All authors
Claude Skills by goondocks-co
github.com/goondocks-co15 skills0 installs10 views
- Building Myco DisciplineThis skill should be used before building any non-trivial change in Myco — a new feature, a refactor, capability work, anything touching shared state, or anything crossing module boundaries. Triggers on "add a feature", "refactor this", "this touches shared state", and on requests framed as "just a small change". Covers capability-first architecture for shared state, structural over procedural invariants, live smoke-test rigor, code review as a normal step, and the "what was this defending ag...Votes: 0GitHub stars: 14
- Debug CaptureThis skill should be used when the user reports that capture went silent: "that session isn’t in the dashboard", "I sent that but it didn’t save", "the session shows zero batches", "MCP tool calls hang", "hooks aren’t firing in this worktree", "the buffer file isn’t growing", or FK constraint errors in the daemon log. Walks the capture lifecycle top-down — agent → hook → daemon HTTP → buffer → registry → SQLite → transcript miner — naming which layer to inspect, in what order, with the comman...Votes: 0GitHub stars: 14
- Dogfood WorktreeThis skill should be used when the user asks to "dogfood this change", "test this in a worktree", "why is the worktree using the production binary", or when capture, MCP, or the CLI in a git worktree behaves like production instead of the worktree build. Covers `make dev-link-worktree` / `make dev-unlink-worktree`, why `.myco/runtime.command` does not travel with `git worktree add`, why a build must happen first, the direct-CLI `MYCO_HOME` trap, the shared-vault schema rollup hazard across wo...Votes: 0GitHub stars: 14
- Playwright CliAutomate browser interactions, test web pages and work with Playwright tests.Votes: 0GitHub stars: 14
- Safe Config UpdatesThis skill should be used when the user asks to "add a setting", "add a field to the settings page", "change myco.yaml", or when any code path writes configuration — a React settings form, a CLI command, a task, or a daemon reaction. Covers the two invariants that prevent silent config loss (every YAML write flows through `updateConfig()`; every `formToConfig()` spreads the original config before overlaying form values) and the full procedure for adding a scoped setting across the machine/gro...Votes: 0GitHub stars: 14
- Write Myco SkillCreate and validate a Myco-managed SKILL.md file using vault_write_skill. Use when authoring a new skill from scratch, updating an existing skill, or fixing a skill that failed the quality gate. Applies whenever you need to produce a valid .agents/skills/<name>/SKILL.md file that passes structural validation. Also load when vault_write_skill returns a rejection error — the error message identifies the failing constraint, but this skill explains the full field contract and the known contaminat...Votes: 0GitHub stars: 14
- Myco HandoffCarry a session's working intention to another session or another agent. PREPARE compresses why we are here, what we are doing, the gotchas, the dead ends and the decisions already closed into a digest of at most 1500 tokens, saved on a Myco plan. RECEIVE takes that plan id, rehydrates the context, marks the referenced plans in progress, loads the suggested skills and resumes the work.Votes: 0GitHub stars: 14
- Myco OkfCreate or maintain an OKF-conformant project wiki — a portable, git-committed markdown knowledge base that lives in the repository rather than in Myco. Turns what Myco holds, the spores and sessions and plans, into human-readable documentation that ships with the code. Any agent can run the procedure; it needs nothing beyond the ordinary Myco tools.Votes: 0GitHub stars: 14
- Myco Outcome TasksAuthor and debug the tasks Myco's own agent runs. A task is one prompt with declared expected evidence, dispatched to a worker: no phases, no turn budget, no orchestrator. It declares the gate that admits it, the tools its run may call, its schedule if it has one, and how the server decides afterwards that it actually did the work. Getting those four declarations consistent is the whole job.Votes: 0GitHub stars: 14
- Myco RulesKeep AGENTS.md minimal, durable and canonical across every agent that reads it. Adds, trims and audits project rules without letting the rules file decay into a dump of whatever was true last week.Votes: 0GitHub stars: 14
- Myco Server DebuggingWork out why a Myco deployment refused something, lost something, or stopped doing something. The server answers a caller's own fault as a terminal refusal carrying a named code, and its own faults as a retryable failure — telling those two apart is the first move in every investigation, because only one of them is worth retrying and only one of them is your bug.Votes: 0GitHub stars: 14
- Myco Server ProvisioningProvision, update, roll back and destroy the Cloudflare Deployment — the Worker front door — with `myco server <verb> --target cloudflare`. One verb, from artifacts the binary carries: no source checkout on the machine that deploys, and no container runtime anywhere.Votes: 0GitHub stars: 14
- Myco SettingsChange a Myco deployment's settings safely, and add a new setting correctly. Deployment settings are one tier with one writer: every change admits the leaf, authorizes the actor, checks the leaf's own rule, persists it with its actor, and re-arms whatever schedule it moved — in that order, in one module. Bypassing that path is how one of those five steps quietly goes missing.Votes: 0GitHub stars: 14
- Myco SetupFinish setting Myco up on this machine. The plugin alone gives you skills and the Myco tools; the binary adds session capture, plan capture, import and the worker. This skill checks what is present, installs the binary with the user's consent, signs in or redeems a join code, wires the agent's hooks and verifies the result — and names the outcome plainly when an install cannot proceed.Votes: 0GitHub stars: 14
- MycoMyco is this project's memory — the sessions that happened, the durable observations (spores) drawn from them, and the plans. It holds why the code is the way it is, which the code itself cannot show. Use it before a design decision, when debugging something non-obvious, when a structure looks arbitrary, when picking up work someone else started, and after learning something worth keeping.Votes: 0GitHub stars: 14