SkillsAdd

Source

ulpi-io/autonomous-engineering

16 skills · 48 combined installs

Skills from this source

#
Skill
Source
8W Activity
Installs
1
adversarial-verify Prove a claim before acting on it: spawn N independent skeptics prompted to REFUTE it (optionally through distinct le…
ulpi-io/autonomous-engineering
3
2
auto-build Implement a whole DAG plan autonomously — one approved pass, one clean rollback point per task, never building on a b…
ulpi-io/autonomous-engineering
3
3
auto-performance Make code measurably faster without breaking it: metric + reproducible baseline FIRST, profile to the real hotspots, …
ulpi-io/autonomous-engineering
3
4
auto-plan Turn a spec into a self-reviewed DAG of atomic build tasks: each task gets acceptance criteria, a disjoint write scop…
ulpi-io/autonomous-engineering
3
5
auto-review Review a change across every dimension at once, then keep only the findings that survive an adversarial check — auton…
ulpi-io/autonomous-engineering
3
6
auto-ship Take verified work to shippable — autonomously, with fail-closed gates and a human sign-off on anything irreversible.…
ulpi-io/autonomous-engineering
3
7
auto-simplify Reduce a change's complexity WITHOUT changing behavior, provably: find duplication/dead code/over-abstraction in the …
ulpi-io/autonomous-engineering
3
8
auto-spec Turn a raw feature request into a grounded, TESTABLE spec — autonomously. It recons the real repo and domain to groun…
ulpi-io/autonomous-engineering
3
9
auto-test Raise test health to a green, MEANINGFUL suite: find untested behaviors, write real tests, loop-until-green — with ev…
ulpi-io/autonomous-engineering
3
10
autonomous-pipeline Run the whole engineering lifecycle end-to-end from one request — spec → plan → build → simplify → test → review → pe…
ulpi-io/autonomous-engineering
3
11
budget-guard The discipline that keeps an autonomous run from becoming a runaway: before any unattended loop or workflow, declare …
ulpi-io/autonomous-engineering
3
12
checkpoint-resume Make long autonomous work durable and resumable: a live .ulpi/runs/<id>.json status file (per-unit + per-phase state,…
ulpi-io/autonomous-engineering
3
13
converge-loop Run a bounded, self-correcting loop that drives code toward a target state and STOPS honestly — until-green (validate…
ulpi-io/autonomous-engineering
3
14
fan-out-work Cover a large work-list in parallel without losing correctness or honesty — scout the items inline, then run each thr…
ulpi-io/autonomous-engineering
3
15
schedule-recurring-agent Stand up a recurring scheduled agent for standing work (triage, monitoring, audits, digests): a self-contained IDEMPO…
ulpi-io/autonomous-engineering
3
16
watch-and-act Wait on an EXTERNAL signal the harness can't notify you about — CI, a deploy, a queue, an endpoint — polling on a cac…
ulpi-io/autonomous-engineering
3