AGENT SKILL

reflect

Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.

License 许可
GPL-3.0
所属仓库
bendusz/bstack
最近更新
2026-11-15
Stars
★ 3
Forks
1

01 前言 Front Matter

name
reflect
description
Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.
disable-model-invocation
true

02 资源文件 4

03 SKILL.md 正文

Reflect

Mine the current conversation for durable learnings, then route them into skill edits.

Invoke when the user says "reflect" or "/poteto: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. Locate the active transcript

Before fanning out, find this conversation's transcript. Claude Code stores transcripts under ~/.claude/projects/<slug>/, where <slug> is the active workspace path encoded with / replaced by -. Use only the active workspace's directory. Do not glob across ~/.claude/projects/*/. That crosses workspace boundaries and reads private chats from unrelated projects.

ls -t ~/.claude/projects/<slug>/*.jsonl ~/.claude/projects/<slug>/*/subagents/*.jsonl 2>/dev/null | head -10

That covers the session (<session>.jsonl) and subagent (<session>/subagents/agent-<id>.jsonl) layouts. For each candidate, read its first user message (the first lines may be queue-operation records; skip those). Take the file whose first user message contains the conversation's opening user prompt. If none matches, pass a tight digest of the session instead.

2. Spawn three reviewers in parallel

One message, three Task calls, subagent_type: general-purpose. Not Explore: reviewers need MCP access to look up the tickets, chat threads, and observability traces the transcript references, and Explore strips MCP tools.

Set model on each reviewer and on the synthesizer from the table. If the Task tool rejects a model alias, use the closest available tier and say so.

Lens model Prompt template
Judgment opus references/judgment-reviewer.md
Tooling sonnet references/tooling-reviewer.md
Divergent opus references/divergent-reviewer.md

Pass each template verbatim, substituting the transcript path or digest where marked. Reviewers return findings in the Task response body.

3. Synthesize

One Task call, subagent_type: general-purpose, model: opus. Not Explore: it spot-verifies citations through MCP, and Explore strips MCP tools. Pass references/synthesizer.md verbatim, with each reviewer's full output inlined where marked. It returns an 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 each Backlog item to your team's devex or backlog tracker without waiting. Only the Accepted list waits for approval.

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): hand to your skill-authoring skill if one is installed (for example superpowers' writing-skills) and run its draft / test / iterate loop; otherwise the parent drafts it and tests it the same way.
  • tune description: <skill path> (the skill exists but didn't trigger when it should have): hand to your skill-authoring skill and tune the description until the trigger test passes.
  • new skill: <kebab-name>: hand creation to your skill-authoring skill. 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.

04 同仓库更多 Skills

bendusz
bendusz/bstack

why

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

★ 3
bendusz
bendusz/bstack

unslop

Cut AI tells from any writing. Must always apply.

★ 3
bendusz
bendusz/bstack

typescript-best-practices

TypeScript best practices. Use when reading or editing any .ts or .tsx file.

★ 3
bendusz
bendusz/bstack

technical-writing

Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /poteto:technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.

★ 3
bendusz
bendusz/bstack

teach

Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.

★ 3
bendusz
bendusz/bstack

principle-type-system-discipline

Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.

★ 3