jawadsajjad503/workbuddy-skill/integration-health-check
Claude Code and agent skill by jawadsajjad503/workbuddy-skill
- community
Checking that the SKILL.md file is still in the repository.
Use first when an integration context is ambiguous or a user needs to verify connection, credentials, accessible organizations, projects, or capabilities before taking an action.
Install
npx vskill@latest install jawadsajjad503/workbuddy-skill/integration-health-checkSKILL.md
The same SKILL.md was published earlier as sandbaseai/workbuddy-skill/integration-health-check.
Integration Health Check
Run this check before integration-specific work whenever the connector, identity, organization, project, environment, or capability is unknown. Establish context with the least-privileged read-only status operation first. Do not guess a target, reuse an unverified identifier, expose credentials, or perform a write merely to discover whether the connection works.
Confirm connection and identity
- Identify the intended integration and the operation the user ultimately wants.
- Call the connector's health, status, or equivalent read-only capability before project-specific operations.
- Verify connection state, credential validity, identity, token scopes, expiration or rotation signals, and any organization or project access returned.
- Treat a successful transport response as insufficient: distinguish authenticated, authorized, partially available, degraded, and unknown states.
Never print tokens, cookies, private keys, or full sensitive headers. Redact secrets and personal data from logs and summaries. If credentials are absent, expired, or over-privileged, explain the smallest safe remediation and stop before attempting a write.
Resolve the target context
Extract the available organizations, workspaces, projects, tenants, environments, modules, and capabilities. Match the user's words to stable identifiers using exact names and documented ownership; do not silently select the first result. Check whether the requested operation is supported in the selected context and whether its permission level is sufficient.
If exactly one authorized target matches, state the selected target and continue. If several match, ask the user to choose using concise, non-sensitive names and identifiers. If none match, report the verified scope, likely permission or naming issue, and the next read-only diagnostic. Do not probe unauthorized targets.
Continue safely
Carry the verified target identifier forward to subsequent calls instead of rediscovering or accepting an untrusted identifier from free text. Re-check health after authentication changes, connector errors, scope changes, or a long pause. Bound requests, respect rate limits, and keep reads and writes explicit. For consequential actions, summarize target, intended side effect, and available rollback before execution.
Record the connector, check time, identity class, selected organization/project/environment, capabilities, status, limitations, and next action. Report only the minimum evidence needed to make the context reproducible. A health check proves current connectivity and returned access; it does not prove that every downstream API, dataset, or write path is available.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/integration-health-check/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/jawadsajjad503/workbuddy-skill/integration-health-check)