技能管道

其他 社区

技能解读

当前原文的自动摘译,尚未人工审校。

任务分类

对于每个编码任务,在执行之前先进行分类。评估范围信号并映射到任务类。输入信号:文件计数、任务描述、现有计划/移交文件、批次指标、CI 环境。如果不确定,请从 Medium 开始。如果任务中出现偏差或质量问题,请添加技能。有关详细的启发式、边缘情况和示例:请阅读references/classification-rules.md。

管道选择

将任务类别路由到正确的变体: 任务类别 · 变体 · 基本原理 琐碎 · 无 · 不需要开销 小 · 标准(最小) · 仅验证 + S&H 中 · 标准(部分) · 范围监控 + 验证 + 审查

标准管道(内循环)

按类别激活技能: 技能 · 琐碎 · 小 · 中 · 大 · 长时间运行的飞行前检查 · 钩子 · 钩子 · 钩子 · 钩子 · 钩子计划访谈 · - · - · - · 推荐 · 推荐意图框架代理 · - · - · 激活 · 激活 · 激活

外循环管道

外部循环跨会话运行,而不是在会话内运行。在节奏(每周、冲刺边界)或当pre-flight-check出现促销就绪模式时触发。何时触发外循环: 每周:建议的最小节奏 冲刺边界:在一系列训练之后 当 pre-flight-check 报告升级就绪计数 > 3 时

深度校准

不仅仅是哪些技能 - 每种技能的深度:维度 · 小 · 中 · 大 · 长时间运行 · 批量 飞行前检查 · Hook · Hook · Hook · Hook · Hook 规划通行证 · 0 · 0-1 · 1-2 · 深度迭代 · 每个任务或伞 意图框架 · - · 单帧 · 全框架 + 监控 · 全面 + 交接 · 团队领导框架

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
通用
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
88 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@pskoett · 未声明许可证
上下文用量评级
较高消耗
接入复杂程度
需简单配置
是否需要外部接口密钥
不需要
兼容的系统
未声明(默认跨平台)
运行环境要求
未检出明确要求
检测到的文件与系统行为
  • 只读
  • 允许写入 / 修改
  • 命令执行
网络行为
仅限本地
安装命令数
无(仅作为资料)

需要注意: 未声明工具权限范围;实际权限由运行环境决定。

作者说明文件(原文) SKILL.md

# Skill Pipeline

The conductor, not a player. This skill classifies tasks, selects the pipeline variant, calibrates depth, and orchestrates handoffs between skills. It produces no artifacts of its own — its output is routing decisions that activate other skills.

## Task Classification

On every coding task, classify before acting. Evaluate scope signals and map to a task class.

**Input signals:** file count, task description, existing plan/handoff files, batch indicators, CI environment.

```
Task received
  │
  ├─ Trivial (typo, rename, version bump)
  │  → No skills. Just do it.
  │
  ├─ Small (isolated fix, single-file, <10 logic lines)
  │  → verify-gate + simplify-and-harden
  │
  ├─ Medium (feature in known area, 2-5 files)
  │  → intent-framed-agent + verify-gate + simplify-and-harden
  │
  ├─ Large (complex refactor, new architecture, unfamiliar codebase, high-risk logic)
  │  → Full standard pipeline
  │  → Recommend /plan-interview before starting
  │
  ├─ Long-running (multi-session, high context pressure, prior handoff exists)
  │  → Full standard pipeline with context-surfing as critical skill
  │
  └─ Batch (multiple features from spec, 5+ discrete tasks, issue triage)
     → Team-based pipeline (agent-teams-simplify-and-harden)
```

When uncertain, start with Medium. Add skills if drift or quality issues appear mid-task.

For detailed heuristics, edge cases, and examples: read `references/classification-rules.md`.

## Pipeline Selection

Route task class to the right variant:

| Task Class | Variant | Rationale |
|------------|---------|-----------|
| Trivial | None | No overhead needed |
| Small | Standard (minimal) | Verify + S&H only |
| Medium | Standard (partial) | Scope monitoring + verify + review |
| Large | Standard (full) | Full inner loop with planning |
| Long-running | Standard (full) | Context-surfing is critical |
| Batch | Team-based | Breadth over depth |
| CI environment | CI | Headless review |
| Periodic | Outer loop | Cross-session improvement |

**Heuristic:** Standard pipeline for **depth** (single complex feature). Team-based pipeline for **breadth** (batch of tasks). CI pipeline when `CI=true` or `GITHUB_ACTIONS=true`.

