reflect

# Reflect Mine the current conversation for durable learnings, then route them into skill edits. Invoke when the user says "reflect" or "/reflect". Skip when the conversation is trivial, off-topic, or already covered by an existing skill the parent followed correctly. One-offs are not learnings. ## 1. Gather the active conversation Use the active conversation already in context. When `session_store_sql` is available, query only the current session ID and the time range needed for this task. Do not search unrelated sessions. If the current session cannot be queried, write a tight digest from the visible conversation and pass that instead. ## 2. Spawn three reviewers in parallel One message, three `Task` calls with `agent_type: "general-purpose"`. Set `model` from the role line in `instructions/pstack-models.instructions.md` in Copilot home. If the configuration or the line is missing, or the value is `auto` or `inherit-parent`, omit `model`. If the Task tool rejects a slug, omit `model` and say so. Each prompt forbids file writes; the parent applies edits. | Lens | `model` | Prompt template | |---|---|---| | Judgment | configured reflect-judgment model or Task default | `references/judgment-reviewer.md` | | Tooling | configured reflect-tooling model or Task default | `references/tooling-reviewer.md` | | Divergent | configured reflect-judgment model or Task default | `references/divergent-reviewer.md` | Pass each template verbatim, substituting the scoped conversation digest where marked. Use a transcript reference only when the current Copilot host explicitly provides one. Reviewers return findings in the `Task` response body. ## 3. Synthesize One `Task` call with `agent_type: "general-purpose"` and the configured reflect-judgment model. Omit `model` when the configuration or role line is missing, or the value is `auto` or `inherit-parent`, and let Copilot choose the agent's default. If the Task tool rejects that configured slug before starting the synthesizer, retry the same read-only brief once without `model` and report the fallback. Keep the completed reviewer outputs; do not repeat their reviews or guess a substitute model. Surface any other error rather than treating it as a model rejection. The prompt forbids file writes but allows available integrations for citation checks. Use `references/synthesizer.md` verbatim, with each reviewer's full output inlined where marked. The synthesizer returns a structured Accepted / Rejected / Backlog list. ## 4. Structural enforcement check Move any Accepted item that a lint rule, script, metadata flag, or runtime check would enforce more reliably to Backlog. See the **encode-lessons-in-structure** principle skill. ## 5. Apply Present the synthesizer's full Accepted / Rejected / Backlog output and wait for explicit approval before applying any Accepted edit. The user picks the subset and may redirect routings. Skill changes affect every future agent in the org. Do not auto-apply. File Backlog items to the team's devex tracker only within existing external-write authorization; otherwise leave them as proposals. Include `- Generated with AI 🤖` once at the end of agent-authored text submitted to an external system. Never edit an installed plugin cache. Before approval, show the proposed writable destination under the project's `.github/skills/<skill>/` or the user's Copilot home `skills/<skill>/`. After approval, copy the skill folder there and edit the copy, preserving its license and attribution. Do not open a PR or push as part of this reflection. Follow each approved row's Routing exactly: - Trivial existing-skill edit (a one-line bullet, a tightened sentence, a stale fact corrected): the parent does it directly. - Substantive existing-skill edit (a new section, a new pattern table, more than ~10 lines): follow the poteto-mode Authoring a skill playbook and run focused task or trigger evals when an eval harness is available. - `tune description: <skill path>` (the skill exists but did not trigger when it should have): add realistic positive and negative trigger cases, then tighten the description against them. - `new skill via authoring playbook: <kebab-name>`: follow the Authoring a skill playbook. Do not invent the shape ad hoc. If your environment ships a SKILL.md validator, run it on every touched skill before declaring done. ## 6. Summarize for the user Short list, no preamble: - Edits applied: `<skill path>`. What changed, one line each. - New skills created: `<skill path>`. One line each (rare). - Backlog filed to the devex tracker: `<issue title>` (`<tags>`). One line each. - Dropped: one line per rejected finding + reason from the synthesizer.