Domains
Forms
Mechanism
Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.
Use when a session exceeds 40 tool calls, the agent contradicts earlier decisions, style/naming drifts, after context compaction, or task scope grows unbounded.
Prevents silent context corruption and convention drift through behavioral self-enforcement; produces checkpoints and handoff docs enabling safe session splits without infrastructure.
Use Cases
A developer lets an agent refactor a large codebase; after 50 tool calls the agent starts using wrong naming. Session Guard enters Yellow Zone, makes the agent recite active rules and checkpoint, then prepares a split. This catches drift early, avoids compounding errors, and keeps the refactor consistent without extra tooling.
An agent hits /compact mid-task and loses early architectural decisions. Session Guard triggers anti-compaction: re-read CLAUDE.md, recite 3-5 critical rules aloud, verify next action matches. The agent resumes correctly instead of guessing, preventing silent violations of project conventions.
Skill Relationships
Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.
Tier 1 · These Skills Use Me
Tier 2 · Current Skill
Tier 3 · I Use These Skills
Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.
Skill File
