SuggestSkills

Discovery is read-only; creation mutates. Keeping the two apart is the permission boundary that makes "never auto-create" real rather than a promise in prose: this skill cannot write a skill even if asked.

1. Frustration is invisible to topic-matching. A topic can be nominally covered by a build/test skill while you keep hitting the same wall inside it. Low ratings and "regressed again" recurrence are the strongest signal a skill is missing. Weight them above raw topic frequency.
2. Discipline gaps hide under covered topics. "App development" maps to a build skill, but the recurring pain may be an unowned discipline (state modeling, error handling, migration safety) that the build skill never addresses. Coverage means the discipline is genuinely handled, not that the topic shares a keyword.

Example 1: routine gap scan

User: "What skills should I build based on my recent work?"
→ Invokes Scan workflow
→ Runs Tools/CollectSignals.ts over the last 45 days
→ Clusters sessions + low ratings, dedups against existing skills/workflows
→ Returns a ranked shortlist with evidence per proposal; nothing is created

Example 2: frustration-led scan

User: "I keep hitting the same wall — am I missing a skill?"
→ Invokes Scan workflow with the frustration store as the lead signal
→ Surfaces discipline gaps hiding under topics that look covered
→ User accepts one proposal → handed to CreateSkill as a separate step

• A clean topic-coverage result with dirty frustration signals is a FALSE negative. If the ratings show recurring frustration in an area you marked covered, re-open it — the discipline under that topic is the gap. (This is the exact failure this skill was built to fix.)
• Recurrence is severity-weighted, not a bare count. Three trivial sessions matter less than one long, painful, repeated migration. A high-severity pain that recurs across a few sessions qualifies even below an arbitrary threshold.
• Behavior is not a skill. "Too verbose", "misread scope", "repeated a reminder" are steering/feedback, not skill gaps. Separate them out and route them to memory/preferences, not to CreateSkill.
• Gathering is deterministic on purpose. If you find yourself grepping stores by hand in the workflow, use the tool instead — hand-gathering makes runs non-reproducible and the eval meaningless.
• Paths are discovered, not assumed. The tool resolves stores via flags/env/root, so it works across installs; do not hardcode a home directory.
• A large work store makes the session list long, not the analysis better. The default 45-day window is the lever — widen it deliberately, and expect the cluster step to carry the cost.