chameleon-doctor
Use when the user explicitly invokes /chameleon-doctor to get a triage report on their chameleon installation health
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Use when the user explicitly invokes /chameleon-doctor to get a triage report on their chameleon installation health
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when the user explicitly invokes /chameleon-pr-review to review a PR or branch diff against the repo's chameleon conventions, principles, and task requirements. Reports convention violations + logic gaps.
Use when the user explicitly invokes /chameleon-journey to run the comprehensive real-world journey harness against the chameleon plugin
Use when the user explicitly invokes /chameleon-init to bootstrap a chameleon profile for the current repository (TypeScript/JavaScript, Ruby, or Python — framework-agnostic, with deeper awareness for Rails and Django/DRF/Flask/FastAPI)
Use when the user explicitly invokes /chameleon-refresh to re-analyze the current repo and update the chameleon profile after drift
Use when the user explicitly invokes /chameleon-receiving-code-review to handle a code review the team left on their PR — verify each comment against the code and the repo's chameleon conventions, decide apply-or-push-back, draft replies, and implement approved fixes one at a time.
Use when the user explicitly invokes /chameleon-deep-work <task> to execute a substantive coding task end to end: dig the code and external unknowns first (no clarifying questions — parallel expert subagents work independent unknowns), present a 100%-understanding brief, then implement and verify in an isolated git worktree under chameleon's per-edit guardrails.
| name | chameleon-doctor |
| description | Use when the user explicitly invokes /chameleon-doctor to get a triage report on their chameleon installation health |
Run the chameleon-mcp doctor action (via the chameleon_telemetry dispatcher). It returns a structured envelope:
overall: ok | warn | errorchecks: a list of subsystem checks (python version, hook_interpreter_deps (a dep-capable Python >= 3.11 resolves for the hooks — when this errors, hook enforcement and guidance are OFF), mcp_server_launcher (uvx resolves so the bundled MCP server can launch — when this errors, the MCP tools like /chameleon-init/refresh/status are unavailable), bash on PATH, timeout(1) on PATH, plugin data writable, hook scripts present and executable, HMAC key sane, daemon liveness, recent hook errors, per-repo profile/trust state, config_json validation, production_ref resolvability when a lock is set, linter_config (rules.json carries no linter-config parse warnings — a degraded linter config is loud, not silent), plus four dead-install detectors for the current repo: profile_artifacts (generated artifacts exist and parse), judge_spawn_health (turn-end reviewer spawns are not all failing), advisory_emission (trusted edits actually resolve archetypes), advisory_suppressed (edits are not injecting nothing because the profile is untrusted here — run /chameleon-trust))summary: countsmcp__plugin_chameleon_chameleon-mcp__chameleon_telemetry with action="doctor" (no params).overall is ok: confirm the install is healthy.overall is warn: surface the warn-status checks as informational, note that they typically don't block operation.
profile_artifacts warn: a generated artifact is missing or corrupt; suggest /chameleon-refresh to regenerate.linter_config warn: rules.json records a linter/formatter config parse warning (part of the config could not be read — torn TOML/YAML or a broken symlink), so some or all of its conventions are missing; a tolerant parse still records what it salvaged. Fix the config, then force a full re-derive (refresh_repo with force: true, or /chameleon-init) — a noop or partial refresh never re-reads linter configs.judge_spawn_health warn: every recent correctness-judge spawn failed; the turn-end review layer is dead. Check the claude binary and auth.advisory_emission warn: trusted edits are not resolving archetypes, so per-edit advisories are silent; suggest /chameleon-refresh then /chameleon-status.overall is error: call out each error-status check as a blocker and suggest the relevant fix:
python_version error: upgrade Python to >= 3.11.hook_interpreter_deps error: no dep-capable Python >= 3.11 resolves for the hooks, so hook enforcement and guidance are OFF — the single most consequential failure. Install/point to a Python >= 3.11 (or uv); the detail names what was found.mcp_server_launcher error: neither uvx nor uv is on PATH, so the bundled MCP server cannot launch and every MCP tool (/chameleon-init, refresh, status, and the codebase queries) is dead even if the hooks resolve a Python. Install uv (which provides uvx): https://docs.astral.sh/uv/getting-started/installation/.bash_on_path error: install bash or ensure it is on $PATH for the hooks to work.plugin_data_writable error: check directory permissions for the chameleon data dir shown in detail.config_json error: .chameleon/config.json is present but malformed (invalid/unsafe JSON); detail carries the parse error. Every config.json feature (production_ref lock, auto_refresh, trust auto-preserve) falls back to its built-in default until the file is fixed — correct the JSON or delete the file to reset to defaults.hook_* error: re-install the plugin or run chmod +x on the listed hook script.data for copy-paste when filing a bug.data. Never claim a check passed that did not run, and never hide a degraded state behind a green summary.chameleon_version and platform info from data; don't paraphrase or guess them.