## Activation Sequences

### Standard Pipeline (Inner Loop)

```
pre-flight-check (SessionStart hook — surfaces prior learnings + heals)
  → classify
  → (recommend /plan-interview if Large or Long-running)
  → intent-framed-agent (at planning-to-execution transition)
  → context-surfing (auto-activates when intent frame + plan exist; concurrent with intent monitoring)
  → [IMPLEMENTATION]
  → self-healing  ← inner-loop recovery primitive; called whenever a command/test/build/external call fails or a helper is missing.
  →                Diagnoses, patches, verifies, files HEAL- entry. Resumes when verified.
  → verify-gate (compile + test + lint; fix loop if red — fix loop calls self-healing)
  → simplify-and-harden (post-completion, if non-trivial diff)
  → self-improvement (on errors, corrections, S&H learning candidates, recurring heal handoffs)
```

**Skill-by-class activation:**

| Skill | Trivial | Small | Medium | Large | Long-running |
|-------|---------|-------|--------|-------|-------------|
| pre-flight-check | Hook | Hook | Hook | Hook | Hook |
| plan-interview | - | - | - | Recommend | Recommend |
| intent-framed-agent | - | - | Activate | Activate | Activate |
| context-surfing | - | - | - | Activate | Critical |
| verify-gate | - | Activate | Activate | Activate | Activate |
| self-healing | On failure | On failure | On failure | On failure | On failure |
| simplify-and-harden | - | If non-trivial | If non-trivial | If non-trivial | If non-trivial |
| self-improvement | On error only | On error only | On error/completion | On error/completion | On error/completion |

### Team-Based Pipeline

```
classify (Batch)
  → (recommend /plan-interview if no spec exists)
  → agent-teams-simplify-and-harden
    ├─ Team lead emits Intent Frame #1
    ├─ Phase 1: parallel implementation agents
    ├─ verify-gate (compile + test + lint)
    ├─ Phase 2: parallel audit agents (simplify, harden, spec)
    ├─ Fix loop (up to 3 audit rounds)
    └─ Learning loop output
  → self-improvement
```

### CI Pipeline

```
classify (CI detected)
  → simplify-and-harden-ci (headless scan, PR changed files only)
  → self-improvement-ci (pattern aggregation, promotion recommendations)
```

### Outer Loop Pipeline

The outer loop runs across sessions, not within them. Trigger on cadence (weekly, sprint boundary) or when `pre-flight-check` surfaces promotion-ready patterns.

```
learning-aggregator (read .learnings/, find patterns, rank promotion candidates)
  → harness-updater agent (apply promotions to CLAUDE.md, AGENTS.md, copilot-instructions.md)
  → eval-creator (create permanent test cases from promoted patterns)
  → eval-creator run (regression check on all existing evals)
```

**When to trigger the outer loop:**
- Weekly: recommended minimum cadence
- Sprint boundary: after a burst of sessions
- When `pre-flight-check` reports promotion-ready count > 3
- After a significant incident or recurring failure
- Manually: user invokes `/learning-aggregator`

**Outer loop is always human-gated.** `learning-aggregator` produces a gap report. `harness-updater` shows diffs for approval. No automatic writes to instruction files without human review.

## Depth Calibration

Not just which skills — how deep each goes:

| Dimension | Small | Medium | Large | Long-running | Batch |
|-----------|-------|--------|-------|-------------|-------|
| Pre-flight check | Hook | Hook | Hook | Hook | Hook |
| Planning passes | 0 | 0-1 | 1-2 | Deep iterative | Per-task or umbrella |
| Intent frame | - | Single frame | Full frame + monitoring | Full + handoff | Team lead frame |
| Context-surfing | - | - | Active | Critical (exit protocol ready) | Lightweight drift checks |
| Verify-gate | Compile + test | Compile + test | Compile + test + lint | Compile + test + lint | Compile + test (per round) |
| Self-healing | On failure (file HEAL) | On failure (file HEAL) | On failure + recurrence check | On failure + recurrence check | On failure (per task) |
| S&H budget | 20% diff, 60s | 20% diff, 60s | 20% diff, 60s | 20% diff, 60s | 30% team growth cap |
| Audit rounds (teams) | - | - | - | - | Up to 3 |
| Self-improvement | Error-triggered | Error-triggered | Error + S&H feed | Error + S&H feed | Error + teams feed |

## Handoff Rules

Artifacts flow between skills. The orchestrator ensures each skill receives what it needs.

**Key handoffs:**

1. **Plan file** (`docs/plans/plan-NNN-<slug>.md`) — produced by `plan-interview`, consumed by `intent-framed-agent` (context), `context-surfing` (wave anchor), `agent-teams` (task extraction).

2. **Intent Frame** — produced by `intent-framed-agent`, consumed by `context-surfing` (wave anchor strengthening). Copied into handoff files on drift exit.

3. **Handoff file** (`.context-surfing/handoff-[slug]-[timestamp].md`) — produced by `context-surfing` on drift exit, consumed by next session for resume.

4. **Verify-gate signal** — produced by `verify-gate` (pass/fail + diagnostics), consumed by `simplify-and-harden` (only activates after green gate) and the heal loop (on failure — verify-gate hands the diagnostics to self-healing, which diagnoses + patches + re-verifies, then signals verify-gate to re-check).

