Skip to content

notque/vexjoy-agent / skills/meta/toolkit

toolkit

Verified

Toolkit management: create and evaluate skills and agents, manage routing tables, generate Claude.md.

FileKindSize
SKILL.mdskill md15.5 KB
agents/skill-creator/analyzer.mdmarkdown4.8 KB
agents/skill-creator/comparator.mdmarkdown4.7 KB
agents/skill-creator/grader.mdmarkdown3.9 KB
assets/skill-creator/eval_viewer.htmlother57.1 KB
references/agent-comparison.mdmarkdown11.5 KB
references/agent-comparison/benchmark-tasks.mdmarkdown6.8 KB
references/agent-comparison/do-creation-compliance-tasks.jsonconfig8.5 KB
references/agent-comparison/examples-and-errors.mdmarkdown1.0 KB
references/agent-comparison/grading-rubric.mdmarkdown4.3 KB
references/agent-comparison/methodology.mdmarkdown7.4 KB
references/agent-comparison/optimization-guide.mdmarkdown12.0 KB
references/agent-comparison/optimization-tasks.example.jsonconfig853 B
references/agent-comparison/optimize-phase.mdmarkdown9.3 KB
references/agent-comparison/read-only-ops-short-tasks.jsonconfig375 B
references/agent-comparison/report-template.mdmarkdown3.8 KB
references/agent-comparison/socratic-debugging-body-short-tasks.jsonconfig372 B
references/agent-comparison/socratic-debugging-trigger-tasks.jsonconfig2.8 KB
references/agent-creator.mdmarkdown10.9 KB
references/agent-creator/agent-design-patterns.mdmarkdown12.4 KB
references/agent-creator/agent-eval-design.mdmarkdown7.7 KB
references/agent-creator/agent-frontmatter-template.mdmarkdown9.3 KB
references/agent-evaluation.mdmarkdown10.6 KB
references/agent-evaluation/batch-evaluation.mdmarkdown1.6 KB
references/agent-evaluation/common-issues.mdmarkdown2.1 KB
references/agent-evaluation/report-templates.mdmarkdown2.2 KB
references/agent-evaluation/scoring-rubric.mdmarkdown2.4 KB
references/blind-ab-tests.mdmarkdown7.8 KB
references/generate-claudemd.mdmarkdown11.0 KB
references/generate-claudemd/CLAUDEMD_TEMPLATE.mdmarkdown4.1 KB
references/generate-claudemd/examples-and-errors.mdmarkdown7.4 KB
references/github-profile-rules.mdmarkdown7.5 KB
references/github-profile-rules/github-api-patterns.mdmarkdown8.2 KB
references/github-profile-rules/rule-categories.mdmarkdown4.8 KB
references/hook-development.mdmarkdown10.9 KB
references/hook-development/architecture.mdmarkdown3.7 KB
references/hook-development/code-examples.mdmarkdown9.4 KB
references/hook-development/preferred-patterns.mdmarkdown6.5 KB
references/hook-development/telemetry-database.mdmarkdown6.5 KB
references/routing-table-updater.mdmarkdown10.2 KB
references/routing-table-updater/batch-mode.mdmarkdown2.1 KB
references/routing-table-updater/conflict-resolution.mdmarkdown3.8 KB
references/routing-table-updater/error-handling.mdmarkdown1.9 KB
references/routing-table-updater/examples.mdmarkdown4.8 KB
references/routing-table-updater/extraction-patterns.mdmarkdown2.2 KB
references/routing-table-updater/routing-format.mdmarkdown3.6 KB
references/routing-table-updater/skill-examples.mdmarkdown2.7 KB
references/skill-composer.mdmarkdown9.1 KB
references/skill-composer/compatibility-matrix.mdmarkdown13.0 KB
references/skill-composer/composition-patterns.mdmarkdown4.9 KB
references/skill-composer/examples.mdmarkdown17.1 KB
references/skill-composer/skill-patterns.mdmarkdown12.5 KB
references/skill-creator.mdmarkdown28.9 KB
references/skill-creator/agent-template.mdmarkdown18.5 KB
references/skill-creator/artifact-schemas.mdmarkdown8.2 KB
references/skill-creator/bundled-components.mdmarkdown2.3 KB
references/skill-creator/complexity-tiers.mdmarkdown8.0 KB
references/skill-creator/domain-research-targets.mdmarkdown13.2 KB
references/skill-creator/enrichment-workflow.mdmarkdown9.9 KB
references/skill-creator/error-catalog.mdmarkdown9.9 KB
references/skill-creator/preferred-patterns.mdmarkdown11.7 KB
references/skill-creator/progressive-disclosure.mdmarkdown8.5 KB
references/skill-creator/skill-template.mdmarkdown14.6 KB
references/skill-creator/workflow-patterns.mdmarkdown7.6 KB
references/system-upgrade.mdmarkdown11.0 KB
references/system-upgrade/component-audit-checklists.mdmarkdown8.4 KB
references/system-upgrade/upgrade-failure-modes.mdmarkdown8.7 KB
references/system-upgrade/upgrade-signal-parsing.mdmarkdown7.3 KB
references/toolkit-evolution.mdmarkdown14.5 KB
references/toolkit-evolution/diagnose-scripts.mdmarkdown9.5 KB
references/toolkit-evolution/evolution-history.mdmarkdown5.5 KB
references/toolkit-evolution/evolution-report-template.mdmarkdown716 B
references/toolkit-evolution/evolve-preferred-patterns.mdmarkdown6.9 KB
references/toolkit-evolution/evolve-scripts.mdmarkdown3.7 KB
references/toolkit-governance.mdmarkdown16.0 KB
references/toolkit-governance/adr-lifecycle.mdmarkdown10.9 KB
references/toolkit-governance/frontmatter-compliance.mdmarkdown11.1 KB
references/toolkit-governance/hook-standardization.mdmarkdown21.5 KB
references/toolkit-governance/routing-table-patterns.mdmarkdown11.6 KB
references/weak-model-uplift.mdmarkdown10.3 KB
scripts/agent-comparison/compare.pyscript2.3 KB
scripts/agent-comparison/generate_variant.pyscript19.6 KB
scripts/agent-comparison/optimize_loop.pyscript89.3 KB
scripts/agent-comparison/trigger_eval.pyscript19.5 KB
scripts/routing-table-updater/extract_metadata.pyscript10.8 KB
scripts/routing-table-updater/generate_routes.pyscript10.5 KB
scripts/routing-table-updater/scan.pyscript4.7 KB
scripts/routing-table-updater/update_routing.pyscript12.4 KB
scripts/routing-table-updater/validate.pyscript7.3 KB
scripts/skill-composer/build_dag.pyscript12.5 KB
scripts/skill-composer/discover_skills.pyscript12.1 KB
scripts/skill-composer/validate.pyscript12.3 KB
scripts/skill-creator/aggregate_benchmark.pyscript10.0 KB
scripts/skill-creator/eval_compare.pyscript10.2 KB
scripts/skill-creator/optimize_description.pyscript12.5 KB
scripts/skill-creator/package_results.pyscript7.8 KB
scripts/skill-creator/run_eval.pyscript6.3 KB

