One repeatable gardening pass over a trajectory corpus — the JSONL of per-turn Turn rows a fak trajectory.Recorder exports. Uses the fak traj toolkit (the data plane + the simhash reference vector-similarity primitive + the pluggable scorer seam) to find the trajectories worth a human's attention — near-duplicate queries the lexical ranker misses, cost outliers, and traces the kernel kept refusing — then PROPOSES prune candidates (it never deletes). The reference application of fak's trajectory observability primitives: proof that a trivial skill can build memory/trajectory gardening ON TOP of the defaults, and the starting point you fork to add your own scorers. Use after a recording run, when a memory store has bloated with redundant work, or on a /loop cadence to keep an agent's trajectory memory lean and its bad-query clusters visible.
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategoryGeneralStars0
About this skill
One repeatable gardening pass over a trajectory corpus — the JSONL of per-turn Turn rows a fak trajectory.Recorder exports. Uses the fak traj toolkit (the data plane + the simhash reference vector-similarity primitive + the pluggable scorer seam) to find the trajectories worth a human's attention — near-duplicate queries the lexical ranker misses, cost outliers, and traces the kernel kept refusing — then PROPOSES prune candidates (it never deletes). The reference application of fak's trajectory observability primitives: proof that a trivial skill can build memory/trajectory gardening ON TOP of the defaults, and the starting point you fork to add your own scorers. Use after a recording run, when a memory store has bloated with redundant work, or on a /loop cadence to keep an agent's trajectory memory lean and its bad-query clusters visible.
Quick start
Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
One repeatable gardening pass over a trajectory corpus — the JSONL of per-turn Turn rows a fak trajectory.Recorder exports. Uses the `fak traj` toolkit (the data plane + the simhash reference vector-similarity primitive + the pluggable scorer seam) to find the trajectories worth a human's attention — near-duplicate queries the lexical ranker misses, cost outliers, and traces the kernel kept refusing — then PROPOSES prune candidates (it never deletes). The reference application of fak's trajectory observability primitives: proof that a trivial skill can build memory/trajectory gardening ON TOP of the defaults, and the starting point you fork to add your own scorers. Use after a recording run, when a memory store has bloated with redundant work, or on a /loop cadence to keep an agent's trajectory memory lean and its bad-query clusters visible.
About this listing
Category
General
Reported license
Apache-2.0
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLI