AGENT SKILL

process-retrospective

Formalized skeleton for the process-retrospective frame port. Use when #348 ships the live producer and replaces this skeleton. DO NOT USE FOR: any current PR — applies-when is 'never' until #348 ships. See trigger-deferred-to and trigger-deferred-since below.

License 许可
MIT
最近更新
2026-08-16
Stars
★ 3
Forks
0

01 前言 Front Matter

name
process-retrospective
provides
process-retrospective
description
Formalized skeleton for the process-retrospective frame port. Use when #348 ships the live producer and replaces this skeleton. DO NOT USE FOR: any current PR — applies-when is 'never' until #348 ships. See trigger-deferred-to and trigger-deferred-since below.
applies-when
never
trigger-status
deferred
trigger-deferred-to
#348
trigger-deferred-since
2026-05-03

02 资源文件 1

03 SKILL.md 正文

<!-- platform-assumptions: markdown skill guidance for VS Code custom agents in Agent Orchestra; this skeleton is formalized but its trigger predicate is deferred — the port resolves to not-applicable on every PR until issue #348 ships the live producer. --> <!-- markdownlint-disable-file MD041 MD003 -->

Process Retrospective (Deferred Skeleton)

Formalized skeleton for the process-retrospective frame port. The port is declared and its credit row emitted as DEFERRED(#348): ... on every PR until issue #348 ships the live producer and trigger predicate.

Deferral Status

Field Value
trigger-status deferred
trigger-deferred-to #348 ("Thin Harness E — Close the learning loop")
trigger-deferred-since 2026-05-03
applies-when never (deterministic false — deferred port)

What this means: on every PR, the frame predicate evaluator resolves never to false, the port is excluded from the umbrella's 95% coverage denominator, and Code-Conductor emits a DEFERRED(#348): credit row via Build-DeferredPortCreditRow.

When #348 Ships

Issue #348 ("Thin Harness E — Close the learning loop") will:

  1. Replace applies-when: never with the real trigger predicate
  2. Flip trigger-status: deferred → trigger-status: live
  3. Remove trigger-deferred-to and trigger-deferred-since fields
  4. Implement the retrospective content methodology in this SKILL.md body
  5. Add the explicit-skip adapter per the port's skip contract

Until then, this skeleton must not be invoked — the applies-when: never frontmatter guarantees the port never triggers.

#443 ↔ #348 Split Contract

Artifacts that are stable (must be preserved when #348 ships):

  • frame/ports/process-retrospective.yaml port YAML (fields change, file persists)
  • skills/process-retrospective/SKILL.md (this file; body replaces, frontmatter evolves)
  • skills/process-retrospective/adapters/process-retrospective-explicit-skip-adapter.md (name persists)
  • DEFERRED(#348): prefix as migration-detection contract (regex ^DEFERRED\(#\d+\):)

Artifacts that are scaffolding (will be replaced by #348):

  • The applies-when: never frontmatter line
  • The trigger-status: deferred + trigger-deferred-to + trigger-deferred-since metadata
  • The deferred skeleton body text in this file

Gotchas

  • Never invoke this skeleton directly. The applies-when: never frontmatter guarantees the port never fires. Any code that bypasses the predicate evaluator and calls this skill directly will get an empty skeleton, not a real retrospective.
  • Do not copy this skeleton's frontmatter into a live skill. When #348 ships, the applies-when, trigger-status, trigger-deferred-to, and trigger-deferred-since fields must all change. Copying them verbatim would silently defer the live port.

Frame Ports Filled By This Skill

Port Work adapter Explicit-skip adapter
process-retrospective This SKILL.md (skeleton — deferred, never triggers) adapters/process-retrospective-explicit-skip-adapter.md

04 同仓库更多 Skills

Grimblaz
Grimblaz/agent-orchestra

webapp-testing

Playwright end-to-end testing guidance for web apps, with practical patterns and setup steps. Use when creating or improving browser-based E2E coverage, test stability, and CI execution. DO NOT USE FOR: React component tests (use ui-testing), canvas game interaction (use browser-canvas-testing), TDD workflow (use test-driven-development), debugging failures (use systematic-debugging), or randomized property tests (use property-based-testing).

测试与质量前端开发
★ 3
Grimblaz
Grimblaz/agent-orchestra

verification-before-completion

Evidence-based verification checklist before marking work complete. Use before PRs, releases, marking tickets done, or any "I'm finished" declaration; also when naming a baseline commit for a differential suite claim, when designing a mutation campaign or red-run evidence, when making an absence claim, a universal claim, or a one-time demonstration offered as a standing guarantee, when attributing a measurement or claiming a sweep or verification loop is complete, and when stating what a check or a CI suite will do about a change. DO NOT USE FOR: post-merge cleanup or archival (use post-pr-review) or processing GitHub review comments (use code-review-intake).

★ 3
Grimblaz
Grimblaz/agent-orchestra

validation-methodology

Reusable validation and review methodology for staged validation, failure triage, and prosecution-depth setup. Use when running validation ladders, triaging failures, or executing adversarial review passes. DO NOT USE FOR: CE Gate orchestration, specialist dispatch ownership, or step execution flow (keep those in Code-Conductor).

★ 3
Grimblaz
Grimblaz/agent-orchestra

upstream-onboarding

Shared opening-phase protocol for upstream agents (Experience-Owner, Solution-Designer, Issue-Planner) and Code-Conductor when invoked on an existing GitHub issue. Renders a scaled context brief and runs a standards check on inherited work at each phase boundary. Use when a user-invocable agent receives a request referencing an existing GitHub issue and must load solution-authoring and upstream-onboarding at the opening phase. DO NOT USE FOR: subagent dispatches (which already operate within an assessed session context); post-merge review (use post-pr-review); research or non-tree subagents.

人力资源Skill与智能体开发
★ 3
Grimblaz
Grimblaz/agent-orchestra

ui-testing

Resilient React component testing strategies focusing on user behavior. Use when writing or reviewing component-level React tests, fixing flaky component tests, or establishing React testing patterns. DO NOT USE FOR: Playwright E2E tests (use webapp-testing), canvas game interaction (use browser-canvas-testing), TDD workflow (use test-driven-development), debugging failures (use systematic-debugging), UI component design (use frontend-design), or randomized property tests (use property-based-testing).

设计师测试与质量前端开发
★ 3
Grimblaz
Grimblaz/agent-orchestra

ui-iteration

Reusable screenshot-driven UI polish workflow for iterative visual refinement. Use when improving layout, hierarchy, spacing, feedback, or Tailwind-based presentation through repeated review-and-adjust passes. DO NOT USE FOR: functional bug fixing, accessibility-only audits, or major redesign strategy work (use Code-Smith or frontend-design).

设计师前端开发
★ 3