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

96%

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%

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

A highly actionable, lean, and well-sequenced orchestration workflow with concrete commands and explicit validation checkpoints. The only weak spot is progressive disclosure: two referenced files are not present in the bundle and the body is long and inline.

Suggestions

Include the referenced bundle files (SUBAGENT_CONTRACT.md and DESIGN_CHOICES.md) in the bundle, or remove the links if the content is meant to be inline, so references resolve to real files.

Consider moving the detailed PR/branch naming rules and ledger field schema into a short reference file to keep SKILL.md as a lean overview, since the body is long and largely inline.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence — no explanations of what Sentry, the CLI, or ledger files are — and nearly every token earns its place, matching the lean score-3 anchor.	3 / 3
Actionability	It provides executable bash (sentry-cli queries, the ledger-filter loop, the dedupe script invocation), exact file paths, a real bundled script (scripts/find-existing-pr.sh), and concrete JSON field specs — copy-paste ready, matching the score-3 anchor.	3 / 3
Workflow Clarity	Multi-step phases are clearly sequenced (Fetch → Ledger Filter → Dedupe → Group → Spawn → Reconcile) with explicit validation checkpoints (terminal-disposition skip, "halt the run" on script failure, per-file ledger collision check) and feedback loops, matching the score-3 anchor.	3 / 3
Progressive Disclosure	It signals one-level-deep references to SUBAGENT_CONTRACT.md and DESIGN_CHOICES.md, but neither referenced file is present in the bundle (only scripts/find-existing-pr.sh exists), and the body itself is a fairly long, monolithic wall of inline procedure that could be partly split out.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 tightly scoped, third-person description with concrete actions, natural trigger terms, and an explicit Use-when clause covering both what and when. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "classifying false positives", "updating the triage ledger", "creating PRs for Sentry error fixes" — matching the score-3 anchor listing several specific concrete actions.	3 / 3
Completeness	It answers both "what" ("Run Fern CLI Sentry false-positive triage for buildwithfern/cli") and "when" with an explicit "Use when..." clause, matching the score-3 anchor.	3 / 3
Trigger Term Quality	Phrases like "investigating Sentry CLI issues", "classifying false positives", and "creating PRs for Sentry error fixes" are natural ways a user would express the need, giving good keyword coverage; it is not below 2 because it avoids jargon-only terms.	3 / 3
Distinctiveness Conflict Risk	It targets a narrow niche (Fern CLI Sentry triage for a specific org/project) with distinct triggers unlikely to conflict with other skills, and uses third person voice.	3 / 3
	Total	12 / 12 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: 134b13f

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.