ecorkran
- 12 skills
- 0 followers
- 5 hours ago last updated
- ▌ Sq Summary · ecorkranGenerates a clipboard summary of the current conversation for a manual context reset, or restores a previously saved summary back into context with --restore. Use when the user asks to summarize the session, save context before a reset, or restore earlier context.
- ▌ Sq Analysis · ecorkranRuns an analysis skill from the squadron analysis pack, such as a tech debt audit or codebase understanding from an understand-anything knowledge graph. Use when the user asks for a codebase audit, architecture review, code quality assessment, or codebase understanding through squadron's analysis pack.
- ▌ Sq Benchmark · ecorkranBuilds and inspects the model benchmark's fix cases and reports how many a project yields. Qualifies a repository's closing commits as fix cases in sandboxes, shows why a commit qualified or was rejected, and says whether the qualified cases can separate two model configs. Use when the user asks how many fix cases a project gives, why a fix commit was rejected, or wants the benchmark yield report.
- ▌ Analysis Understand · ecorkranConsumes an existing understand-anything knowledge graph and writes squadron planning documents from it. Reads the graph the plugin already produced — it does not analyze the codebase itself and does not run the plugin. Use when the user asks for a codebase comprehension analysis derived from an existing knowledge graph. Does not auto-invoke.
- ▌ Sq Auth · ecorkranShows squadron's credential and profile status for each provider. Use when the user asks whether their API keys or provider credentials are configured, or asks about auth status.
- ▌ Sq Task · ecorkranSends a one-shot task to a named squadron agent. Use when the user wants to give an already-running agent a prompt to work on.
- ▌ Sq Replay · ecorkranCompares producer model configs on a past slice by regenerating its design or task breakdown in a sandbox under each config, judging the first drafts pairwise, and reporting quality, cost, time and failure rate. Use when the user asks which model or effort writes the best slice designs or task breakdowns, wants to replay a slice under different models, or wants the replay report.
- ▌ Sq Review · ecorkranRuns a squadron review — code, slice design, task plan, architecture, pull request, or a resolve check on whether an earlier review's findings were addressed. Use when the user asks for any of these to be reviewed, or asks whether review findings were handled.
- ▌ Sq Monitor · ecorkranWatches a running squadron pipeline until it stops, evaluates its reviews, fixes the findings that are valid and important, drops the rest with a reason, and saves a session summary. Use when the user says a pipeline is running and asks to monitor it, wait for it, or evaluate and respond to its findings.
- ▌ Sq Onboard · ecorkranAdopts an existing codebase into squadron and Context Forge one step at a time, driven by `sq onboard`. Use when the user asks to onboard, adopt or bring an existing (brownfield) project under squadron and Context Forge.
- ▌ Sq Pr · ecorkranResolves and reports a pull request, or opens one from the current branch with a description assembled from the branch's own artifacts. Use when the user asks to show, check, or create a PR through squadron.
- ▌ Sq Run · ecorkranRuns a squadron pipeline step by step via the prompt-only executor, driving cf operations, dispatches, reviews, checkpoints and commits. Use when the user asks to run a pipeline such as slice, design or tasks.