issue-root-resolution

Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%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 exceptionally tight, actionable process skill with strong validation and feedback loops throughout. The only real weakness is that its two referenced exemplar files are missing from the stated paths, which undermines the advertised progressive disclosure.

Suggestions

Either create the referenced files at ../rdd-advisory-transport/references/shared-advisory-transport-proposal.md and issue-impact-matrix.md, or correct the paths in the References section so they resolve.

If the exemplar files are intentionally external, note their location/availability explicitly so a reader does not assume they are bundle-local and hit a dead end.

Consider inlining a one-line shape description of each exemplar so the skill remains useful even when the referenced files are unreachable.

Dimension	Reasoning	Score
Conciseness	Lean and dense throughout — every rule is directive ('Read full bodies and comments, never titles', 'Verify every claim against current origin/main the day you act') with no padding or explanation of concepts Claude already knows.	5 / 5
Actionability	Highly actionable with explicit decision rules ('Close only with evidence: (A)...(D)...'), enumerated deletion-ranking (1)(2)(3), and concrete commands ('go test ./... at the repository root'); code absence is unpenalized for an instruction skill this concrete.	5 / 5
Workflow Clarity	Execution Steps 1-6 form a clear sequence with pervasive explicit validation (re-verify on main, decoy-test new guards, audit worker reports) and feedback loops (map contradicts hypothesis -> map wins -> correct public record), satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	Body sections are well-organized, but the two References point to ../rdd-advisory-transport/references/*.md paths that do not exist, so navigation breaks at the one level of depth it advertises.	3 / 5
	Total	18 / 20 Passed

Description

83%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 that clearly states both purpose and activation conditions with bilingual synonyms. Minor compression of the action list and slight overlap risk with generic triage keep it just short of a perfect score.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Audit and resolve issue clusters by verified root cause', 'deletion-driven fix', 'mechanism map', 'close outdated issues') with only minor compression gaps; not a comprehensive 5-level enumeration.	4 / 5
Completeness	Explicitly answers both 'what' ('Audit and resolve issue clusters by verified root cause') and 'when' via a concrete 'Trigger:' clause with multiple phrases, satisfying the explicit-trigger-guidance requirement.	5 / 5
Trigger Term Quality	Good keyword coverage including bilingual synonyms ('atacar la raíz', 'resolver issues de raíz', 'close outdated issues', 'backlog roots'), though some terms like 'mechanism map' lean technical and a few natural phrasings are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (cluster-level root-cause backlog audit, distinct from single-defect flows) with specialized triggers, but terms like 'close outdated issues' and 'backlog roots' carry minor overlap risk with general issue-triage skills.	4 / 5
	Total	17 / 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: skills/issue-root-resolution/SKILL.md
Commit: d96a5d4

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.