compiler-orchestrator

Orchestrate the Rust compiler port end-to-end. Discovers the current frontier, fixes failing passes, ports new passes, reviews, and commits in a loop.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./compiler/.claude/skills/compiler-orchestrator/SKILL.md

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and well-sequenced with strong validation feedback loops throughout the orchestration loop. Its weakest area is progressive disclosure: a large inlined pass table and log spec could be moved to reference files to keep SKILL.md a lean overview.

Suggestions

Extract the 49-row Pass Order Reference table into a referenced file (e.g. references/pass-order.md) and keep only a short summary inline, signaling the reference clearly.

Move the detailed orchestrator-log format/status spec into references/orchestrator-log-format.md, leaving a brief pointer in the main body.

Consider a references/ file documenting the subagent prompt templates so SKILL.md stays a concise orchestration overview.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes competence — it skips basic explanations and uses tight tables, commands, and numbered steps — though the 49-row pass table and some redundancy in delegation instructions could be trimmed slightly.	4 / 5
Actionability	It provides copy-paste-ready bash commands (test-rust-port.sh invocations), exact file paths, concrete subagent prompt templates with required fields, and a named commit skill, covering the common FIX/PORT/commit cases fully.	5 / 5
Workflow Clarity	The Core Loop is explicitly sequenced (Steps 1–5 with loop-back), includes re-test checkpoints after every subagent, parallel diagnosis, max-retry feedback loops (3 fix rounds / 5 port attempts), and validation-via-test before committing.	5 / 5
Progressive Disclosure	Structure is clear with sectioned headers, but there are no bundle files (references/scripts/assets) and the 49-pass reference table plus detailed log-format spec are inlined directly in SKILL.md rather than split into separate one-level-deep reference files.	3 / 5
	Total	17 / 20 Passed

Description

63%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and action-rich, clearly stating what the skill does across the full port lifecycle. Its main weakness is the absence of explicit 'when to use' trigger guidance, which caps completeness.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when advancing or resuming the Rust compiler port, or when the user asks to fix failing port passes or port the next pass.'

Include a few natural trigger phrases a user would say (e.g. 'port the next Rust compiler pass', 'fix the compiler port frontier') to broaden keyword coverage.

Optionally mention the `status` argument as a lightweight invocation trigger so users know they can query state without acting.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'Discovers the current frontier, fixes failing passes, ports new passes, reviews, and commits' — giving comprehensive coverage of the orchestrator's capabilities.	5 / 5
Completeness	It clearly answers 'what does this do' (orchestrate the port end-to-end with concrete actions) but lacks any explicit 'Use when...' or equivalent trigger guidance for when Claude should invoke it.	3 / 5
Trigger Term Quality	Terms like 'Rust compiler port', 'failing passes', and 'commits' are domain-relevant but lean technical; common user-facing synonyms or natural phrasings a user would actually say are limited.	3 / 5
Distinctiveness Conflict Risk	'Rust compiler port' plus the specific loop of discover/fix/port/review/commit carves a clear niche, with only minor overlap risk against adjacent compiler-helper skills.	4 / 5
	Total	15 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: facebook/react
Path: compiler/.claude/skills/compiler-orchestrator/SKILL.md
Commit: 7c6ac13

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.