CtrlK
BlogDocsLog inGet started
Tessl Logo

local-log-debug

Inspect and analyze uniclipboard's local JSONL logs on a SINGLE machine — query, filter, and time-merge the per-role (gui/daemon/cli) log files to answer "what just happened" or trace a symptom (pairing, sync, transfer, clipboard capture, daemon lifecycle) back through the logs. Use when the user asks to "check the logs", "why did X fail", "what did the daemon do", or describes a bug to diagnose from logs on this one host. NOT for cross-device peer debugging (use dual-side-debug) and NOT for writing/reviewing tracing code (use tracing-best-practices).

76

Quality

95%

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

88%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, well-sequenced debugging guide with copy-paste commands, a validated status-first workflow, and genuinely non-obvious domain knowledge (UTC filename dates, profile resolution, UC_LOG_DIR escape hatch). The only deductions are minor: a few trimmable passages, a stray unclosed ```text fence at the end of the file, and no progressive-disclosure split despite ~200 lines of inline reference material.

Suggestions

Remove the stray unclosed ```text code fence at the very end of the body (after the 'Things to avoid' list) — it is a formatting artifact that may render trailing content as code.

Consider moving the jq cookbook and subsystem target/span cheat-sheet into a one-level-deep references file (e.g. references/query-cookbook.md) to keep SKILL.md a lean overview while preserving the detail on demand.

Trim the opening paragraph, which largely restates the frontmatter description, and tighten the pre-split-layout warning to its load-bearing fact (old single-file path is wrong for this skill).

DimensionReasoningScore

Conciseness

The body is dense and assumes competence (no explaining what JSONL or tracing is; aphorisms like "logs are observability, not state" carry real guidance), but there are minor instances that could be trimmed: the opening paragraph restates the frontmatter description, and the pre-split-layout warning paragraph runs long. This sits between the 4 anchor ('efficient, minor over-explanation') and the 5 anchor ('every token earns its place'), noticeably above the midpoint.

4 / 5

Actionability

Fully executable throughout: exact invocation path (`.agents/skills/local-log-debug/uc-logs.sh <command>`), a command table with defaults (`--lines N` default 50, `--profile` default `dev`), copy-paste jq filters, and real target/span strings seeded from actual logs. Covers the common cases (status, grep, query, merge) exactly as the top anchor requires.

5 / 5

Workflow Clarity

The 'Recommended workflow' is a clearly sequenced 5-step process with explicit validation checkpoints: run `status` first, judge per-role freshness, and "stop and confirm the profile before drawing conclusions. Don't silently analyze stale logs" — a real error-recovery feedback loop. The read-only nature of the task means the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

Well-organized single-file structure with clear section headers, decision tables, and a script as the single entry point — but everything is inline in one ~200-line file, including reference-grade material (the jq cookbook and the subsystem cheat-sheet) that could live in a one-level-deep reference file. This matches the 4 anchor ('good structure, most content appropriately placed, minor organization gaps') rather than the 5 anchor's explicit split into referenced files; it is well above the 3 anchor since nothing is buried or nested.

4 / 5

Total

18

/

20

Passed

Description

100%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.

An exemplary description: concrete actions, natural trigger phrasing covering both what and when, and explicit boundaries that redirect the two most likely confused skills. It is long but every clause earns its place; no padding or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "query, filter, and time-merge the per-role (gui/daemon/cli) log files" — and enumerates the symptom domains covered ("pairing, sync, transfer, clipboard capture, daemon lifecycle"), giving comprehensive coverage of what the skill does. It is dense with signal rather than padded, so it is not the 4 anchor's 'minor gaps in coverage'.

5 / 5

Completeness

Explicitly answers both: what ("Inspect and analyze uniclipboard's local JSONL logs ... query, filter, and time-merge") and when ("Use when the user asks to 'check the logs' ... or describes a bug to diagnose"), with concrete trigger phrases exactly as the 5 anchor requires. The negative triggers ("NOT for cross-device peer debugging") further sharpen the when.

5 / 5

Trigger Term Quality

Includes natural phrases users would actually say — "check the logs", "why did X fail", "what did the daemon do", "describes a bug to diagnose from logs" — covering the question, symptom, and imperative phrasings. Coverage is comprehensive with natural variations, matching the top anchor; nothing common is missing.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (local logs on a SINGLE machine) and explicitly disambiguates adjacent skills — "NOT for cross-device peer debugging (use dual-side-debug) and NOT for writing/reviewing tracing code (use tracing-best-practices)"). Minimal conflict risk; the 4 anchor's 'minor overlap risk' does not apply because the overlaps are named and redirected.

5 / 5

Total

20

/

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
UniClipboard/UniClipboard
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.