Junhanliu-dev/espalier-engineering / skills/espalier-init
espalier-init
VerifiedAnalyze 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/).
templates/rules/coding-standards.md
View on GitHub# Coding Standards
## Discovered Conventions
{list every pattern found to be consistent across the codebase}
## Type Discipline
- {how types are used — strict? loose? where?}
- {specific type choices that are project conventions}
## Error Handling Pattern
{the specific pattern this project uses — with code example from the project}
## Naming Conventions
| Element | Convention | Example |
|---------|-----------|---------|
| {files} | {pattern} | {real example} |
| {functions} | {pattern} | {real example} |
| {types} | {pattern} | {real example} |
| {constants} | {pattern} | {real example} |
Beyond casing, a name STATES what it holds or does — a reader who has not
opened the body can tell. Public/exported names (functions, endpoints, DB
columns, event fields) are contracts: a cryptic public name blocks review
(harness-reviewer Readability Review, P1). Internal terseness the project
itself uses consistently ({observed idioms, e.g. `i`, `ctx`}) is fine.
## Comments & Docstrings
- Density: {observed — e.g. "sparse; code self-explains, comments only for non-obvious constraints"}
- Docstrings: {observed convention — e.g. "JSDoc on exported functions" / "none"}
- What earns a comment: {observed — e.g. "a constraint the code cannot show"}
- Match the observed density — a comment states a constraint the code cannot
show; never narrate what the next line does.
- Keep comments SHORT: one plain, easy-to-read line beats a paragraph. A
comment that needs several sentences is explanation that belongs in the
change's docs, not the code. (A documented project convention requiring
fuller docstrings outranks this default.)
- Default to NO comment: add one only for a constraint the code cannot
show. No section banners, no doc-blocks restating a signature, no
narration, no restating the code in prose — delete any comment that
merely repeats what the line already says.
- A deliberate shortcut with a known ceiling carries the one allowed line,
in this project's comment syntax: `ceiling: <limit>; <trigger>` — one
per shortcut, greppable (`harness-coder.md` → Solution Selection Ladder).
## Readable by Default
- No magic values: a literal on a decision path (threshold, limit, retry
count, timeout, rate, status string) is never inlined — it becomes a
named constant per the constants convention above, and when the name
alone cannot carry what the value is or where it comes from, one short
comment at the declaration explains it. Self-explaining literals
(0, 1, "") stay literal.
- Flat control flow: guard clauses and early returns over nested
conditionals; no chained one-liner doing three things.
- Small, single-purpose functions: a block that needs its own explanation
is extracted under an intent-stating name.
- Comments are the last resort: structure the code so it explains itself
(comment rules above).
- {observed exceptions — terse idioms this codebase itself uses consistently}
## Required Patterns
{things that must always be done — each backed by observed consistency}
## Forbidden Patterns
{things never done in this codebase — each backed by observed absence}
## External Calls
- {timeout/retry/fallback conventions detected}
## Logging
- {library, format, level usage}
## Validation
- {where, how, what library}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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: 197k | Updated | Claude CodeCodex | Verified | Install |
| 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: 119k | Updated | Claude CodeCodex | Verified | Install |
| 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: 118k | Updated | Claude CodeCodex | Verified | Install |