nklisch/skilltap / plugin/skills/skilltap
skilltap
VerifiedUse skilltap when setting up, inspecting, reconciling, or troubleshooting supported local agent harnesses.
Operate the local agent environment
skilltap is a non-interactive control plane for one person's supported local agent harnesses. It manages explicitly selected resources, shared instructions, native marketplaces/plugins, complete skill directories, and drift between desired and observed state. It does not search, rank, browse, or recommend skills, plugins, or marketplaces.
Start with the user's intent
- First-time setup: first check whether
skilltapis available. If it is missing, explain that the plugin does not bundle an executable and use the verified installer fromhttps://skilltap.dev/install.sh(or Homebrew) only with the user's authorization. After the binary exists, runskilltap bootstrap --help, thenskilltap bootstrap. Treat the binary result and each first-party plugin target result as separate facts; Codex may report an unsupported native plugin-install path. - “What is wrong?” or a health check: run
skilltap status --help, thenskilltap status --jsonwhen structured output is useful. - Existing native resources should become managed: use
skilltap adoptafter reviewing status. Adoption observes and records; it does not push changes. - “What would change?”: run
skilltap planand explain its operations, compatibility, ownership, and next actions before mutating anything. - Apply an accepted plan: run
skilltap sync. Useskilltap harness listto inspect target ids,--target <id>to narrow to one harness,--target allto select every enabled harness, and scope flags to choose global or a project. - Explicit marketplace/plugin/skill lifecycle work: use the matching
marketplace,plugin, orskillcommand family. Instructions useinstructions; automatic safe updates use the optionaldaemon.
Always ask the executable for exact syntax at the point of use:
skilltap --help, skilltap <group> --help, and
skilltap <group> <command> --help are authoritative. Do not copy a full flag
table into this skill.
Scope and safety
Commands are global by default. --project selects the current project,
--project <path> selects another project, and --all-scopes covers global
plus managed projects. Use skilltap harness list for registered target ids;
--target <id> selects one harness and --target all selects every enabled
harness independently of scope. Use --json when passing a stable result to
another agent or script.
Plans disclose partial or destructive consequences. --yes acknowledges a
reported partial foreground operation; it does not bypass invalid input,
missing dependencies, unsupported required components, drift, or native
policy. If output names an operation-scoped consequence or asks for a user
decision, stop and convey that decision instead of inventing a bypass.
The canonical global instruction file is ~/AGENTS.md. skilltap may manage
native Codex/Claude bridges, but existing divergent files, overrides, broken
links, and ownership conflicts are health findings—not permission to overwrite
user content. A skill is its complete directory with a top-level SKILL.md;
never reduce it to that file when references or scripts are present.
For configuration paths and instruction precedence, read configuration and instructions. For interpreting results, updates, daemon behavior, and recovery decisions, read diagnostics.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |