resolve-findings

Resolve findings by implementing the chosen fix path in code, tests, or docs. Accept optional `path` and a `priority` selector; by default resolve only the next highest remaining priority bucket, in order `P0`, `P1`, `P2`, `P3`. Also accept explicit levels or `all`. Default to `path=infer`. Confirm effective variables before starting.

Quality

73%

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 ./.agents/skills/resolve-findings/SKILL.md

Quality

Content

75%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 procedural skill with concrete file references, a clear readiness gate, and a validation step. The main gaps are a missing explicit retry feedback loop after re-running checks and slightly vague verification guidance in step 5.

Suggestions

Make step 5 a closed feedback loop: 'Re-run targeted checks; if any fail, fix and re-run until green before updating the findings record.'

Tighten the redundancy between the Priority/Path Input sections and Workflow step 1 by stating the variable-confirmation once in the workflow and referencing it from the input sections.

Specify what 'targeted checks' means concretely (e.g., which verification vs. validation pass per finding type) to lift actionability.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and never explains known concepts; the only tighten-able redundancy is between the Priority/Path Input sections and Workflow step 1's 'Confirm the effective variables first', placing it just below the every-token-earns-its-place anchor 5.	4 / 5
Actionability	Concrete guidance includes 'Use path/findings.md', the explicit P0–P3 bucket order, and 'Move findings between open and closed sections, preserve notes and open questions ordering'; the vague 'narrowest useful verification or validation pass' in step 5 is a minor gap keeping it below fully-executable anchor 5.	4 / 5
Workflow Clarity	A clear 6-step numbered sequence includes a readiness checkpoint ('Check readiness before coding … ask the next follow-up question before editing') and a validation step ('Re-run targeted checks'), but step 5 lacks an explicit 'if checks fail, fix and retry' feedback loop — a minor validation gap for a destructive/batch skill, so anchor 4 fits better than 5.	4 / 5
Progressive Disclosure	Well-organized sections (Role, Priority Input, Path Input, Workflow, Rules) and one-level-deep references clearly signaled at the top ('../shared/references/findings.schema.md', 'findings.lifecycle.md'); the relative ../shared paths and inlined input handling are minor organization gaps versus the clean one-level-deep anchor 5.	4 / 5
	Total	16 / 20 Passed

Description

58%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 states a clear, concrete 'what' and a distinctive priority-bucket mechanism, but it omits any 'when to use' trigger guidance and relies on domain jargon without natural user-facing synonyms. Adding an explicit 'Use when…' clause with natural trigger phrases would raise completeness and trigger_term_quality.

Suggestions

Append a 'Use when…' clause naming natural trigger phrases (e.g., 'Use when the user asks to resolve, fix, or close findings from a findings record, or to work through P0–P3 priority buckets').

Add user-facing synonyms and any relevant file extensions alongside the jargon (e.g., 'findings', 'fixes', 'open issues', 'findings.md') to improve trigger_term_quality.

Lead with the core capability before parameter mechanics so the 'what' reads as comprehensive rather than parameter-heavy.

Dimension	Reasoning	Score
Specificity	Quotes 'implementing the chosen fix path in code, tests, or docs' and 'resolve only the next highest remaining priority bucket, in order P0, P1, P2, P3' — several concrete actions, but it is one capability with parameter detail rather than the broad multi-capability coverage of anchor 5.	4 / 5
Completeness	A clear 'what' is present ('Resolve findings by implementing the chosen fix path in code, tests, or docs') but there is no 'Use when…' clause or equivalent trigger guidance; per the rubric guideline a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Terms 'resolve findings', 'fix path', 'priority', 'P0/P1/P2/P3' are relevant domain keywords a user in this workflow might say, but no synonyms, file extensions, or natural variations are present, matching anchor 3 rather than the comprehensive coverage of 4-5.	3 / 5
Distinctiveness Conflict Risk	The findings-record plus priority-bucket (P0–P3) niche is mostly distinct with minimal conflict risk, though 'resolve findings in code, tests, or docs' lightly overlaps general coding skills, fitting anchor 4 rather than the clear-niche anchor 5.	4 / 5
	Total	14 / 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: Agenta-AI/agenta
Path: .agents/skills/resolve-findings/SKILL.md
Commit: 7a975fb

Reviewed: 3 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.