rdd-defect-workflow

Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.

Quality

76%

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 ./internal/assets/skills/rdd-defect-workflow/SKILL.md

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.

The body is a lean, well-structured workflow with concrete rules, a decision table, and explicit validation gates; its main weakness is a few unexplained tool references (CodeGraph, source-mutating normalization) that lack executable specifics.

Suggestions

For "CodeGraph-first impact mapping" and "source-mutating normalization", add the concrete command or a one-line pointer to how they are invoked so the guidance is fully executable.

Make the validation feedback loop explicit (validate -> on failure, fix candidate -> re-validate) rather than only stating findings require a new candidate.

Clarify the kill-switch check with the exact signal/source to inspect (e.g., a specific config key or file) so step 1 is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is dense and terse throughout — compact imperative rules, a decision-gate table, and numbered steps with no padding and no explanation of concepts Claude already knows, matching the lean-and-efficient anchor where every token earns its place.	5 / 5
Actionability	Guidance is concrete and specific for an instruction-only skill ("hard limit is 400 additions plus deletions", "Require an approved issue (status:approved)", "dedicated worktree", explicit output fields), but a few directives like "CodeGraph-first impact mapping" and "source-mutating normalization" name tools/processes without giving executable commands, leaving minor gaps.	4 / 5
Workflow Clarity	Execution Steps give a clear 1-5 sequence and the Decision Gates table plus read-only validation form explicit checkpoints with a feedback path ("findings require a new candidate"), but the validate->fix->retry loop is implicit rather than spelled out, fitting the "most checkpoints present, minor gaps" anchor.	4 / 5
Progressive Disclosure	The body is under 50 lines, needs no external references, and is organized into well-labeled sections (Activation Contract, Hard Rules, Decision Gates, Execution Steps, Output Contract, References), meeting the simple-skill exception for a top score.	5 / 5
	Total	18 / 20 Passed

Description

66%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 explicitly signals triggers and targets a distinctive niche, but its capability statement ("Guide work") is vague and the keyword dump is jargon-heavy rather than natural user phrasing.

Suggestions

Replace the generic "Guide work" with 2-3 concrete verbs describing what the skill actually does (e.g., "orchestrate receipt-driven defect reviews", "enforce correction and rollback gates").

Soften jargon trigger terms into phrases a user would naturally type, and add common synonyms/extensions alongside "RDD".

Lead with a clear capability sentence before the trigger list so the "what" is as explicit as the "when".

Dimension	Reasoning	Score
Specificity	The description names the RDD domain and several concrete concepts ("review authority", "receipt/lineage", "correction/recovery", "delivery gate/kill switch", "bounded review defects"), but the only action verb is the generic "Guide work", so capabilities are named yet not comprehensive.	3 / 5
Completeness	Both elements are present: an explicit "Trigger:" clause answers "when", and "Guide work" plus the domain list answers "what"; the "what" is vague, fitting the anchor where one of the two could be more explicit.	4 / 5
Trigger Term Quality	It lists several relevant domain keywords ("RDD", "receipt-driven development", "review authority", "kill switch"), but the terms are heavily jargon-laden and a user is unlikely to naturally say phrases like "bounded review defects" or "delivery gate/kill switch", so common natural variations are missing.	3 / 5
Distinctiveness Conflict Risk	The RDD/receipt-driven-development niche with its distinctive trigger terms (kill switch, bounded review defects, receipt/lineage) is highly specific and unlikely to fire for an unrelated skill, matching the clear-niche anchor.	5 / 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: Gentleman-Programming/gentle-ai
Path: internal/assets/skills/rdd-defect-workflow/SKILL.md
Commit: 71cf25f

Reviewed: 4 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.