القائمة
Recall all feedback, corrections, and constraints from the current conversation before rewriting or iterating. Triggers on: reflect, step back, reconsider, recall feedback, what did I say, incorporate all feedback, or when iterative drafts keep missing the mark.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Gotchas for the agents-cli headless release. The macOS home base signs, notarizes, and npm-publishes over SSH with no GUI and no Touch ID — three things must be primed or the release stalls. Triggers on: release stuck at sign/publish, errSecInternalComponent, "no npmjs.com bundle", "Missing embedded.provisionprofile", making the release autonomous.
Search, browse, and read agent conversation transcripts across Claude, Codex, Gemini, and OpenCode. Use this skill to find previous sessions, recover context, or inspect what agents have done.
Organize AI coding agents into teams that collaborate on a shared task. Create teams, add teammates, start them, monitor progress, and collect results. Use this skill when you need parallel agent execution. For single-agent dispatch, use `agents run` instead.
Use FIRST for any question about THIS codebase's structure, symbols, or relationships — where a function/class/file is defined, what calls or imports it, what breaks if you change it, how two parts connect, or to load focused source context before editing or reviewing. Routes to the cgraph MCP tools (graph_query / graph_explain / graph_impact / graph_path / graph_context), which serve ranked file:line results, node neighborhoods, transitive blast radius, and token-budgeted source bundles from a resident per-project graph daemon in ~10ms — far cheaper than grepping and reading files. Prefer over blind grep/read for code navigation, dependency tracing, and impact analysis.
Register and connect to your machines over Tailscale SSH with agents-cli. Use this skill to sync devices from the tailnet, list them, open a shell on another machine, or see agent sessions running across your whole fleet.
Schedule agents to run on a cron schedule or one-shot at a specific time. The scheduler auto-starts on first add. Triggers on: 'schedule an agent', 'recurring job', 'cron', 'daily', 'every weekday', 'run at 2pm'.
| name | reflect |
| description | Recall all feedback, corrections, and constraints from the current conversation before rewriting or iterating. Triggers on: reflect, step back, reconsider, recall feedback, what did I say, incorporate all feedback, or when iterative drafts keep missing the mark. |
| argument-hint | [optional: specific topic to reflect on] |
| user-invocable | true |
You are mid-conversation. The user has given you feedback — corrections, preferences, pushback, confirmations. Before your next attempt, you must surface all of it.
Scan the entire conversation. Extract every instance where the user:
Present these as a numbered list. Quote the user's words where possible — don't paraphrase into something softer.
Format:
FEEDBACK INVENTORY:
1. [REJECTED] "the first hook isn't really useful — it sounds like scrolls dropping"
→ Thesis statements don't hook. Lead with something concrete/surprising.
2. [CORRECTED] "an agent run by cron can do push notifications to ask for permissions"
→ "Autonomous = unreachable" is wrong. The real issue is latency tolerance, not absence.
3. [CONFIRMED] The per-binary network policy detail — user flagged this as the most interesting finding early on.
→ This should be the anchor, not supporting detail.
4. [CONSTRAINT] Don't sell Rush. No product pitch.
→ Can reference contextually but not promote.
5. ...
After listing, ask: what's the thread connecting these corrections? Usually the user is pushing toward one thing you keep missing. Name it explicitly.
Example: "The thread: I keep leading with framing and structure instead of a single concrete thing that's genuinely surprising."
Before writing anything new, state in 1-2 sentences what you'll do differently this time, grounded in the feedback inventory.
Now write the next draft/response with all constraints active simultaneously. Not just the latest correction — all of them.
Creative iteration fails when the agent treats each correction as a local patch. Feedback is cumulative — correction #5 doesn't replace corrections #1-4. But without explicit recall, agents drift: they fix the latest issue and regress on earlier ones.
This skill forces global constraint satisfaction before each attempt.