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-requirements.md

View on GitHub
---
name: espalier-requirements
description: Requirements analysis skill - decompose requirements into actionable specs
---

# Requirements Analysis

## Purpose
Transform a user requirement into a structured specification that coding and review
agents can execute against without ambiguity.

## Output Format

For every requirement, produce:

### 1. Requirement Summary
- **What:** One sentence describing the feature/fix
- **Why:** Business motivation
- **Who:** Affected users/systems

### 2. Acceptance Criteria
List concrete, verifiable conditions:
- [ ] When {action}, then {expected result}
- [ ] {boundary condition} is handled by {behavior}
- [ ] {error case} results in {specific response}

### 3. Scope Definition
- **In scope:** {exactly what will be changed}
- **Out of scope:** {explicitly excluded to prevent scope creep}
- **Files likely touched:** {predicted based on architecture knowledge}
- **Layers involved:** {which architectural layers}

### 4. Technical Considerations
- Dependencies on external services?
- Data model changes needed?
- Breaking changes / backwards compatibility?
- Performance implications?

### 5. Task Decomposition
Break into sub-tasks that each fit in one agent context window:
1. {Sub-task 1} — estimated files: {N}
2. {Sub-task 2} — estimated files: {N}
3. ...

Size each sub-task as one coder's bounded work — one seam: a schema list
with its hooks and tests; one screen with its hook and its GraphQL
documents; one resolver with its abuse tests. The test of a good size is
that a coder starting fresh finishes it with its instructions still at
full strength. When unsure, split: a second spawn costs one context-pack
read; a spawn that runs past its attention costs a review round. Test
writing splits the same way at Stage 3 — one spawn per test-file group.
The contract phase stays one spawn; a contract too large for one spawn
hands off (the coder's Handoff protocol). Splitting changes DISPATCH only:
the panel still reviews the COMBINED diff once.

### References (when the requester named a model)

When the requirement points at code as the model — "like `X` does", "the
same semantics as `vendor/rate-limiter`", a file, a folder, a library, a
URL — record it, one line each, under `## References`: the path (or URL)
and what to take from it (semantics, a shape, a protocol — never "copy
it"). The section exists only when the requester named one; the context
pack carries it as `- References:`, the coder reads it before the layer's
reference files, the reviewer checks fidelity to it. A reference that
contradicts a project convention is settled here, by the grill, not by
the coder.

### Contract and notes (what requirements.md holds)

The five sections above — plus `## Open Questions`, `## Convention Notes`,
`## References` when the requester named a model, and `## Retired
Surface` when a simplify cut filed the change — are the CONTRACT: what the coder builds to, what the reviewer checks against, the
text the human approves at the Requirements Approval Gate. Derivation,
alternatives considered, what was settled for next time, and the grill's
full question-and-answer record go to `requirements-notes.md` in the same
change directory, under the same headings, linked once from the Requirement
Summary as `Notes: requirements-notes.md`. Frontmatter is unchanged. The
Stage 2 review files a heading outside the contract set as a P2 with Fix =
"move to requirements-notes.md"; before the first coder spawn the
orchestrator prints the same list (`req_shape_check`) as information only —
nothing is refused on size, the human approved this text.

## Process
1. Read the requirement carefully
2. Read relevant wiki/ files for business context
3. Read engineering-structure.md to understand affected modules
4. Produce the structured output above — draft the FULL requirements doc first,
   so the grill has a document for its inline writes to land in (same order as
   the fix lane: draft, then grill).
5. **Grill the requirement.** Unless the pipeline passed `--no-grill`, invoke the
   `espalier-grill` skill in `spec` mode on the draft. Pass `familiarity: low`
   ONLY when the requester's own words say the area is new to them ("I don't
   know this module", "never touched the auth code") — never from your read
   of them; the grill then reads the map to them first (its Step 1.6). Grill interrogates the
   requirement (adaptive depth — it may skip a crisp one) and writes resolved
   decisions into the Acceptance Criteria and Scope Definition sections above.
   Record its verdict (`GRILLED (light)` / `GRILLED (full)` /
   `SKIPPED: <reason>`) — the orchestrator logs it to pipeline-state.md.

## Anti-Patterns
- NEVER start coding without acceptance criteria
- NEVER assume scope — ask if unclear
- NEVER combine unrelated changes in one requirement
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