Skip to content

Junhanliu-dev/espalier-engineering / skills/espalier-init

espalier-init

Verified

Analyze any existing codebase, discover its patterns and best practices, and generate an Espalier structure (rules, skills, wiki, pipeline) so AI coders produce code matching that project's language and conventions. Greenfield repos take the two-pass Decide-Then-Bind path (/espalier-map charts the conventions, init binds them); boilerplate repos run init normally, then map the product. Wires into Claude Code, Codex, and/or GitHub Copilot (.claude/, .agents/skills/ + .codex/, .github/).

FileKindSize
SKILL.mdskill md43.5 KB
hook-templates/check-layer-boundaries-go.shscript665 B
hook-templates/check-layer-boundaries-python.shscript821 B
hook-templates/check-layer-boundaries-typescript.shscript1.6 KB
hook-templates/copilot-hook-adapter.shscript2.4 KB
hook-templates/drift-detect.shscript5.7 KB
hook-templates/drift-helpers.shscript56.4 KB
hook-templates/espalier-outside.shexecutablescript28.8 KB
hook-templates/espalier-pr.shexecutablescript43.2 KB
hook-templates/espalier-stats.shexecutablescript27.3 KB
hook-templates/lookup-helpers.shscript9.5 KB
hook-templates/map-guard.shexecutablescript3.9 KB
hook-templates/maprun-dispatch.shexecutablescript21.0 KB
hook-templates/maprun-integration.shexecutablescript3.4 KB
hook-templates/maprun-merge.shexecutablescript2.9 KB
hook-templates/maprun-pr.shexecutablescript12.8 KB
hook-templates/maprun-verify.shexecutablescript5.0 KB
hook-templates/maprun.pyscript65.6 KB
hook-templates/parse-drift-blocks.pyscript1.1 KB
hook-templates/post-edit-wrapper.shscript2.0 KB
hook-templates/post-merge-backlink.shscript2.2 KB
hook-templates/pre-push-gate-wrapper.shscript3.0 KB
hook-templates/pre-push-gate.shscript18.1 KB
hook-templates/rebuild-commit-index.shscript2.6 KB
references/discovery-checklist.mdmarkdown18.5 KB
references/validation.mdmarkdown16.7 KB
references/wiki-templates.mdmarkdown710 B
references/wiring.mdmarkdown13.5 KB
templates/agent.mdmarkdown3.7 KB
templates/agents/harness-coder.mdmarkdown33.9 KB
templates/agents/harness-reviewer.mdmarkdown25.1 KB
templates/agents/harness-security.mdmarkdown14.0 KB
templates/agents/modes/fix-round.mdmarkdown3.0 KB
templates/agents/modes/re-review.mdmarkdown5.3 KB
templates/agents/modes/repo-audit.mdmarkdown2.8 KB
templates/agents/modes/simplification.mdmarkdown7.0 KB
templates/agents/modes/stage6-abuse-coverage.mdmarkdown1.3 KB
templates/agents/modes/wiki-sweep.mdmarkdown5.6 KB
templates/pipeline.mdmarkdown18.9 KB
templates/rules/coding-standards.mdmarkdown3.2 KB
templates/rules/development-process.mdmarkdown3.2 KB
templates/rules/engineering-structure.mdmarkdown1008 B
templates/rules/production-standards.mdmarkdown5.8 KB
templates/rules/security-standards.mdmarkdown5.6 KB
templates/scout-prompts.mdmarkdown9.0 KB
templates/skills/espalier-ask.mdmarkdown6.4 KB
templates/skills/espalier-audit.mdmarkdown10.0 KB
templates/skills/espalier-coding-references/platform-native.mdmarkdown9.4 KB
templates/skills/espalier-coding-spec.mdmarkdown496 B
templates/skills/espalier-coding.mdmarkdown4.0 KB
templates/skills/espalier-doctor.mdmarkdown8.0 KB
templates/skills/espalier-fix.mdmarkdown77.5 KB
templates/skills/espalier-grill.mdmarkdown21.5 KB
templates/skills/espalier-map.mdmarkdown20.0 KB
templates/skills/espalier-maprun.mdmarkdown31.1 KB
templates/skills/espalier-prune.mdmarkdown13.0 KB
templates/skills/espalier-repot.mdmarkdown7.6 KB
templates/skills/espalier-requirements.mdmarkdown4.7 KB
templates/skills/espalier-review.mdmarkdown4.5 KB
templates/skills/espalier-security.mdmarkdown5.6 KB
templates/skills/espalier-simplify.mdmarkdown25.0 KB
templates/skills/espalier-stages/1-2-requirements.mdmarkdown7.6 KB
templates/skills/espalier-stages/3-coding.mdmarkdown15.0 KB
templates/skills/espalier-stages/4-panel.mdmarkdown14.3 KB
templates/skills/espalier-stages/5-6-contract.mdmarkdown10.3 KB
templates/skills/espalier-stages/7-10-delivery.mdmarkdown16.8 KB
templates/skills/espalier-stages/simple.mdmarkdown14.0 KB
templates/skills/espalier-testing.mdmarkdown2.9 KB
templates/skills/espalier.mdmarkdown27.7 KB

