ccb-clear
The ccb-clear skill executes the `ccb clear` command to reset conversation context for Claude Code Bridge agents without removing project state, configuration, or session data. Use this when a user requests to clear or reset CCB agent contexts via commands like `$ccb-clear`, `$ccb_clear`, or explicit reset requests, targeting all mounted agents or specific named agents as needed.
git clone --depth 1 https://github.com/SeemSeam/claude_codex_bridge /tmp/ccb-clear && cp -r /tmp/ccb-clear/inherit_skills/qoder_skills/ccb-clear ~/.claude/skills/ccb-clearSKILL.md
# CCB Clear Use this skill to clear provider conversation context for mounted CCB agents. In the CCB source checkout, this skill is only for clearing the active work-environment CCB collaboration with the installed release `ccb`. It is not a source validation workflow. For testing current source changes, use `/home/bfly/yunwei/ccb_source/ccb_test` from the dedicated external test project `/home/bfly/yunwei/test_ccb2` instead. Other external test projects require explicit `CCB_TEST_ROOTS` or `CCB_SOURCE_ALLOWED_ROOTS`. Commands: ```bash command ccb clear ``` ```bash command ccb clear "$AGENT" ``` ```bash command ccb clear agent1 agent2 ``` Rules: - `ccb clear` targets all configured mounted agents. - `ccb clear <agent...>` targets only the named agents. - This sends provider-native `/clear` to each target pane. - It does not delete `.ccb` state, workspaces, auth, sessions, logs, or memory files. - Do not use `ccb kill`, `ccb -n`, or restart commands unless the user explicitly asks for process/runtime reset. - After running the command, report the command output. Do not poll or wait.
Send a request to a CCB agent with `ask`.
Submit one node result to the assigned Reviewer and finish only after a bounded pass/rework chain.
Execute one scoped implementation or investigation item and return evidence without changing workflow authority.
Diagnose and recover CCB communication and reply delivery stalls. Use when a user reports a missing CCB_REPLY, stuck ask, agent stuck busy/delivering, queued work behind an active job, cancelled/incomplete reply, empty artifact, callback not continuing, duplicate retry after success, or a CCB mailbox/communication backend that appears stuck.
Compact CCB managed agent conversation context with `ccb compact`. Use when the user writes `$ccb-compact`, `$ccb_compact`, or asks to summarize one or more mounted agent contexts without restarting agents or deleting project state.
Private built-in CCB configuration skill for agentroles.ccb_self. Design, edit, validate, and prepare reloads for .ccb/ccb.config, role bindings, providers, windows, workspaces, tool windows, sidebar, and provider startup inputs. Use only inside ccb_self; non-self agents should delegate CCB config changes to ccb_self.
Diagnose a named CCB agent by combining authoritative runtime and job lineage with deep read-only pane inspection, apply bounded recovery when evidence supports it, verify the result, and request authorization before submitting a redacted GitHub issue. Use for `$ccb_diagnose agentname`, `$ccb-diagnose agentname`, or reports that a CCB agent is stuck, disconnected, not continuing, not replying, or showing provider errors.
Maintain this CCB project's GitHub-facing release and npm publication surface. Use when preparing, publishing, auditing, or fixing CCB releases; updating README.md, README/zh.md, localized README files, CHANGELOG.md, VERSION, package.json, GitHub release notes/assets, repository description/topics, npm registry state, or GitHub Actions release/test status.