x1linwang
- 4 skills
- 0 followers
- 2 hours ago last updated
- ▌ Skill Authoring · x1linwangWrite an agent skill - a SKILL.md with YAML frontmatter - so that it is actually loaded at the right moment. Use this when authoring or editing a SKILL.md, when a skill you wrote is never picked up, when rewriting a skill's description or name so it routes, when deciding what belongs in written instructions versus a deterministic tool, and when a SKILL.md has grown long enough to split into a body plus references. Covers YAML frontmatter, progressive disclosure, why the description is the routing mechanism, and how to test that a skill triggers. This is about writing skills - it is NOT for a Langflow Agent component that will not call a connected tool.
- ▌ Langflow Env Doctor · x1linwang bundleDiagnose a broken local Langflow course setup on macOS or Windows - Docker, docker compose, .env, the container, port 7860, or a component that will not load. Use this whenever `docker` is not found, the daemon will not respond, `docker compose up` hangs or exits, the container never reaches (healthy), localhost:7860 refuses to connect or shows an error page, or a pull or build stalls with no progress. Covers these literal errors: "docker-credential-desktop: executable file not found in $PATH", a bare "EOF" from the daemon, and "port is already allocated". Also use it as a first step before debugging anything else about a local Langflow, and after a fresh clone to check the setup is complete.
- ▌ Langflow Flow Debug · x1linwangDebug a Langflow 1.11.x flow that runs without erroring but produces the wrong result or nothing at all, and run a flow from the command line instead of the Playground. Use this when a Chat Output is empty, a node appears not to have run, an If-Else takes the wrong branch or both outputs look blank, a Prompt Template has grown input fields you did not add, an Agent ignores a tool that is clearly connected, or an API call to /api/v1/run returns 403, gzip garbage, or a partial result. Also use it to pick the right auth scheme for a Langflow API call, since two different schemes apply to different routes.
- ▌ Langflow Component Build · x1linwangWrite a custom Python component for a local Langflow 1.11.x deployment, or add an action to one you were given, and get it to actually appear in the component menu and be callable by an Agent. Use this whenever a component does not show up in the sidebar, shows up but has no inputs, loads but the Agent never calls its tool, or the Agent calls the wrong action of the right tool; and whenever adding a method, renaming a method, editing an Output(info=...) string, adding a tool_mode input, or setting up a category folder under custom_components/. Also use it before running tests/verify_components.py or restarting the container after a Python edit. Four of the failure modes here are silent - no error, no traceback, just a component that is missing or an Agent that answers from memory.