templates/skills/espalier-review.md

View on GitHub
---
name: espalier-review
description: >-
  Expert plan + code reviewer for {project}. Use in two spots — BEFORE
  implementation (plan review, gates the start) and AFTER (code review, before
  merge) — to check a change against {project}'s conventions, layer boundaries,
  and production-readiness standards. The code-review loop spawns the
  harness-reviewer agent. Triggers: "review this", "code review", "plan review",
  "check before merge", "is this ready to ship", "review the diff/PR".
---

# Expert Reviewer

## Two Review Loops

### 1. Plan Review — before implementation
- **When:** a plan / requirements exist, before any code is written.
- **Input:** the plan or `requirements.md` + the project rules.
- **Do:** check scope, layer placement, and the checklists below against the plan.
- **Output:** findings (format below) that gate the start of implementation.
- **Gate (pass condition):** zero P0/P1 findings against the current plan —
  P2/P3 are recorded, never blocking. On a non-pass, the plan is revised and
  re-reviewed; round counting and escalation are owned by pipeline Stage 2
  (`max-req-rounds`), not this skill.
- **Who:** runs inline — no agent spawned.

### 2. Code Review — after implementation, before merge
- **When:** the coder reports a change complete.
- **Input:** the diff + the coder's `coding-report.md` + the project rules.
- **Do:** spawn `harness-reviewer` (the canonical agent) — it runs the
  Runtime-Surface, Production-Readiness, and (advisory) Minimalism +
  Readability reviews and writes `review-record.md`.
- **Output:** `review-record.md` + a `VERDICT:` sentinel that gates the merge.
- **Gate (pass condition):** verdict `PASS`/`PASS_WITH_FIXES` with `p0=0 p1=0`
  on the sentinel — P2/P3 (minimalism + readability advisories included) are
  recorded, never blocking. On a non-pass, the coder fixes and the change is
  re-reviewed; round counting and escalation are owned by pipeline Stage 4
  (`max-code-rounds`), not this skill.
- **Who:** `harness-reviewer`, re-spawned each fix round until the verdict is clean.

## Review Output Format
Each finding MUST include:
- Problem: what's wrong
- Fix: how to fix it
- Priority: P0 (blocker) / P1 (must fix) / P2 (should fix) / P3 (suggestion)

## Review Checklist (Project-Specific)
- [ ] Follows {project}'s naming conventions
- [ ] Error handling matches project pattern
- [ ] New code placed in correct layer/module
- [ ] No forbidden cross-layer dependencies
- [ ] {detected convention} is followed
- [ ] Tests cover the changed interface

## General Checks
- [ ] Correctness: Does it do what the requirement says?
- [ ] Consistency: Does it match existing patterns?
- [ ] Completeness: Edge cases handled?
- [ ] Leanness: nothing built beyond the requirement (no speculative
      abstraction/config); no NEW dependency where stdlib, a native feature, or
      an installed dependency covers it. Advisory P2/P3 except the new-dependency
      P1 — canonical rules in `espalier/agents/harness-reviewer.md` (Minimalism
      Review). Never flag a construct the rules/specs mandate.
- [ ] Readability: names state intent, judged against the project's own
      conventions — never personal taste. A cryptic EXPORTED/public name is the
      single P1; everything else advisory P2/P3 — canonical rules in
      `espalier/agents/harness-reviewer.md` (Readability Review).

## Production-Readiness Checks
`espalier/rules/production-standards.md` is the SINGLE SOURCE for these checks and
their severity tiers — do not restate severities here (they drift). Confirm each
that applies to the change:
- [ ] External calls carry a timeout + decided failure behaviour
- [ ] List queries on request paths are bounded/paginated; no N+1 on hot paths
- [ ] New endpoints/consumers emit a structured log — actor, entity id, outcome
- [ ] No swallowed errors; persistence-path failures never continue as success
- [ ] Migrations follow expand → migrate → contract; destructive steps requirement-authorized
- [ ] Mutating consumers/webhooks are idempotent under redelivery

## Output Template

The CANONICAL output format (columns, verdict vocabulary, sentinel line) is
defined in `espalier/agents/harness-reviewer.md` — that file wins on any
disagreement. Shape:

### Review: {what was reviewed}
| # | Priority | File | Problem | Fix |
|---|----------|------|---------|-----|
| 1 | P0 | path/file.ext | ... | ... |
| 2 | P1 | path/file.ext | ... | ... |

**Verdict:** PASS / PASS_WITH_FIXES / FAIL / ESCALATION_REQUIRED
(ESCALATION_REQUIRED is fix-lane-only — see the agent file for when.)
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall