities

95%

Clean

mcp-scan (Snyk)Model Context Protocol security validation

95%

Skipped

Snyk (dep)Open source security scanning

50%

Skipped

Socket.devSupply chain security analysis

50%

Skipped

VirusTotalMulti-engine malware detection

50%

Skipped

CrowdStrikeAdvanced threat intelligence

50%

Skipped

OSV-ScannerOpen Source Vulnerability database check

50%

Skipped

OWASP Dep-Check

50%

Last scanned: May 9, 2026, 4:14 AM166.4s1 file scanned

SKILL.md

name:: cco-orchestration
description:: Executable checklist for one cco pipeline run (parallel groups, METRICS_READ, audit NDJSON, n8n gates).

cco orchestration checklist

Start of run

Resolve <content-brain> per rules/project-identity.md (same ~/ai-brain/projects/<project_name>/ as Cursor kb-identity).
Parse inbound JSON; validate run_id, action, event_id idempotency.
Optional git pull for active workspace per rules/repo-hygiene.md when using git-tracked brain or project files.
METRICS_READ — load <content-brain>/analytics/metrics-current.json, metrics-latest.md; append metrics_snapshot_read to ~/.gemini/memory/observability/events.jsonl.
Load pipeline state (~/.gemini/memory/pipelines/current-state.md); align FSM with action.
Append phase_enter audit for current phase.

Per phase

Execute parallel group personas (see orchestration table); internal comms: caveman ultra except security-autoclarity.
After each handoff between personas: append handoff audit (hashes not bodies).
On phase completion: phase_exit audit.
No mid-pipeline hand-holding: do not end a turn by telling the operator to run cco again or to “start BRIEF” manually. After RESEARCH, enter BRIEF (cmo, vp-brand, vp-editorial per orchestration) in the same invocation / continued session until awaiting_user.

Human gate

When drafts + QA complete: set FSM awaiting_user; emit cco.run.awaiting_user with CcoRunReport JSON only.

Continue / revise

continue: METRICS*READ if policy says so; archivist when publish metadata present; phase*\* audits.
revise: jump to last_checkpoint from run record; re-run downstream; emit cco.run.revision_applied when done.

End

Success: cco.run.completed, ledger consistent under <content-brain>/_meta/; commit via normal git if applicable.
Failure: ~/.gemini/memory/pipelines/failures/<run_id>-<ts>.md, cco.run.failed, FSM failed.

Forbidden

Third production external agent; caveman in outbound JSON; skipping QA before awaiting_user.

Related Skills

akshay-na/team-discovery

development

VerifiedTrustedCommunity

Discovery + naming convention reference for typed dev/SME/QA/devops team members in any workspace folder. Primary consumer: `tech-lead` (org-tier).

4SKILL.mdUpdated May 28, 2026

akshay-na/team-discovery

akshay-na/task-orchestration

devops

VerifiedTrustedCommunity

Automated task classification, agent selection, and state tracking. Use when routing tasks to agents, selecting pipelines, or managing task state.

4SKILL.mdUpdated May 28, 2026

akshay-na/task-orchestration

akshay-na/systems-design-depth

testing

VerifiedTrustedCommunity

Use when designing scalable systems, evaluating consistency models, planning state management, making architectural decisions, or when trade-offs around coupling, failure isolation, and reversibility need explicit reasoning before implementation.

4SKILL.mdUpdated May 28, 2026

akshay-na/systems-design-depth

akshay-na/swarm-task-decomposition

tools

VerifiedTrustedCommunity

CTO/tech-lead helper — split work into disjoint shard briefs with caps (instance_cap, partition_basis, determinism keys).

4SKILL.mdUpdated May 28, 2026

akshay-na/swarm-task-decomposition

Download

For Claude Desktop. Download once, then upload the file in the app — no terminal needed.

Need help? View full Cowork setup guide →

Install manually

Choose your platform

# Clone the repo
git clone https://github.com/akshay-na/dotfiles.git

# Copy into Claude Code skills folder (global)
cp -r dotfiles/ai/gemini-content-team/skills/cco-orchestration ~/.claude/skills/

Claude Code Skills — official skills path docs.

Repository

akshay-na/dotfiles

4 stars

Compatible with

Claude Code

OpenAI Codex CLI

ChatGPT