CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sentry-automation

Automate Sentry tasks via Rube MCP (Composio): manage issues/events, configure alerts, track releases, monitor projects and teams. Always search tools first for current schemas.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/sentry-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 solid, actionable reference with clearly sequenced workflows, concrete tool slugs, and genuine pitfall knowledge (slug vs. display name, numeric issue IDs vs. UUID event IDs). The main weaknesses are the fully inlined ~230 lines of API detail that belong in progressive-disclosure reference files and the absence of example payloads or verification steps for the create/update operations.

Suggestions

Split per-domain detail (e.g., references/alerts.md, references/releases.md) out of SKILL.md, keeping the body as an overview with one-level-deep, clearly signaled references — the inlined parameter tables and Quick Reference are what hold progressive_disclosure at 3.

Add a minimal example JSON for alert-rule `conditions`/`actions`/`filters` so the most schema-fragile operation doesn't depend on 'check Sentry docs'.

Add post-creation verification steps (e.g., re-list rules to confirm the new alert exists, confirm the release appears before uploading source maps) to close the workflow validation gaps.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (no explanation of what Sentry or MCP is) and stays lean, but ID-format pitfalls are repeated per-workflow and again under 'Known Pitfalls', and the Quick Reference table re-lists tool slugs already named in the workflows.

4 / 5

Actionability

Concrete tool slugs, real parameter values (`is:unresolved`, `statsPeriod: 24h`), and a searchable query-syntax section make the guidance executable, but the alert-rule `conditions`/`actions` payloads — the most fragile inputs — get no example JSON and defer to 'check Sentry docs'.

4 / 5

Workflow Clarity

Workflows are clearly sequenced with [Required]/[Optional]/[Prerequisite] tags and an explicit setup checkpoint ('Confirm connection status shows ACTIVE before running any workflows'), plus 429 backoff guidance, but write operations like alert-rule and release creation lack post-creation verification steps.

4 / 5

Progressive Disclosure

The file is well-sectioned with headers, but it is a ~230-line single file whose per-workflow parameter details and Quick Reference table are an inlined API reference that would be better split into references/ files; no bundle files exist to offset this.

3 / 5

Total

15

/

20

Passed

Description

70%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, distinctive description that names the domain and several concrete capability areas, but it never tells Claude when to invoke it. Adding an explicit trigger clause (e.g., "Use when the user mentions Sentry, error tracking, alert rules, or release monitoring") would lift completeness to the top band.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases (e.g., 'Use when the user mentions Sentry, error tracking, crash reports, alert rules, or release deployments') to fix the missing 'when' that caps completeness at 3.

Include natural synonyms users actually say — 'error tracking', 'error monitoring', 'crash reports' — to round out trigger term coverage.

Replace generic verbs like 'manage' and 'monitor' with more concrete operations (e.g., 'list and triage issues, create alert rules, record release deploys') for full specificity.

DimensionReasoningScore

Specificity

"manage issues/events, configure alerts, track releases, monitor projects and teams" lists five concrete action areas, but the verbs (manage, monitor, track) are generic compared to the fully itemized 5-anchor.

4 / 5

Completeness

The "what" is clear (automating Sentry operations across five areas), but there is no "Use when..." clause or equivalent trigger guidance; "Always search tools first" is an execution instruction, not a trigger, so completeness is capped at 3 per the rubric.

3 / 5

Trigger Term Quality

Covers "Sentry", "issues", "events", "alerts", "releases", "projects", "teams" — good natural-term coverage, but misses common user phrasings like "error tracking", "error monitoring", or "crash reports".

4 / 5

Distinctiveness Conflict Risk

"Sentry" scoped via "Rube MCP (Composio)" carves out a clear niche with distinct triggers and minimal conflict risk with any other skill domain.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

davepoon/buildwithclaude

Path

plugins/all-skills/skills/sentry-automation/SKILL.md

Reviewed

Table of Contents

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.