ironclaw-reborn-orientation

Use when starting work in the IronClaw repo, deciding where a feature/fix/prompt/doc belongs, tracing how a request flows, looking up which crate owns a subsystem, or when repo docs, the knowledge graph, or component names seem stale, missing, or contradictory.

Quality

82%

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

Quality

Content

86%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.

A lean, highly actionable orientation skill that gives executable greps and a clear fallback-driven discovery procedure without over-explaining concepts Claude already knows. The only meaningful drag is a time-sensitive audit date placed outside a deprecated section.

Dimension	Reasoning	Score
Conciseness	Dense and information-rich with little padding, but the time-sensitive 'verified against HEAD on 2026-07-02' date sits in the intro rather than a deprecated/old-patterns section, and a few framing asides ('The repo's own docs drift...') could be trimmed, keeping it below a 5.	4 / 5
Actionability	Multiple copy-paste-ready, executable commands cover the common cases — 'grep -rl --include=Cargo.toml "<crate_name>" crates/ Cargo.toml', 'ls -d crates///prompts ...', 'python3 scripts/ci/docs_publication_boundary.py', 'bash scripts/codebase-graph.sh status' — alongside concrete class/service names in the flow map.	5 / 5
Workflow Clarity	The numbered Discovery procedure is a clear sequence with an explicit fallback ('fall back immediately', 'note the fallback in your report; do not retry the graph'), but it lacks a formal validate→fix→retry loop; orientation work does not trigger the destructive/batch cap, so this lands at 4 rather than 3.	4 / 5
Progressive Disclosure	Under 50 lines with no bundle files needed and clear section headers (Where things go, There is no legacy enclave, Discovery procedure, Two skill systems, Sibling skills); sibling-skill and rules pointers are appropriately one level deep, satisfying the simple-skill exception.	5 / 5
	Total	18 / 20 Passed

Description

78%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.

A strong, trigger-rich description anchored to a specific repo, clearly answering when to use the skill and staying distinct from sibling skills. The main weakness is that capabilities are implied via triggers rather than stated as explicit action verbs.

Dimension	Reasoning	Score
Specificity	Lists several concrete activities — 'deciding where a feature/fix/prompt/doc belongs', 'tracing how a request flows', 'looking up which crate owns a subsystem' — but they are framed as trigger conditions rather than explicit capability verbs, leaving minor gaps in coverage.	4 / 5
Completeness	Has an explicit, specific 'Use when...' clause answering 'when' thoroughly; the 'what' (orientation/placement/ownership lookup) is conveyed through the trigger list rather than stated as a standalone capability, so it is not a clean 5.	4 / 5
Trigger Term Quality	Natural developer phrases like 'starting work in the IronClaw repo', 'tracing how a request flows', and 'docs... stale, missing, or contradictory' are well covered, though common synonyms like 'navigate the codebase' or 'find where code lives' are absent.	4 / 5
Distinctiveness Conflict Risk	Scoped to the 'IronClaw repo' with references to the knowledge graph, crates, and drift detection — a clear niche with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 2 missing, 1 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: nearai/ironclaw
Path: .claude/skills/ironclaw-reborn-orientation/SKILL.md
Commit: b0b999d

Reviewed: 11 hours 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.