reborn-feature

Build a user-facing feature in the Reborn stack with the smallest existing contract surface.

Quality

75%

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 ./.claude/skills/reborn-feature/SKILL.md

Quality

Content

92%

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

The body is dense, executable, and well-sequenced with strong validation feedback loops, scoring top marks on conciseness, actionability, and workflow clarity. Its only weakness is progressive disclosure: it is a single monolith with an unrealized script reference and no bundled detail files.

Suggestions

Either provide the referenced `scripts/codebase-graph.sh` as a bundled script or remove the reference so paths match the actual bundle structure.

Move the per-crate ownership map and boundary rules into a `references/` file (e.g. `references/ownership.md`) and link to it from the body to keep SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	Every line names a crate, descriptor type, or concrete command with no space spent explaining concepts Claude already knows; it assumes competence and leans on the codebase's own vocabulary. It matches the lean, efficient anchor where every token earns its place.	3 / 3
Actionability	It provides specific executable commands (`rg -n 'ProductSurface\|ProductView\|...' crates/...`, `cargo test -p ironclaw_product`, `cargo clippy ... -- -D warnings`), concrete file paths, and named types, all copy-paste ready for the repo. This matches the fully executable, copy-paste-ready anchor.	3 / 3
Workflow Clarity	The process is clearly sequenced (Before editing -> Default implementation -> Boundary rules -> Verification) with explicit validation checkpoints ('Run the graph status check once... verify the result against live code') and feedback loops (re-check on dependency changes, run the architecture test when ownership changes). This matches the clear-sequence-with-explicit-validation anchor.	3 / 3
Progressive Disclosure	Sections are well organized, but the body is a single self-contained monolith (~88 lines, over the 50-line simple-skill threshold) with no bundle files present, while it references `scripts/codebase-graph.sh` as though bundled. The referenced path is unrealized and detailed material (per-crate ownership map, boundary rules) stays inline, matching the anchor for some structure but content that should be separate kept inline.	2 / 3
	Total	11 / 12 Passed

Description

57%

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 distinctive and domain-specific but lacks explicit 'when to use' guidance and enumerates only a single composite action rather than multiple concrete capabilities. Adding a 'Use when...' clause and listing concrete actions (route, command, capability) would raise completeness and specificity.

Suggestions

Append an explicit trigger clause, e.g. 'Use when adding a WebUI route, product command, or capability descriptor in the Reborn stack.'

Enumerate concrete capabilities instead of one composite action, e.g. 'Add routes, product commands, capability descriptors, and frontend pages'.

Include natural user-facing terms ('route', 'command', 'endpoint', 'WebUI feature') alongside 'Reborn stack' to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ('Reborn stack') and a single composite action ('Build a user-facing feature') plus a constraint ('smallest existing contract surface'), but does not enumerate multiple concrete actions. Closer to the anchor that names domain and some actions without being comprehensive, rather than the verbose-enough score-3 example listing several specific actions.	2 / 3
Completeness	It clearly states what the skill does, but includes no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines. The 'when' is only implied, matching the anchor that has 'what' but missing or implied 'when'.	2 / 3
Trigger Term Quality	'feature' and 'user-facing' are natural trigger words a user might say, but the distinctive terms ('Reborn stack', 'contract surface') lean toward project-internal jargon and common variations like 'route', 'command', 'endpoint', or 'WebUI' are absent. It has some relevant keywords but is missing common variations.	2 / 3
Distinctiveness Conflict Risk	The 'Reborn stack' framing and 'smallest existing contract surface' qualifier carve a clear, narrow niche tied to a specific codebase, making it unlikely to trigger for unrelated skills. This matches the anchor for a clear niche with distinct triggers and low conflict risk.	3 / 3
	Total	9 / 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/reborn-feature/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.