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

61%

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

77%

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

The body is concise, well-sequenced, and includes an explicit readiness checkpoint plus a verification step, giving strong conciseness and workflow clarity. Actionability and progressive disclosure lag: guidance stays at the instructive level without executable specifics, and the shared reference files it cites are not present in the bundle.

Suggestions

Add concrete, executable detail to the implementation step — e.g. an example findings-record snippet and the exact edit/move semantics (section headers, status markers) so the guidance is copy-paste ready.

Provide inline minimal schema/context for the findings record (or confirm the shared reference files exist) so the cited ../shared/references/*.md paths resolve and progressive disclosure is verifiable.

Specify the 'targeted checks' to re-run with an example invocation or selection rule, turning the verification step from direction into an actionable command.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it states behaviors and rules without explaining what findings, priority buckets, or validation are, so every token earns its place.	3 / 3
Actionability	Steps are concrete in intent ('Use path/findings.md', 'Move findings between open and closed sections') but lack executable specifics (no commands, no file-edit mechanics, no concrete record-format examples), leaving guidance instructive rather than copy-paste ready.	2 / 3
Workflow Clarity	A clear six-step sequence with an explicit readiness/checkpoint gate ('If the intended resolution path... is still ambiguous, ask the next follow-up question before editing') and a verification step ('Re-run targeted checks'), which matches the explicit-checkpoint anchor.	3 / 3
Progressive Disclosure	It points to two shared references, but those references (../shared/references/findings.schema.md, findings.lifecycle.md) do not exist in the bundle, so the navigation is not verified one-level-deep and is only weakly signaled inline.	2 / 3
	Total	10 / 12 Passed

Description

45%

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 specific about actions and inputs but reads as an internal spec rather than a user-facing trigger: it lacks a 'Use when...' clause and relies on jargon ('priority bucket', 'P0-P3') that users would not naturally say. Completeness and trigger-term quality are the main weaknesses.

Suggestions

Add an explicit 'Use when...' clause with natural user-facing triggers, e.g. 'Use when the user asks to fix, resolve, or address open findings from a review.'

Replace or gloss internal jargon ('priority bucket', 'P0-P3') with common terms like 'highest-priority findings' or 'critical, high, medium, low issues' so the description triggers on natural phrasing.

State the activation moment concisely to separate this skill from general coding (e.g. 'Use after a findings record exists and the user wants chosen fixes implemented').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('implementing the chosen fix path in code, tests, or docs', 'update the active findings record') and concrete inputs/behaviors (priority selector, P0-P3 buckets, path inference), matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly states what the skill does, but 'when' guidance is absent — there is no explicit 'Use when...' clause or equivalent trigger telling Claude when to invoke it, which the guidelines cap at 2.	2 / 3
Trigger Term Quality	It uses internal jargon ('priority bucket', 'findings record', 'P0-P3') rather than natural terms a user would say; there is no 'Use when...' phrasing or common user keywords like 'fix findings', 'resolve issues', or 'apply fixes'.	1 / 3
Distinctiveness Conflict Risk	It has a recognizable niche ('resolve findings' vs authoring them), but the generic notion of 'implementing fixes in code, tests, or docs' could overlap with general coding or other remediation skills, leaving it somewhat conflict-prone.	2 / 3
	Total	8 / 12 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: 93872a6

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.