CtrlK
BlogDocsLog inGet started
Tessl Logo

hunt-a-prod-error

A user saw internal_error, "Unexpected server error", a 500, or an opaque failure in a shipped OpenWork build. Find the cause from local logs and Sentry, name the regressing PR, file the issue, and reply where it was reported.

71

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

90%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 tight, highly actionable prod-error hunting workflow with executable commands and a clear sequence. The main gap is the absence of explicit error-recovery feedback loops in the early investigative steps.

Suggestions

Add a short validate→retry loop for the Sentry/log correlation (e.g. 'if firstSeen yields no matching commit, widen --since to 5d and re-check').

Spell out a concrete fallback when the asar-extracted server.js does not match the stack's source lines (e.g. check release tag vs. local HEAD).

DimensionReasoningScore

Conciseness

Lean and dense — assumes Claude knows OTLP, Sentry, asar, and undici without explaining them, and every line (log paths, the tally one-liner, the blind-spot caveat) earns its place.

5 / 5

Actionability

Provides copy-paste-ready commands — the rg|python3 5xx tally, the asar extract-file command, exact Sentry tags and org/project/region — covering the common cases concretely.

5 / 5

Workflow Clarity

A clear five-step sequence with checkpoints ('Confirm the shipped code matches source before reasoning about it', the Bun/undici repro gate), but lacks explicit validate→fix→retry recovery loops for the log and Sentry steps.

4 / 5

Progressive Disclosure

Well organized into five numbered sections with nothing bloating the file that belongs elsewhere; no bundle files exist, so all guidance is appropriately inline with clear navigation.

4 / 5

Total

18

/

20

Passed

Description

83%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 strong, specific description that names concrete actions and exact error strings a user would report. It would score higher on completeness by adopting an explicit 'Use when...' trigger clause alongside the scenario framing.

Suggestions

Add an explicit 'Use when a user reports internal_error, a 500, or an opaque server failure in a shipped OpenWork build' clause to make the trigger unambiguous.

Include a couple of broader natural trigger phrases (e.g. 'production error', 'server crash') to widen the match surface for user reporting.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'Find the cause from local logs and Sentry', 'name the regressing PR', 'file the issue', and 'reply where it was reported' — giving comprehensive coverage of the task.

5 / 5

Completeness

Answers both what (find cause, name PR, file, reply) and when (a user saw one of the listed errors in a shipped OpenWork build), but the trigger is phrased as a scenario rather than an explicit 'Use when...' clause.

4 / 5

Trigger Term Quality

Includes the exact user-facing strings ('internal_error', 'Unexpected server error', 'a 500', 'opaque failure') that a reporter would paste, but omits broader natural variations like 'production bug' or 'server is down'.

4 / 5

Distinctiveness Conflict Risk

Targets a narrow niche — opaque failures in shipped OpenWork builds, cross-referencing local logs and Sentry — with trigger strings unlikely to match unrelated skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

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
different-ai/openwork
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.