reborn-extension-surfaces

Use when adding or changing a Reborn integration — a new extension, a channel surface, model-callable tools, or a shared auth provider — or when deciding whether something is "a channel", "an extension", or "a tool". Maps the unified extension model (NEA-25) to the exact manifest sections, crates, seams, and tests.

Quality

85%

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

82%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.

An information-dense, highly actionable architectural skill with concrete commands, exemplar paths, and a final validation gate. Slightly verbose in spots and validation is concentrated at the end rather than interleaved.

Dimension	Reasoning	Score
Conciseness	Dense with high-signal crate paths, trait names, and manifest sections, assuming Claude's domain competence; minor repetition (e.g., 'implementation only, never taxonomy' appears twice) that could be trimmed.	4 / 5
Actionability	Provides executable commands (grep -c '^[[tools]]', rg -n "impl ReplySink for", cargo test -p ironclaw_architecture_tests, pnpm --dir … test) and concrete exemplar manifest/file paths to copy from.	5 / 5
Workflow Clarity	Each surface has a numbered sequence plus an explicit final validation gate ('Always finish with cargo test… the gates are the machine reviewers'); validation is end-of-flow rather than per-step, so not a 5.	4 / 5
Progressive Disclosure	Well-sectioned body with one-level-deep, clearly signaled references to deeper docs (overview §3/§4/§5, standard-operations.md, conversation-binding.md); no bundle files exist to split further.	4 / 5
	Total	17 / 20 Passed

Description

87%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, domain-specific description that clearly states what it does and when to use it with concrete trigger phrases. Minor room to expand action verbs and synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete targets ('a new extension, a channel surface, model-callable tools, or a shared auth provider') and maps the model to 'exact manifest sections, crates, seams, and tests', but the action verb is essentially a single one ('maps').	4 / 5
Completeness	Explicitly answers both: 'what' (maps the unified extension model NEA-25 to manifest sections, crates, seams, and tests) and 'when' (a concrete 'Use when…' clause with multiple trigger phrases).	5 / 5
Trigger Term Quality	Good natural-phrase coverage ('adding or changing a Reborn integration', 'new extension', 'channel surface', 'shared auth provider', deciding whether something is 'a channel', 'an extension', or 'a tool'), with a few common synonyms missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche with distinct triggers ('Reborn integration', 'NEA-25', channel/extension/tool distinction); highly unlikely to fire for an unrelated skill.	5 / 5
	Total	18 / 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: nearai/ironclaw
Path: .claude/skills/reborn-extension-surfaces/SKILL.md
Commit: b0b999d

Reviewed: 5 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.