5. **HEAL entries + artifacts** (`.learnings/HEALS.md`, `.learnings/heals/<HEAL-ID>/`) — produced by `self-healing`, consumed by `pre-flight-check` (surfaces prior heals at session start by `Pattern-Key` / `Active-Context`), `learning-aggregator` (cross-session recurrence analysis), and `self-improvement` (when `Handoff` block flags promotion at Recurrence ≥ 3).

6. **Learning candidates** (`learning_loop.candidates`) — produced by `simplify-and-harden` and `agent-teams`, consumed by `self-improvement` for pattern tracking.

7. **Learning entries** (`.learnings/*.md`) — produced by `self-improvement`, consumed by `learning-aggregator` for cross-session analysis and by `pre-flight-check` at session start.

8. **Gap report** — produced by `learning-aggregator`, consumed by `harness-updater` agent for promotion and `eval-creator` for test case generation.

9. **Eval cases** (`.evals/cases/*.md`) — produced by `eval-creator`, consumed by regression runs and surfaced by `pre-flight-check`.

**Precedence:** If `context-surfing` and `intent-framed-agent` both fire simultaneously, context-surfing's exit takes precedence. Degraded context makes scope checks unreliable.

For the full artifact/signal/budget table: read `references/handoff-matrix.md`.

## Decision Points

The orchestrator intervenes at these moments:

### Task Arrival
Classify the task. Select pipeline variant and depth. Emit routing decision. If Large/Long-running, recommend `/plan-interview`. If Batch, recommend team-based variant.

### Plan Approval
When user approves a plan from `plan-interview`, flow directly into the execution stage — no separate "should I proceed?" prompt. This means activating `intent-framed-agent` to emit an Intent Frame. The intent frame itself still requires user confirmation before coding begins (that confirmation is part of `intent-framed-agent`, not an extra gate). Populate task tracking with checklist items.

### Planning-to-Execution Transition
When no plan-interview was used and the user signals readiness ("go ahead", "implement this", "let's start"), activate `intent-framed-agent`. Emit Intent Frame. Wait for user confirmation of the frame before coding.

### Failure mid-implementation
A command, test, build, lint, or external call fails before verify-gate even runs (or any other mid-task gap appears — missing helper, env drift, API change). Route into `self-healing`: diagnose, patch, verify, file the HEAL entry. Resume execution from the working state. Most heals are recurrences — `self-healing` searches `HEALS.md` by Pattern-Key first.

### Implementation Complete
Activate `verify-gate` to run compile, test, and lint checks. If any fail, route into `self-healing` for the diagnosis/patch/verify loop (up to 3 attempts per phase). After each heal, verify-gate re-runs the checks. Once all checks pass and the diff meets the non-trivial threshold (see `references/classification-rules.md`), activate `simplify-and-harden`. If the diff is trivial, signal completion directly after verify-gate passes.

### Drift Detected
If `context-surfing` fires a drift exit, stop execution. Write handoff file. If the task was classified below Large, consider re-classifying upward for the next session.

### Session Resume
Check for handoff files in `.context-surfing/`. If found, read completely. Re-establish context from handoff. Re-classify if needed. Resume from recommended re-entry point.

## Overrides

Users can override any routing decision:

- **Force depth:** `depth=small` / `depth=large` — override classification
- **Force variant:** `variant=teams` / `variant=standard` — override pipeline selection
- **Skip review:** `--no-review` — skip `simplify-and-harden`
- **Force planning:** invoke `/plan-interview` on any task regardless of classification
- **Skip all skills:** user says "just do it" on a non-trivial task — respect the override

## Re-classification

Tasks can change class mid-execution. Watch for:

- **Escalation signals:** scope expanded beyond original estimate, many more files affected than expected, `context-surfing` drift exit, `intent-framed-agent` detects significant scope change
- **De-escalation signals:** task turns out simpler than planned, plan reveals minimal changes needed

When re-classification is warranted:
1. Note the signal that triggered re-classification
2. Adjust active skills (add or remove pipeline stages)
3. If escalating to Large: recommend `/plan-interview` if no plan exists
4. If de-escalating: drop unnecessary stages, proceed with lighter pipeline

## Anti-Patterns

- **Do NOT re-implement skill logic.** This skill classifies and dispatches. Each individual skill owns its own procedure.
- **Do NOT auto-invoke plan-interview.** It is a human gate. Recommend it; let the user decide.
- **Do NOT create a third monitoring layer.** During execution, `intent-framed-agent` monitors scope and `context-surfing` monitors quality. The orchestrator dispatches at decision points, then gets out of the way.
- **Do NOT override individual skill guardrails.** If `simplify-and-harden` has a 20% budget cap, the orchestrator respects it.
- **Do NOT force skills on trivial tasks.** The pipeline exists to help, not to slow down simple work.

## Pipeline Variant Details

For complete step-by-step walkthroughs of each variant including hybrid scenarios and session resume: read `references/pipeline-variants.md`.

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。