triage-findings

Coordinate findings work with the user, decide whether scan, test, or sync should run, and turn the current findings set into a ready plan. Accept optional `path` and GitHub PR `url`; 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/triage-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 well-structured, lean instruction-only skill with a clear numbered workflow and concrete named artifacts; it sits just below top marks because of minor description/body redundancy, implicit decision criteria, and non-navigable reference links.

Suggestions

Add brief decision criteria for choosing between scan-codebase, test-codebase, sync-findings, and resolve-findings so the triage decision is actionable rather than left to judgment.

Make the shared references navigable markdown links and confirm the referenced files (findings.schema.md, findings.lifecycle.md) exist at the stated ../shared/references/ path.

Drop the redundant 'Default:' restatements in the URL Input and Path Input sections since the same defaults appear in the description.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and never explains background concepts, but the URL Input / Path Input sections restate the defaults already in the description, leaving minor trimmable redundancy that keeps it just below a 5.	4 / 5
Actionability	Guidance is concrete for an instruction-only skill — it names the exact sibling skills (scan-codebase, test-codebase, sync-findings, resolve-findings), the exact file (path/findings.md), and the variables to confirm — with the minor gap that criteria for choosing between scan/test/sync/resolve are left implicit.	4 / 5
Workflow Clarity	A clearly numbered 5-step sequence with an effective-variables checkpoint and a 'produce a ready plan' gate is present; this is a discussion/planning skill so the destructive/batch validation cap does not apply, and it lacks the explicit error-recovery feedback loops needed for a 5.	4 / 5
Progressive Disclosure	Sections (Role, URL Input, Path Input, Workflow, Rules) are well organized and the two shared references are signaled one level deep at the top, but the referenced paths are plain backtick strings rather than navigable links and could not be verified to exist in the local bundle, keeping it just under a 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 conveys concrete actions and a distinct triage role in lean third-person voice, but omits any explicit "Use when..." trigger guidance and relies on workflow-internal jargon rather than natural user phrases.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases (e.g., 'Use when the user wants to triage findings, decide the next findings step, or plan scan/test/sync work').

Include user-facing synonyms and variations (e.g., 'triage', 'what should I run next', 'findings review') alongside scan/test/sync so the trigger terms match what users actually say.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Coordinate findings work", "decide whether scan, test, or sync should run", "turn the current findings set into a ready plan", "Confirm effective variables" — with only minor gaps in coverage, fitting the score-4 anchor better than the comprehensive score-5 example.	4 / 5
Completeness	The description gives a clear "what" but no explicit "when"/trigger guidance; per the rubric, a missing "Use when..." clause caps completeness at 3, and it is not vague enough to fall to 2.	3 / 5
Trigger Term Quality	Domain terms like "findings", "scan", "test", "sync" are present but these are workflow-internal labels rather than the natural phrases a user would utter, and no "Use when..." clause or synonyms/extensions appear, matching the score-3 anchor (relevant keywords, missing common variations).	3 / 5
Distinctiveness Conflict Risk	The triage niche (deciding between scan/test/sync/resolve) is mostly distinct, with only minor overlap risk against the sibling skills it dispatches to, fitting the score-4 anchor rather than the clearly-niched score-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/triage-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.