code-oss-logs

Find and read timestamped process logs from Code OSS dev builds, including main.log, renderer.log, extension host logs, and agenthost.log. For bundles produced by Export Agent Host Debug Logs, use agent-host-logs.

Quality

76%

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 ./.github/skills/code-oss-logs/SKILL.md

The canonical home for this skill is code-oss-logs in microsoft/vscode

Quality

Content

82%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 highly actionable, information-dense skill body: executable commands, a use-case routing table, and a complete directory map. Weaknesses are minor — slight redundancy between the console-forwarding section and the tips, and no explicit error-recovery loops in the main procedure.

Suggestions

Add a brief fallback step to the Procedure for when the expected log folder or file is missing (e.g., check the launch command's --user-data-dir, or fall back to `find ... -size +0`).

Consolidate the console-forwarding workflow and the related Tips bullets, which restate the same forwarding/probe guidance.

Consider moving the full directory-layout tree or the console-forwarding workflow into a one-level-deep reference file to keep SKILL.md a leaner overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (directory tree, use-case table, commands — no explanation of what logs or Electron are), but there is minor redundancy: the "Temporary Console Forwarding Workflow" section and several "Tips" bullets cover overlapping console-probe ground that could be trimmed or merged.	4 / 5
Actionability	Fully executable, copy-paste-ready commands throughout: `ls -lt "$HOME/.vscode-oss-dev/logs" \| head -5`, `tail -50 "<timestamp>/window1/renderer.log"`, `rg -n "MY_PROBE\|error" "<timestamp>"`, `find "<timestamp>" -type f -size +0 -print`, plus a concrete code edit for enabling console forwarding — the common cases (find latest run, read a log, search a run) are all directly covered.	5 / 5
Workflow Clarity	The Procedure is a clear 4-step sequence with a fallback for custom user-data-dirs, and the console-forwarding workflow ends with an explicit restore/cleanup checkpoint ("Before finishing, restore the flag to its default-off state and remove every temporary console.log probe"). It falls short of anchor 5 only because the main reading procedure lacks explicit validation feedback loops (e.g., what to do if the logs dir is empty or the expected file doesn't exist).	4 / 5
Progressive Disclosure	No bundle files exist (no references/, scripts/, or assets/), and the body is well-organized with clear section headers, tables, and code blocks. However, at ~130 lines with large self-contained reference blocks (the full directory-layout tree and the console-forwarding workflow), some content could arguably be split into one-level-deep reference files — good structure with minor organization gaps.	4 / 5
	Total	17 / 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 strong, specific description with good trigger keywords and excellent distinctiveness (including explicit disambiguation toward a sibling skill). Its main weakness is the absence of a 'Use when...' trigger clause, which caps completeness at 3.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks about Code OSS or Agents app logs, dev-run logs, or specific log files like main.log or renderer.log."

Include a few natural synonyms users might say, such as "log files" or "dev logs", to broaden trigger matching.

Consider mentioning the Agents app in the description body since the skill's content also covers it.

Dimension	Reasoning	Score
Specificity	"Find and read timestamped process logs" names the domain with concrete actions, and the enumeration "main.log, renderer.log, extension host logs, and agenthost.log" is highly specific, but there are only two distinct action verbs (find, read) — closer to 'several specific actions; minor gaps' than the comprehensive multi-action anchor 5.	4 / 5
Completeness	The 'what' is clear ("Find and read timestamped process logs from Code OSS dev builds"), but there is no 'Use when...' clause or equivalent explicit trigger guidance; the final sentence only disambiguates toward agent-host-logs, so completeness is capped at 3 per the guidelines.	3 / 5
Trigger Term Quality	Natural terms a user would say are present ("Code OSS", "dev builds", "main.log", "renderer.log", "agenthost.log", "Export Agent Host Debug Logs"), but common variations like "log files", "Agents app logs", or "vscode logs" are missing — good coverage with a few natural terms absent.	4 / 5
Distinctiveness Conflict Risk	It carves out a clear niche ("Code OSS dev builds" with named log files) and explicitly redirects overlapping cases ("For bundles produced by Export Agent Host Debug Logs, use agent-host-logs"), giving minimal conflict risk with other skills.	5 / 5
	Total	16 / 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: posit-dev/positron
Path: .github/skills/code-oss-logs/SKILL.md
Commit: b0258bc

Reviewed: 5 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.