Architect Spec
Write an implementation spec for a hard issue. Read compiler source, identify exact functions/lines, design the fix, document edge cases.
Get the complete skill folder, including its scripts and reference files.
When to use this skill
Use Architect Spec when an AI agent needs a reusable SKILL.md workflow for this job: Write an implementation spec for a hard issue. Read compiler source, identify exact functions/lines, design the fix, document edge cases.
When not to use it
Skip Architect Spec when the task is outside the coding category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.
How to install
Where will you use it?
mkdir -p ~/.claude/skills/architect-spec # Save SKILL.md to ~/.claude/skills/architect-spec/SKILL.md
- Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/architect-spec/SKILL.md. For a shared project, commit the folder at .claude/skills/architect-spec/ instead.
- Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
- For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.
Full install guide for Claude, Cursor, and Codex →
Try a starter prompt
After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.
Use the Architect Spec skill for this task: Use Architect Spec when this documented workflow matches the task. Confirm any required inputs or files before making changes.
What supports this recommendation?
69/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.
- Documentation
- 74/100
- Practical detail
- 68/100
- Source evidence
- 58/100
- Source signals
- 72/100
Model compatibility evidence
- claudeinferred
The skill text mentions Claude or a closely associated term. This is keyword-derived compatibility; no hands-on model test is recorded.
- chatgptuntested
No model-specific signal or recorded compatibility test was found.
- geminiuntested
No model-specific signal or recorded compatibility test was found.
- copilotuntested
No model-specific signal or recorded compatibility test was found.
- llamauntested
No model-specific signal or recorded compatibility test was found.
- perplexityuntested
No model-specific signal or recorded compatibility test was found.
- mistraluntested
No model-specific signal or recorded compatibility test was found.
- grokuntested
No model-specific signal or recorded compatibility test was found.
Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.
What this skill does
# Write Implementation Spec
Any agent can use this skill to produce an architect-quality implementation plan for an issue.
## Steps
1. Read the issue file at `plan/issues/{N}.md`
2. For each sub-pattern in the issue, find the codegen function: ```bash # Search for relevant function names grep -n "function compile.*{keyword}" src/codegen/*.ts # Or search for the Wasm instruction that's wrong grep -n "{wasm_op}" src/codegen/*.ts ```
3. Read the function and understand current behavior (what it emits and why it's wrong)
4. Design the fix — what instructions should be emitted instead
5. Write the spec in the issue file under `## Implementation Plan`:
```markdown ## Implementation Plan
### Root cause [1-2 sentences]
### Work Item {letter}: {title} (~{N} CE) **Patterns addressed**: {which sub-patterns from the breakdown} **Risk**: {Low|Medium|High} — {why} **Priority**: {1st|2nd|3rd}
#### Root cause {specific function and line that emits wrong instructions}
#### Changes **File: `src/codegen/{file}.ts`** - Function `{name}` (line ~{N}) - {what to change and why}
#### Edge cases - {case 1} - {case 2}
#### Test {specific test262 file to verify: before fix = CE, after fix = pass or runtime error} ```
6. Recommend which work items to do first (highest impact, lowest risk)
## Principles
- Every fix should be ~10-20 lines, purely additive - No new repair passes — extend existing logic - No instruction stream restructuring - Each work item independently testable - Prefer compile-time fixes over post-hoc repairs
Intended uses
- Use Architect Spec when this documented workflow matches the task.
Implementation notes
- Review the source instructions and adapt inputs before running the workflow.
Try it, then tell us how it went
A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.