references/system-upgrade/upgrade-signal-parsing.md

View on GitHub
# Upgrade Signal Parsing Reference

> **Scope**: Extracting actionable upgrade items from Claude Code release notes, user goal changes, and learning.db retro candidates. Does NOT cover component implementation — only parsing and classification.
> **Version range**: Claude Code releases, all versions
> **Generated**: 2026-04-15 — verify signal categories against current release format

---

## Overview

Upgrade signals arrive in three forms: Claude Code release notes (feature additions, deprecations,
breaking changes), user goal-change statements (new workflows to support), and retro-driven signals
from the learning.db graduation queue. Each form requires a different parsing strategy. The most
common failure is treating a feature mention as an upgrade requirement without identifying *which
component type* is affected.

---

## Signal Type Classification

| Signal Form | Entry Point | Affected Components | Urgency Heuristic |
|-------------|-------------|--------------------|--------------------|
| Claude Code release note | `feat:` / `fix:` / `BREAKING:` prefix | Hooks (new events), agents (new capabilities), routing tables | BREAKING = Critical; new tool = Important; fix = Minor |
| User goal change | "from now on", "whenever X", "always Y" | Hooks (behavioral automation), agents (routing triggers) | User-stated = Critical |
| Retro graduation | `learning.db` rows with `graduated_to IS NULL` | Agent failure modes, skill instructions | Recurrence count drives priority |

---

## Pattern Table: Release Note Keywords → Component Types

| Keyword Pattern | Component Type | Change Action |
|-----------------|---------------|---------------|
| `new tool:`, `added tool` | Agents with `allowed-tools` | Add to `allowed-tools` list |
| `deprecated:`, `removed:` | Any component using deprecated API | `deprecate` or `upgrade` |
| `BREAKING:` + tool name | All hooks using that tool | `upgrade` — verify event schema |
| `hook event:`, `new event type` | Hooks registered for that event | `create-new` or `upgrade` |
| `model:`, `default model changed` | Agents with hardcoded model names | `upgrade` — update model field |
| `compaction`, `context window` | Hooks monitoring session state | `upgrade` — adjust thresholds |

---

## Correct Patterns

### Building a Change Manifest from a Release Note

Parse each actionable item as a triple: (what changed, which component types are affected, urgency tier).

```markdown
## Change Manifest — Claude Code vX.Y

| Signal | Component Types | Change Action | Tier |
|--------|----------------|--------------|------|
| New `Write` tool event type in PostToolUse | Hooks with PostToolUse | Upgrade event schema | Critical |
| Deprecated `--json` flag in bash | Scripts using bash --json | Upgrade call sites | Important |
| New Claude model released (e.g. `claude-<family>-<version>`) | Agents and skills with a `model:` pin | Review model field against the 2026-11-01 policy | Minor |
```

**Why**: A manifest without the component-type column causes the AUDIT phase to scan everything.
Scoping to component types cuts audit time from O(all) to O(affected).

