learning-harvest
FeaturedManage the operational learnings lifecycle — load prior learnings to inform current work, harvest new patterns worth preserving, and keep the document tight over time. Provides a protocol for accumulating actionable patterns from practice that complement standards and defaults. Use when a workflow session completes and produced insights worth persisting, when starting a session that should benefit from prior patterns, or when the user says 'harvest learnings', 'what have we learned', 'capture this pattern', 'tighten learnings', 'compress learnings', or 'operational learnings'.
Install
Quality Score: 88/100
Skill Content
Details
- Author
- techygarg
- Repository
- techygarg/lattice
- Created
- 6 months ago
- Last Updated
- 4 days ago
- Language
- JavaScript
- License
- MIT
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
resolve-issue-learnings
Harvest the generic, cross-repo learnings that resolve-issue captured during its runs and turn the real ones into honored conventions — verifying each candidate against the current resolve-issue skill as ground truth, then writing the survivors to a user-global conventions file that resolve-issue reads on its next run, or proposing them as edits to its own SKILL.md when invoked inside the editable plugin source. Use whenever someone wants to distil / harvest / review / apply the learnings resolve-issue has accumulated. Do NOT trigger to RUN the issue-to-PR pipeline (that is resolve-issue) or to watch a run (resolve-issue-dashboard); this skill neither drives a run nor reads a single run's state.md — it processes the accumulated learning store. Trigger phrases: "harvest resolve-issue learnings", "distil the resolve-issue runs", "update my resolve-issue conventions", "apply what resolve-issue learned", "/resolve-issue-learnings".
harvest-session-learnings
Scan the current working session and the active task's artifacts for reusable, generalizable lessons (what was tried, what failed and why, what surprised us, what the next task should do differently) and propose anchored entries to append to the task's LEARNINGS.md, the produce-side counterpart to the ADR-0017 consume path that task-init already reads. Append-only and read-only on existing entries; de-duplicates against what is already captured; keeps durable lessons and drops one-off task trivia. Use on demand mid-task after a hard-won fix or a surprising failure, or at closure to sweep a long session before the context is lost. Do not use to rewrite or prune existing learnings (never edit prior entries), to capture a single in-flight observation (use capture-observation), to close a slice or the task (use slice-closure or task-close), or when nothing durable was learned (return a NO_OP rather than manufacturing a lesson).
insight-harvester
Mines raw session learnings and /insights output into evidenced friction patterns and concrete config-diff proposals. Used by /vulyk-evolve. Trigger when asked to analyze learnings, find friction patterns, or prepare an evolution changeset.