Staff Platform/SRE @ Shield AI. I make AI reliable enough to put to work.
Bo, a Staff Platform/SRE engineer at Shield AI, publishes agent skills covering memory curation, planning and scoping changes, behavior-preserving refactors, brainstorming and stress-testing ideas, building and auditing SKILL.md packages, and independent validation of work against acceptance criteria. Their catalog stands out for its focus on reliability: several skills enforce evidence limits, reversible decisions and before-and-after proof, alongside a test fixture for auditing skills.
Agentops
36 skills · 452 stars · Apache-2.0
Agent Native Dispatch independent tasks to parallel workers or subagents without write collisions.
Agy Native Run a supplied task in headless AGY (Antigravity, Gemini) and collect its result.
Bad Skill Lint test fixture for scripts/skill-eval.sh: a SKILL.md with missing name and id front matter, an em
Claude Exec Run one prompt through headless Claude with scoped permissions and a time bound.
Codex Exec Run one prompt through headless Codex and capture the result.
Council Compare independent opinions from several models or contexts without inflating agreement.
Craft Goal Draft or lint a bounded long-running goal prompt with a finish line and hard limits.
Doc Write or update READMEs, docs, repo instructions and handoff notes, checked against source.
Domain Settle what domain terms mean per context, and which repository conventions or language standards…
Good Skill A planted fixture that satisfies every blocking skill-eval rule so the gate passes cleanly.
Idea Genie Brainstorm evidence-backed options for what to build, or stress-test an idea.
Implement Change or repair code, config or services without weakening tests; report what ran and what did not.
Implement Execute one bounded RED to GREEN experiment from bead or caller intent; return derived subject id…
Interview Interview you one question at a time, each with a recommendation, to settle a big outcome before…
Known Bad A test fixture that intentionally fails Pass-2 checks.
Known Good Test fixture skill that satisfies all 15 auditor checks (Pass 1 + Pass 2).
Navigate Pick the next work in an epic or bead graph; closed is not proven.
Orchestrate Coordinate several workers: what idle agents do next, which finished work gets checked first, how…
Plan Shape a request into one end-to-end slice with observable behavior; review write scope and revers…
Postmortem Explain why a change, incident or session went as it did, separating proven causes from coincidence.
Premortem Find how a rollout plan could fail before committing to it.
Reality Check Audit claims that work is done or shipped against the diff or repo.
Refactor Restructure or clean up code with no behavior change, proved by before-and-after checks.
Research Answer one cited question: how code works, or whether a repeated pattern deserves a rule.
Reverse Engineer Tear down a competitor''s repo or product into a feature inventory and adoption choices.
Review Give advisory feedback on a plan, design or code change.
Rpi Drive one accepted change through implementation and checks to done, with one fresh review only w…
Save and curate agent memory: lessons, rules and evidence limits Record reviewed lessons and agent rules with evidence, limits and invalidation.
Security Review code for security problems; scan for vulnerabilities, secrets, dependency and prompt risks.
Skill Builder Create, repair, audit or consolidate agent skills (SKILL.md packages).
Skill Eval Measure whether a skill helps by comparing runs with and without it.
Test Write or assess tests that prove behavior and would fail without the fix.
Using Gc Operate Gas City through its own doors: Mayor, doctor and native run state.
Using Gc Operate a caller-selected Gas City 1.4 with upstream registry packs and native run-centered surfa…
Validate Freshly judge exact subject content against bead or caller acceptance, optionally persist verdict…
Validate Freshly judge whether a finished change and its claims meet original acceptance: PASS, FAIL or NO…