sentry-triage

Run Fern CLI Sentry false-positive triage for buildwithfern/cli. Use when investigating Sentry CLI issues, classifying false positives, updating the triage ledger, or creating PRs for Sentry error fixes.

Quality

86%

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

81%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.

A strong operational runbook with highly actionable commands, a well-sequenced validated workflow, and good structure. Its main weakness is repetition of the 1:1 spawning rule, which inflates length without adding clarity.

Suggestions

Consolidate the strict 1:1 spawning rule into a single authoritative statement in 'Subagent Orchestration'; remove its restatements in 'Workflow Overview', the mapping table caption, and the anti-patterns to reduce repetition.

Tighten the 'Grouping Rule' section by merging the repeated rationale sentences ('Grouping should be rare...', 'Do not group just because...') into one concise principle.

If the skill is meant to ship with bundle files, add the referenced DESIGN_CHOICES.md / SUBAGENT_CONTRACT.md / scripts to the skill bundle so the progressive-disclosure split is real rather than conceptual.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and action-oriented, but the strict 1:1 spawning rule is restated roughly five times and the grouping rationale is somewhat over-explained; could be tightened.	3 / 5
Actionability	Provides copy-paste-ready commands (sentry-cli invocations, the dedupe script, jq ledger queries), an exact branch-naming scheme, and concrete Group Plan and spawn-prompt templates covering common cases.	5 / 5
Workflow Clarity	A clearly sequenced Fetch -> Ledger Filter -> Dedupe -> Grouping -> Spawn -> Reconcile flow with explicit validation checkpoints (halt on script failure, ledger collision check, sanity-check) and a re-plan feedback loop.	5 / 5
Progressive Disclosure	Well-organized overview with clear headers and one-level-deep, clearly signaled references (DESIGN_CHOICES.md, SUBAGENT_CONTRACT.md, ledger/_meta.json, scripts), though no actual bundle files ship alongside SKILL.md to verify the split.	4 / 5
	Total	17 / 20 Passed

Description

92%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 specific, well-scoped description with concrete actions, explicit when-to-use triggers, and minimal conflict risk. The only minor gap is a lack of synonyms or file extensions among the trigger terms.

Dimension	Reasoning	Score
Specificity	Names the domain plus multiple concrete actions ('classifying false positives', 'updating the triage ledger', 'creating PRs for Sentry error fixes'), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (run Sentry false-positive triage) and when, with a concrete 'Use when...' clause enumerating specific triggers.	5 / 5
Trigger Term Quality	Includes several natural trigger phrases ('investigating Sentry CLI issues', 'classifying false positives', 'creating PRs for Sentry error fixes'); a few synonyms/extensions are missing.	4 / 5
Distinctiveness Conflict Risk	A narrow, named niche (Sentry CLI false-positive triage for buildwithfern/cli) with distinct triggers and minimal overlap risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: fern-api/fern
Path: .devin/automation/sentry-triage/SKILL.md
Commit: b5df187

Reviewed: 2 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.