---

### Parsing a User Goal-Change Statement

Extract the automation trigger and the behavioral change. Map trigger → hook event type.

```markdown
User: "from now on when a file is renamed, update all imports"

Parse:
- Trigger: file renamed (PostToolUse on Write/Edit with path change detection)
- Behavior: update imports (new hook, requires Bash tool)
- Affected: hooks/posttool-rename-sweep.py (exists — upgrade) OR new hook (create-new)
- Urgency: Critical (user-stated)
```

**Why**: Goal-change statements always imply automation (hooks), not one-time actions.
If no existing hook covers the trigger, `create-new` is the right action.

---

### Classifying Retro-Driven Signals

Query learning.db for graduated patterns and map to component updates.

```bash
# learning-db.py has no list subcommand: read the learnings table directly, read-only.
# Retro candidates: not yet graduated, seen 3+ times
sqlite3 -readonly ~/.claude/learning/learning.db \
  "SELECT topic, key, category, observation_count FROM learnings
   WHERE graduated_to IS NULL AND observation_count >= 3 ORDER BY observation_count DESC"

# Candidates that mention agents
sqlite3 -readonly ~/.claude/learning/learning.db \
  "SELECT topic, key, observation_count FROM learnings
   WHERE graduated_to IS NULL AND (topic LIKE '%agent%' OR tags LIKE '%agent%')"
```

Map recurrence count to tier:
- Count >= 5: Critical (pattern is systemic, not one-off)
- Count 2-4: Important
- Count 1: Minor (may be noise)

---

<!-- no-pair-required: section header, not a standalone failure mode block -->
## Pattern Catalog

### Require At Least One Signal Before Proceeding

**Detection**:
```bash
# Look for empty Change Manifest tables in task_plan.md
grep -A 5 "Change Manifest" task_plan.md | grep -c "^|"
# Should be > 1 (header row + at least one data row)
```

**Why this matters**: A zero-signal manifest means the trigger was too vague. The AUDIT phase will
scan all components with no scoping, producing noise and wasting time. Phase 1 instructions
explicitly say: "If you extracted 0 actionable signals, do not proceed."

Do instead: Ask the user for specifics. Quote the exact feature or change being referenced.

---

### Verify Interface Change Before Scheduling Upgrade

**Signal**: A release note mentions "improved JSON output" and the agent
immediately schedules upgrades to every script that uses JSON.

**Why this matters**: Not every mention is a breaking change. Only changes that alter the
interface (tool signature, event schema, model name) require upgrades.

Do instead: For each signal, ask: "Does this change the interface a component depends on?"
If no: Minor or skip. If yes: Important or Critical.

---

### Separate Signal Types by Source in Manifest

**Signal**: A single Change Manifest combining release-note signals, user
goal-change statements, and retro signals without flagging their source.

**Why this matters**: Each signal type has different urgency heuristics and different component
scope. Mixing them without source labels causes the PLAN phase to assign wrong tiers.

Do instead: Separate into sections by signal type. Label each row with its source.

---

## Error-Fix Mappings

| Error Message | Root Cause | Fix |
|---------------|------------|-----|
| "No signals found in changelog" | Input too vague (e.g., "update for the new Claude") | Ask for specific feature or change name |
| AUDIT scanning all 120+ components | Signal type column missing from manifest | Add component-type column before proceeding |
| Change action undefined for a signal | Signal classified but action not specified | Force a choice: deprecate / upgrade / create-new / inject-pattern |
| Tier not assigned | Urgency heuristic skipped | Apply: BREAKING=Critical, new=Important, fix=Minor |

---

## Detection Commands Reference

```bash
# Retro candidates: not yet graduated, seen 3+ times (read-only; learning-db.py has no list subcommand)
sqlite3 -readonly ~/.claude/learning/learning.db \
  "SELECT topic, key, category, observation_count FROM learnings
   WHERE graduated_to IS NULL AND observation_count >= 3 ORDER BY observation_count DESC"

# Verify Change Manifest has data rows
grep -A 5 "Change Manifest" task_plan.md | grep -c "^|"

# Find components using a deprecated pattern (replace PATTERN)
grep -rn 'PATTERN' agents/ skills/ hooks/ --include="*.md" --include="*.py"
```
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall