Skip to main content
Exécutez n'importe quel Skill dans Manus
en un clic
Dépôt GitHub

control-tower-plugins

control-tower-plugins contient 18 skills collectées depuis linuxarena, avec une couverture métier par dépôt et des pages de détail sur le site.

skills collectés
18
Stars
0
mis à jour
2026-07-17
Forks
1
Couverture métier
6 catégories métier · 100% classifié
explorateur de dépôts

Skills dans ce dépôt

ship
Développeurs de logiciels

Take a finished change from working diff to a ready-for-review PR, ending with the PR URL as plain text. Use when the user says "ship it" or wants to go from a working change to an opened PR.

2026-07-17
pr
Développeurs de logiciels

Commit the current change, push a branch, and open a draft PR. Use when the user wants to open a PR for finished work.

2026-07-16
control-tower-usage
Développeurs de logiciels

How to drive the `ct` CLI to run matches and produce every number and graph a control experiment ships. Covers `ct run eval`, `ct run monitor`, `ct run summarize`, `ct game-metrics metrics / graph roc / graph pareto`, `ct traj`, and the viewers. Load this when you launch a match, compute safety or usefulness, regenerate a graph, or need the exact reproduce command for an output. White loads it always; main and others load it on demand.

2026-07-08
empirical-ai-research
Développeurs de logiciels

The empirical-research method and quality bar for AI-control experiments run through the ct CLI. Reduce uncertainty fast, iterate on qualitative plus quantitative evidence, size for power, keep splits clean, report honestly, and hold P1 observability, P2 affordance discipline, and the per-team B/R/W/M criteria. Loaded by every role.

2026-07-08
post-writing
Rédacteurs techniques

The public, LessWrong-style writeup of a control experiment. Ruthlessly compressed for a reader with zero context, leading with the surprise, citing public-viewer trajectory URLs only. Load this in the writing phase when producing the shipped post into `outputs/`. It lifts the STRONG-tagged claims from the internal [report-writing]; same evidence base, far less detail. Before shipping it runs the lw-review gate below.

2026-07-08
red-team
Analystes des systèmes informatiques

The red (attacker) role for ONE protocol in an automated control-research run. Load this when you are spawned as red_<protocol>. Holds red's self-managed loop, guarded objective, iteration discipline, and validity rules. Every shared fact (folder layout, iteration mechanics, the stop gate, the game, safety formula, the quality bar, ct commands) lives in a general skill and is referenced here by name, never copied.

2026-07-08
white-team
Analystes des systèmes informatiques

The white (referee) role for ONE protocol in an automated control-research run. Load this when you are spawned as white_<protocol>. Holds white's self-managed loop, guarded objective, task-set ownership, validity disciplines, and per-protocol stopping judgment. Every shared fact (folder layout, iteration mechanics, the stop gate, the game, safety formula, the quality bar, ct commands) lives in a general skill and is referenced here by name, never copied.

2026-07-08
autonomous-execution
Autres occupations informatiques

The discipline that makes a multi-hour control run actually finish instead of stalling or quitting early. It keeps going, get unstuck, fix problems, self-review before you report. Loaded by every agent to keep it going.

2026-07-08
launch-control-research
Analystes des systèmes informatiques

The interactive entry point for an automated control research run, loaded by main. Use when a human says "start an automated control research session" (or similar). Runs the questionnaire, helps write proposal.md, waits for "start", then bootstraps the folder, brings up the dashboard, spawns the team, writes the predicted-results preview into outputs/ while waiting on teammates, and drives the loop.

2026-07-08
protocol-iteration-structure
Analystes des systèmes informatiques

The single home for how a control experiment is organized on disk and how a protocol is iterated to its stopping point. Loaded by blue, red, white, and the judge. Covers the folder layout, one-knob iteration, move order, convergence, the smoke gate, and the per-protocol stopping condition.

2026-07-08
deliver
Développeurs de logiciels

Take a request — a Linear issue or a feature description — all the way to a reviewed, ready PR: triage it, work out the right approach, propose it for a quick OK, implement, then ship. Use when the user wants the agent to plan and build something end to end.

2026-07-08
babysit
Analystes en assurance qualité des logiciels et testeurs

Watch an open PR until it's clean — poll CI, address bot comments, hide each bot comment as it's handled, then mark ready for review. Use when the user wants a draft PR monitored through to green.

2026-07-08
blue-team
Autres occupations informatiques

The blue (defender) role for ONE protocol in an automated control-research run. Load this when you are spawned as blue_<protocol>. Holds blue's self-managed loop, guarded objective, iteration discipline, and validity rules. Every shared fact (folder layout, iteration mechanics, the stop gate, the game, safety formula, the quality bar, ct commands) lives in a general skill and is referenced here by name, never copied.

2026-07-08
control-research-knowledge
Autres occupations informatiques

The domain reference for AI control research, loaded by every role. The blue/red/white game, trusted/untrusted/human, honest vs attack evals, the safety and usefulness metrics, trusted monitoring and the other protocols. The deeper source is https://github.com/linuxarena/control-tower/blob/main/docs/control-concepts.md.

2026-07-08
judge
Autres occupations informatiques

The judge role, an ephemeral read-only subagent main spawns per protocol at phase boundaries and on demand to grade that protocol against its proposal and the shared quality bar. Load this when you are spawned as the judge. Holds the grading procedure, the game-tree-completeness walk, the grade.md format, and the recompute-and-verify disciplines. Shared facts live in the general skills, referenced here by name.

2026-07-08
literature-review
Enseignants postsecondaires, autres

Structured process for a literature review, search strategy, source vetting, and synthesis. Use when asked to review existing work on a control-research topic (prior protocols, attacks, monitors, safety results). Not for incidental background reading during a run.

2026-07-08
report-writing
Autres occupations informatiques

The internal, hypothesis-graded per-protocol report. One report per protocol at `outputs/reports/<protocol>.md`, capturing everything that protocol's team tried and why, qualitatively and quantitatively, with a support tag on every claim and a runs table of every run inside the report so nothing is lost. Load this in the writing phase when synthesizing a protocol's matches into its report. This is the internal tier; the public post is [post-writing].

2026-07-08
trajectory-analysis
Autres occupations informatiques

The trajectory-analysis role, an ephemeral single-invocation subagent any team member spawns to autopsy specific run trajectories against one investigation question. Load this when you are spawned for a trajectory autopsy. Holds the bounded autopsy procedure, the RED FLAGS checks, and the write-into-the-caller's-dir rule. Shared facts live in the general skills, referenced here by name.

2026-07-08