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

92%

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

85%

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

A dense, highly actionable orientation skill with concrete commands, a clear sequenced discovery workflow, and well-organized sections. Its only real weakness is a bare time-sensitive date in the intro that the conciseness rubric penalizes.

Suggestions

Move the 'verified against HEAD on 2026-07-02' stamp out of the intro into a short 'Last verified' provenance line or an 'old patterns' section so time-sensitive info doesn't sit in the main orientation prose.

Group the inline stale-doc warnings ('RecoveryRequired is a legacy status', 'root CLAUDE.md still points there') into a small 'Stale/legacy references' subsection so 'Where things go' stays focused on current architecture.

Consider breaking the long single-sentence canonical request-flow chain into a short labeled list or a dedicated 'Request flow' reference so the overview stays skimmable.

Dimension	Reasoning	Score
Conciseness	Mostly lean with no concept over-explanation, but the bare time-sensitive date 'verified against HEAD on 2026-07-02' sits in the intro rather than a provenance/deprecated section, which the rubric penalizes.	2 / 3
Actionability	Provides copy-paste-ready commands (`bash scripts/codebase-graph.sh status`, `grep -rl "<crate_name>" crates/*/Cargo.toml Cargo.toml`) and exact crate paths and patterns (`include_str!` in the owning crate).	3 / 3
Workflow Clarity	The 'Discovery procedure' is a numbered 4-step sequence with an explicit FRESH/stale branch, a 'fall back immediately and note it' recovery checkpoint, and a 'verify crate status before building on it' validation grep.	3 / 3
Progressive Disclosure	No bundle files are needed; the under-50-line body is organized into clear labeled sections (Where things go, legacy enclave, discovery procedure, sibling skills) per the simple-skill allowance.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 precise, trigger-rich description tightly scoped to the IronClaw repo, with concrete actions and an explicit 'Use when' clause. It clearly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'deciding where a feature/fix/prompt/doc belongs', 'tracing how a request flows', 'looking up which crate owns a subsystem' — rather than vague language.	3 / 3
Completeness	Opens with an explicit 'Use when' clause and the trigger actions double as the skill's capabilities (orient, locate, trace), answering both what and when.	3 / 3
Trigger Term Quality	Covers natural phrases a developer would say ('starting work in the IronClaw repo', 'where a feature belongs', 'docs seem stale, missing, or contradictory') with good variation.	3 / 3
Distinctiveness Conflict Risk	Scoped to the IronClaw repo with niche triggers (crate ownership, request-flow tracing, stale docs), making conflict with generic skills unlikely.	3 / 3
	Total	12 / 12 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: 1 missing	Warning

	Total	15 / 16 Passed

Repository: nearai/ironclaw
Path: .claude/skills/ironclaw-reborn-orientation/SKILL.md
Commit: b60038b

Reviewed: 2 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.