clave-workflow-manager
Skill4 starsChanged 7 months agoNo licenceView on GitHub
Working rules for a Crux company that keeps its tasks and approvals in clave through the clave MCP integration: who a session is in clave, how it names itself, which token it holds, how a repository is set up and extended (`clave init` once, `clave add` later), and the claim → plan → approval → work → evidence → finish loop every item follows. Use when: the company's COMPANY.md says `task_tool: clave-workflow-manager`, a session starts in such a company, an item is pulled or finished, a Class A step needs approval, a repository or team must be connected to clave, or the clave MCP tools are missing.
- Reads credentials
In this repository132 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- advisory-roadmap-writerSkill
- ai-usecase-prioritiserSkill
- ansible-inventory-reviewSkill
- ansible-playbook-runnerSkill
- api-exploitSkill
- api-reconSkill
- api-surface-analyserSkill
- architecture-thinkingSkill
- backend-doc-writerSkill
- backend-test-writerSkill
- blocker-dependency-trackerSkill
- board-security-updateSkill
- ci-pipeline-implementationSkill
- client-email-writerSkill
- codebase-scannerSkill
- compliance-reviewSkill
- component-implementationSkill
- cost-efficiency-analyserSkill
- cross-team-summary-writerSkill
- crux-coordinatorSkill
- crux-teamSkill
- cyber-risk-executive-briefSkill
- decision-clarifierSkill
- dependency-auditSkill
- deployment-config-reviewSkill
- developer-execution-disciplineSkill
- doc-summariserSkill
- document-requirements-checkSkill
- eligibility-matrix-builderSkill
- engagement-setupSkill
- environment-setup-reviewSkill
- executive-recommendation-writerSkill
- executive-summary-writerSkill
- finding-documentSkill
- follow-up-questionerSkill
- frontend-doc-writerSkill
- frontend-test-writerSkill
- grant-project-writerSkill
- hledger-balance-reportSkill
- hledger-cashflow-reportSkill
- hledger-income-statementSkill
- hledger-journal-writebackSkill
- hledger-ledger-health-checkSkill
- hledger-register-reviewSkill
- hledger-transaction-draftSkill
- incentive-eligibility-checkSkill
- incident-executive-briefSkill
- iso27001-isms-consultingSkill
- jira-workflow-managerSkill
- kubernetes-architecture-analyserSkill
- kubernetes-namespace-auditSkill
- kubernetes-network-policy-applySkill
- kubernetes-storage-healthSkill
- kubernetes-tenant-onboardingSkill
- leadership-style-mapperSkill
- lead-intake-triageSkill
- linux-hardening-reviewSkill
- linux-host-auditSkill
- The first 60 shown.
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.