mark393295827/session-learn
Use when a completed work session should yield durable concepts, corrections, decisions, reusable patterns, and a traceable next action.
npx skills add https://github.com/Mark393295827/third-brain-v7-skills --skill session-learn
<skill_contract>
<input>Completed session objective, actions, artifacts, verification receipts, errors, decisions, and destination paths.</input>
<output>Deduplicated durable deltas for concepts, entities, corrections, patterns, ideas, decisions, and gaps.</output>
<done>Each retained delta is formatted, linked, logged, provenance-preserving, and paired with a traceable next action when unresolved.</done>
<non_goals>Automatic-capture claims without a hook, raw transcript storage, conversational filler, or immutable-source edits.</non_goals>
Close a session by extracting only reusable deltas. Invocation must be explicit or performed by a verified external hook; this skill never claims it ran automatically.
Provide: session objective, actions, outputs, verification receipts, errors, decisions, and destination paths. Optional: existing notes for deduplication.
<intake>
Establish the session boundary and compare intended versus observed result. Ignore conversational filler and separate execution evidence from retrospective interpretation.
</intake>
<unknowns_gate>
If the session outcome or evidence is unavailable, return INSUFFICIENT_EVIDENCE. Ask for a missing artifact only when it determines whether a lesson is valid; otherwise preserve it as an unresolved gap.
</unknowns_gate>
<execute>
Scan for seven signal types:
Apply Closure Protocol: Format the smallest durable note, Link it to source/project/concepts, and Log the write plus verification. Merge semantic duplicates; preserve source immutability and provenance.
</execute>
<evaluate>
For each candidate ask: Is it new, reusable, traceable, and decision-relevant? Reject session-specific trivia and unsupported generalizations. Confirm each write exists and links resolve before reporting closure.
</evaluate>
<state_contract>
Persist {run_id, status, attempt, budget, evidence, unknowns, last_error, next_action} plus session id, extracted candidates, accepted/rejected reasons, write paths, links, and closure receipt. Append corrections; do not erase superseded beliefs.
</state_contract>
INSUFFICIENT_EVIDENCE: artifacts cannot establish the lesson; preserve it as a gap.BLOCKED_PERMISSION: the destination is read-only; return the proposed note and path without claiming a write.VERIFY_FAILED: a write or link check fails; repair once or return the exact failure.BUDGET_STOP: rank remaining candidates by reuse value and persist the queue.Return status, result (accepted knowledge deltas), evidence (session receipts and write checks), unknowns, and next_action.
</skill_contract>
Take mark393295827/session-learn from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.