Skip to main content
aberson
Profil créateur GitHub

aberson

Vue par dépôt de 56 skills collectés dans 3 dépôts GitHub.

skills collectés
56
dépôts
3
mis à jour
14 août 2026
explorateur de dépôts

Dépôts et skills représentatifs

mesh-probe-alpha
non classé

Read exact lifecycle markers from this disposable plugin's shared reference. Use when a request contains the unique trigger {{TRIGGER_ALPHA}}.

14 août 2026
mesh-probe-beta
non classé

Read exact lifecycle markers from this disposable plugin's shared reference and helper asset. Use when a request contains the unique trigger {{TRIGGER_BETA}}.

14 août 2026
skill-eval-setup
Développeurs de logiciels

Auto-generate an evaluation framework (evals.json + test_scenarios.json) for any skill by reading its SKILL.md, then output a ready-to-paste self-improvement loop prompt. Use as "/skill-eval-setup <skill-name-or-path>".

10 août 2026
skill-iterate
Développeurs de logiciels

Serial-iterate every scorable skill autonomously overnight via hill-climb. Default invocation drains all .claude/skills/*/evals-bearing skills (minus an embedded skip-list); per-skill budget capped by 1h wall-clock OR 12 iterations, whichever first. Carries…

10 août 2026
repo-sync
Développeurs de logiciels

Sync GitHub issues to match a plan's structure (umbrellas + step issues), with rich bodies optimized for fresh-context LLM work. Detects letter-named phases, sub-phase notation, table-row step formats. Use after plan changes or to bring issue bodies up to…

5 août 2026
plan-expedite
Autres occupations informatiques

Chain plan-review-autofix, plan-wrap-autofix, repo-sync, and task-handoff into one autonomous prep step before /build-phase. Required arg --plan <path>. Default continues in-window — emits a /goal + /build-phase command pair (the /goal arms the Stop hook over…

16 juil. 2026
session-wrap
Autres occupations informatiques

The session-transition front door. Bare invocation TRIAGES the session — context utilization, task-boundary state from current.md, git state, armed /goal — announces one route, then ACTS: continue (checkpoint + one line), clear-next (durable state to disk,…

16 juil. 2026
goblin-do
Autres occupations informatiques

The single front door for a chosen goblin atom. Mode-dispatches a resolved suggestion or UAT task — a `small` suggestion or a safe `uat` task is EXECUTED via /build-step (auto-ship a genuinely-clean result, park the rest with a one-line --land to ship later);…

15 juil. 2026
Affichage de 8 skills collectés sur 48.
improve-bot-evolve
Développeurs de logiciels

Autonomous generation-phase improvement loop. Generates a pool of Claude-proposed improvements, fitness-tests each vs the current parent, stacks the winners onto a new snapshot (with an import-check gate), and regression-checks against the prior parent —…

6 juil. 2026
improve-bot-advised
Développeurs de logiciels

Autonomous advisor-driven improvement loop. Runs games, reviews replays with Claude strategic analysis against Protoss guiding principles, prioritizes improvements, and executes them via /improve-bot — repeating for hours to iteratively strengthen the bot.…

20 juin 2026
improve-bot
Développeurs de logiciels

Run a long autonomous session to improve the Alpha4Gate bot's performance along a measurable axis. Supports demo (no mutations), training-only soak runs (learning self-improvement via the daemon), plan-based dev work, and (with --self-improve-code) fully…

30 mai 2026
a4g-dashboard-check
Analystes en assurance qualité des logiciels et testeurs

Screenshot every Alpha4Gate dashboard tab using Playwright and review for issues. Detects system state (fresh start, SC2 running, advised run active) and adapts review criteria accordingly. Invoke as "/a4g-dashboard-check".

30 mai 2026
a4g-ui-test
Analystes en assurance qualité des logiciels et testeurs

Alpha4Gate wrapper for ui-review-loop. Starts bot + API + frontend, drives the command panel via Playwright, runs three reviewers. Invoke as "/a4g-ui-test --problem '...'".

30 mai 2026
improve-bot-triage
Développeurs de logiciels

Triage the findings from the most recent /improve-bot run log into a pickable list, classify each finding by action-type, and emit a ready-to-run /improve-bot invocation for the picked item. Use between /improve-bot runs to decide what to target next without…

30 mai 2026
3 dépôts affichés sur 3
Tous les dépôts sont affichés