sleepy-panda-srl
OrganizationAn operating framework for agentic engineering: the tailored context, standards, gates and institutional memory a team needs so any coding agent works their way. Open-core by Sleepy Panda SRL.
Categories
Indexed Skills (7)
clarify
Run a bounded clarification pass before planning a full-lane task whose intent is ambiguous or whose acceptance criteria are not yet testable. Use when the ask is underspecified, the constraints conflict, or the criteria can't be written as observable checks — surface the smallest set of decision-questions, get human answers, and fold them into EARS-shaped acceptance criteria before any code is planned.
codify
Turn a just-surfaced mistake or a repeating review comment into a draft rule-change proposal with provenance. Use right after an incident, a postmortem, or a PR review that exposes a recurring failure — the output is a proposal routed to the human/eval gate, never a rule merged on the agent's own authority.
consolidate
Bring a memory store back under its budget by merging, compressing, splitting, and retiring records — the repair a breached memory budget calls for. Use when the index verify recipe reports a breach, or on the librarian's scheduled pass. The output is drafts through the human gate; raising the budget is not one of the moves.
milestone-close
Verify that a milestone's exit criterion was demonstrated rather than asserted, before it is marked done. Use when a milestone is proposed for closing — re-derive each clause independently instead of replaying the sessions that built it, and return CLOSE or REQUEST-CHANGES with a signed fidelity note. Runs in a context that did not implement the milestone, and after the work has merged.
pre-commit
Grade a finished diff before it is committed. Use when full-lane work is complete — re-measure the diff against the criterion it claims to meet, re-run the verify recipes yourself rather than reading the implementer's report of them, and return APPROVE, APPROVE-WITH-ADJUSTMENTS, or REQUEST-CHANGES. Runs in a context that has not seen the work being done.
session-open
Grade a session's plan before any file is written. Use at the start of full-lane work — a plan against the workspace's constitution, its plan or roadmap, and the criterion the session claims to serve. Runs in a context that has not seen the plan being drafted, and returns APPROVE, APPROVE-WITH-ADJUSTMENTS, or REQUEST-CHANGES. Not for triage-lane work.
portulan
Boot the Portulan engine in this repository — load the always-loaded kernel, find and read the team's workspace (identity, principles, gate map, definition of done, repo card), and report what is and is not enforced here. Use at the start of a working session in a repository that has a `.portulan/` workspace, when asked to "boot Portulan", or when you need to know this team's gates, lanes, verify recipes, or definition of done before acting.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.